PLANNING OF A HOST VEHICLE

FIELD OF DISCLOSURE

[0001] The present disclosure relates to the field of vehicle automation. More particularly, the present disclosure relates to system and method for planning smooth evasive movement of a host vehicle on a road based on speed and velocity of target vehicles and road conditions.

BACKGROUND OF THE DISCLOSURE

[0002] With the advent of autonomous vehicle (AV) technology, vehicles are equipped with driving controls that require less and less driver intervention. For example, an adaptive cruise control system not only maintains speed of the vehicle but also slows down the vehicle in event of a slower moving preceding vehicle (target vehicle), which is detected using sensors such as RADAR (Radio Detection and Ranging) and cameras, and autonomous parking system. Further, the vehicle is provided with steering controls for parking the vehicle.

[0003] Providing smooth and collision free maneuvering and automatic lane changing controls for the A Vs is important for driver, passenger comfort and safety. As the AV technology advances, there are more autonomous applications that are provided for the vehicles. For example, future A Vs probably shall employ autonomous systems related to lane changing, overtaking, turning away from the slow and fast moving target vehicles, turning into the slow and fast target vehicles, etc.

[0004] Prevalent maneuvering and automatic lane changing controls for the A Vs focus on generating a higher order trajectory for the host vehicle, but do not address complexities of the host vehicle’s surrounding environment. Existing technologies do not focus on evasive maneuver trajectory planning considering vehicle dynamics and surround environment, and lack focus on dynamic or online trajectory optimization or adaptation, which is useful for adapting to changing environment or surroundings of road or traffic conditions. Further, the prevalent approaches focus on planning the trajectory based on only sensor information. However due to latency in the sensor information a measured state of the target vehicle may be different from an actual state of the target vehicle leading to collision of the host vehicle and the target vehicle. Furthermore, the trajectory planning does not take into account road conditions and geometry, leading to problems for the host vehicle during evasive maneuver.

[0005] There is therefore a need in the art for system and method that can dynamically plan and adjust the trajectory for evasive maneuver of the host vehicle based on speed and velocity of the target vehicles and the road conditions, which overcomes above-mentioned and other limitations of existing approaches.

OBJECTS OF THE INVENTION

[0006] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are as listed herein below.

[0007] It is an object of the present disclosure to provide a system and method for planning an online dynamic trajectory with constraints for evasive maneuver.

[0008] It is an object of the present disclosure to provide a system and method for evasive maneuver planning of a host vehicle in an emergency condition.

[0009] It is an object of the present disclosure to provide a system and method for evasive maneuver planning of a host vehicle in an emergency condition to avoid collision. [00010] It is yet another object of the present disclosure to provide a system and method for assessing free clearance of a host vehicle’s surroundings.

[00011] It is still another object of the present disclosure to provide a system and method to adapt an evasive maneuver trajectory based on a road profile.

[00012] It is still another object of the present disclosure to dynamically adapt host vehicle trajectory based on drive passage estimation and emergency collision assessment.

SUMMARY

[00013] This summary is provided to introduce simplified concepts of a system and method for dynamic evasive trajectory planning of a host vehicle on a road, which are further described below in the Detailed Description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended for use in determining/limiting the scope of the claimed subject matter.

[00014] The present disclosure relates to the field of vehicle automation. More particularly, the present disclosure relates to system and method for planning smooth evasive movement of a host vehicle on a road considering velocity of target vehicles and the road conditions.

[00015] An aspect of the present disclosure relates to a system implemented in a host vehicle for optimizing a trajectory for the host vehicle for dynamic evasive maneuver in a drive passage, the system comprising: an input unit comprising one or more sensors mounted on the host vehicle, wherein the one or more sensors capture one or more parameters of surroundings of the host vehicle; a processing unit comprising a processor coupled with a memory, the memory storing instructions executable by the processor to: initialize an evasive maneuver trajectory for the host vehicle by receiving the one or more parameters, wherein the initialization is performed for steering the host vehicle in an emergency operation for a collision escape; determine a trajectory regression for the host vehicle and perform a target edge collision correction to avoid collision with a target vehicle, selected from one or more target vehicles, by analyzing and optimizing the trajectory of the host vehicle while keeping trajectory for evasive maneuver laterally closer to the target vehicle, wherein the target vehicle is located in front of the host vehicle and causes evasive maneuver of the host vehicle; perform a maneuvers election of the host vehicle based on a set of attributes to determine an adaptive road profile for adaptation of the trajectory for the host vehicle based on road trajectory, wherein the adaptation enables the collision escape during the evasive maneuver of the host vehicle; and perform a maneuver fusion of estimated trajectory for the target vehicle and the adapted trajectory for the host vehicle to determine a fused trajectory so that the fused trajectory is used to optimize the trajectory of the host vehicle for dynamic evasive maneuver based on the determined fused trajectory for the host vehicle.

[00016] In an embodiment, the trajectory regression for the host vehicle is determined based on any or a combination of the initialized evasive maneuver trajectory, one or more iteration constraints for a trajectory generation and the drive passage.

[00017] In an embodiment, the one or more iteration constraints for the trajectory generation comprise any or a combination of available longitudinal distance, lateral deviation, radius of curvature of the optimized trajectory and lateral acceleration of the host vehicle.

[00018] In an embodiment, the target edge collision correction is performed based on the determined trajectory regression for the host vehicle, and current position and orientation of the target vehicle. [00019] In an embodiment, the set of attributes for maneuver selection of the host vehicle comprise any or a combination of the performed target edge collision correction, the one or more parameters, motion of the host vehicle and the estimated trajectory of the target vehicle.

[00020] In an embodiment, the optimized trajectory for the host vehicle is retained as the adapted trajectory for the host vehicle when the lateral acceleration of the host vehicle reaches beyond a predefined maximum lateral acceleration, otherwise the optimized trajectory for the host vehicle is adapted to the performed maneuver fusion when the optimized trajectory falls below a lower threshold of the predefined maximum lateral acceleration.

[00021] In an embodiment, the trajectory regression determines the collision escape for the host vehicle while maintaining one or more of the lateral acceleration, radius of curvature of the trajectory and an available longitudinal distance in an estimated drive passage for trajectory planning of the host vehicle, within corresponding predefined threshold limits.

[00022] In an embodiment, the determined fused trajectory directs the host vehicle to a path on the drive passage where the host vehicle has minimum lateral deviation and escapes collision.

[00023] In an embodiment, the drive passage dynamics comprises determining any or a combination of adjacent lane availability with respect to the drive passage, a lateral and longitudinal clearance for the host vehicle, and motion of the target vehicle.

[00024] In an embodiment, the target edge collision correction determines an escape trajectory by considering any or a combination of an edge avoidance and body collision of the host vehicle with the one or more of target vehicles

[00025] In an embodiment, the processor determines the dynamic evasive maneuver trajectory of the host vehicle based on the fused and optimized trajectory.

[00026] Another aspect of the present disclosure relates to a method for optimizing a trajectory for a host vehicle for dynamic evasive maneuver in a drive passage, carried out according to instructions stored in a computer implemented in the host vehicle, comprising: receiving an input signal comprising one or more parameters of surroundings of the host vehicle from an input unit, the input unit comprising one or more one or more sensors mounted on the host vehicle; initializing an evasive maneuver trajectory for the host vehicle by receiving the one or more parameters, wherein the initialization is performed for steering the host vehicle in an emergency operation for a collision escape; determining a trajectory regression for the host vehicle and performing a target edge collision correction to avoid collision with a target vehicle, selected from one or more target vehicles, by analyzing and optimizing the trajectory of the host vehicle while keeping trajectory for evasive maneuver laterally closer to the target vehicle, wherein the target vehicle is located in front of the host vehicle and causes evasive maneuver of the host vehicle; performing a maneuver selection of the host vehicle based on a set of attributes to determine an adaptive road profile for adaptation of the trajectory for the host vehicle based on road trajectory, wherein the adaptation enables the collision escape during the evasive maneuver of the host vehicle; and performing a maneuver fusion of estimated trajectory for the target vehicle and the adapted trajectory for the host vehicle to determine a fused trajectory so that the fused trajectory is used to optimize the trajectory of the host vehicle for dynamic evasive maneuver based on the determined fused trajectory for the host vehicle.

[00027] Various objects, features, aspects and advantages of the present disclosure will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like features.

BRIEF DESCRIPTION OF DRAWINGS

[00028] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. The diagrams are for illustration only, which thus is not a limitation of the present disclosure.

[00029] FIGs. 1A-C illustrate architecture of a dynamic evasive maneuver trajectory planning system to illustrate its overall working in accordance with an embodiment of the present disclosure.

[00030] FIG. 2 illustrates exemplary functional components of a processing unit in accordance with an embodiment of the present disclosure.

[00031] FIG. 3 illustrates exemplary representation of an evasive maneuver scenario with sharp deceleration of a target vehicle in accordance with an embodiment of the present disclosure.

[00032] FIG. 4 illustrates exemplary representation for free drive passage estimation around a host vehicle in accordance with an embodiment of the present disclosure. [00033] FIG. 5 illustrates exemplary representation for regression modeling of evasive maneuver for a host vehicle in accordance with an embodiment of the present disclosure.

[00034] FIG. 6 illustrates exemplary representation of position of host vehicle during evasive maneuver phases for edge collision in accordance with an embodiment of the present disclosure.

[00035] FIG. 7 illustrates exemplary representation of a target edge collision correction in accordance with an embodiment of the present disclosure.

[00036] FIG. 8 illustrates an exemplary representation showing adaptive road profiling with respect to a transitioning from a straight line road segment to a curved road segment in accordance with an embodiment of the present disclosure.

[00037] FIG. 9 illustrates an exemplary representation of maneuver fusion illustrating fusion of trajectory waypoints of the host vehicle for evasive maneuver and the estimated positions of target vehicle in accordance with an embodiment of the present disclosure.

[00038] FIG. 10 illustrates exemplary implementation of fused trajectory optimization in accordance with an embodiment of the present disclosure.

[00039] FIG. 11 is a flow diagram illustrating a method for optimizing a trajectory for a host vehicle for dynamic evasive maneuver in a drive passage to avoid collision of the host vehicle with a target vehicle in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION

[00040] In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details.

[00041] Various methods described herein may be practiced by combining one or more machine-readable storage media containing the code according to the present invention with appropriate standard computer hardware to execute the code contained therein. An apparatus for practicing various embodiments of the present invention may involve one or more computers (or one or more processors within a single computer) and storage systems containing or having network access to computer program(s) coded in accordance with various methods described herein, and the method steps of the invention could be accomplished by modules, routines, subroutines, or subparts of a computer program product.

[00042] As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.

[00043] Embodiments of the present invention may be provided as a computer program product, which may include a machine -readable storage medium tangibly embodying thereon instructions, which may be used to program a computer (or other electronic devices) to perform a process. The term “machine-readable storage medium” or “computer-readable storage medium” includes, but is not limited to, fixed (hard) drives, magnetic tape, floppy diskettes, optical disks, compact disc read-only memories (CD-ROMs), and magneto-optical disks, semiconductor memories, such as ROMs, PROMs, random access memories (RAMs), programmable read-only memories (PROMs), erasable PROMs (EPROMs), electrically erasable PROMs (EEPROMs), flash memory, magnetic or optical cards, or other type of media/machine -readable medium suitable for storing electronic instructions (e.g., computer programming code, such as software or firmware).A machine -readable medium may include a non-transitory medium in which data may be stored and that does not include carrier waves and/or transitory electronic signals propagating wirelessly or over wired connections. Examples of a non-transitory medium may include, but are not limited to, a magnetic disk or tape, optical storage media such as compact disk (CD) or digital versatile disk (DVD), flash memory, memory or memory devices. A computer -program product may include code and/or machine-executable instructions that may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and/or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, etc. [00044] Various terms as used herein are shown below. To the extent a term used in a claim is not defined below, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing. [00045] The present disclosure relates to the field of vehicle automation. More particularly, the present disclosure relates to system and method for planning smooth evasive movement of a host vehicle on a road based on speed and velocity of target vehicles and the road conditions.

[00046] FIGs. 1A-C illustrate architecture of a dynamic evasive maneuver trajectory planning system to illustrate its overall working in accordance with an embodiment of the present disclosure.

[00047] According to an embodiment, a dynamic evasive maneuver trajectory planning system 100 (interchangeably referred to as system 100, hereinafter) is implemented in a vehicle (interchangeably referred to as host vehicle, hereinafter). The system 100 comprises an input unit 104, a processing unit 106 and an output unit 108. The input unit 104 may comprise one or more pre -processors, which processes perception inputs, raw sensed inputs from sensors or a camera or a Radio Detection And Ranging (RADAR) and fused raw sensed inputs from a Light Detection and Ranging (LIDAR) (forming part of sensor unit 102, which is operatively coupled with the input unit 104) configured in the host vehicle to capture images of surrounding of the host vehicle. The pre-processed sensed inputs may comprise parameters of position and velocity of vehicles surrounding the host vehicle (interchangeably referred to as target vehicles, hereinafter), road profile information and drive passage information. In an implementation, sensors or camera of the sensor unit 102 may be placed below rear-view mirror in front side of the host vehicle. The processing unit 106 may comprise a processor and a memory and/or may be integrated with existing systems and controls of the host vehicle. For instance, signals generated by the processing unit 106 may be sent to an output unit 108 or an electronic control unit (ECU) of the host vehicle. The output unit 108 may be an interface that operatively couples processing unit 106 with a trajectory control and steering actuation unit 110 for dynamic planning of trajectory for evasive maneuver and performing lateral steering of the host vehicle to avoid collision on drive passage. The output unit 108 may also be a display device or any other audio-visual device that provides dynamic trajectory information for the host vehicle so as to avoid collision with the target vehicles.

[00048] At the input unit 104, the pre -processors process the camera, the RADAR and the LIDAR measurements and raw data captured by the sensor unit 102. The pre -processor of input unit 104 may receive input signals comprising a sequence of images, information related to presence, position, and velocity of target vehicles, and information related to surrounding environment from the sensor unit 102.

[00049] In an embodiment, at input block 142a, perception information, images and raw data for the host vehicle, the target vehicle, and the drive passage are captured using vehicle sensors, cameras, RADARs, and LIDARs. The perception information, the images and the raw data are combined at a perception, sensor fusion and target selection block 142b and 180 for further processing and planning dynamic trajectory.

[00050] In an embodiment, during situation and threat analysis 112, the processing unit 106 performs situation and threat analysis 144 and 152 to determine and assess the host vehicle’s surrounding environment, the target vehicles, and the drive passage for performing emergency steering operation. The situation and threat analysis 112 estimate a free drive passage 144a around the host vehicle and performs a collision and threat assessment 144b for determining anticipated risk of collision of the host vehicle with the surrounding target or traffic vehicle on the drive passage. The free drive passage estimation 144a determines free drive corridor around the host vehicle. Further, the collision and threat assessment 144b assimilates information related to such as the target vehicles, road signs, toll booth, road partition between on-coming and out going traffic etc. to avoid collision of the host vehicle. The situation and threat analysis 144 and 152 further analyses surrounding environment of the host vehicle and estimates the drive passage for performing emergency steering of the host vehicle so as to avoid collision.

[00051] In an embodiment, at trajectory initialization 114, the processing unit 106 performs trajectory initialization 156 to determine an evasive maneuver trajectory for the host vehicle. The estimated free drive passage determined at the situation and threat analysis 152 is received as input to the trajectory initialization 156 to perform an emergency steering operation for collision escape. The trajectory is initialized based on longitudinal and lateral distances that are available in the drive passage for evasive maneuver, a permissible radius of curvature of the trajectory and a lateral acceleration of the host vehicle.

[00052] In an embodiment, at trajectory regression modeling 116, the processing unit 106 performs trajectory regression modeling 158 to find an optimized trajectory for evasive maneuver of the host vehicle. The processing unit 106 outlines trajectory of the host vehicle so to provide an escape for the host vehicle from the collision with the target vehicles rather than a lane change. Further, the trajectory regression modeling is performed on the initial trajectory to optimize the trajectory to keep the host vehicle’s lateral acceleration and the longitudinal distance within a predefined threshold limit. The trajectory is tuned using an iterative loop to keep the lateral acceleration and longitudinal clearance together as constraints to converge the trajectory within predefined limits of the constraints which indirectly limits the steer rate demand to escape collision. The trajectory regression modeling for the host vehicle is determined based on evasive maneuver trajectory, the longitudinal distance, the lateral deviation, the radius of curvature of the optimized trajectory and the lateral acceleration of the host vehicle, and the drive passage. In an embodiment, the trajectory regression modeling 158 receives as input constraints for trajectory generation 172. The constraints for the trajectory generation 172 comprise a maximum lateral acceleration (i.e. upper threshold of maximum lateral acceleration), a range of radius of curvature and a longitudinal clearance limit (i.e. maximum driving passage). The maximum lateral acceleration depends on velocity of the host vehicle, whereas maximum driving passage or longitudinal clearance limit may be determined by free drive passage estimation 144a while considering speed of the host vehicle.

[00053] In an embodiment, at target edge collision correction 118, the processing unit 106 performs a target edge collision correction 160 to determine an escape trajectory by considering avoidance of edge or body collision of the host vehicle with an intended target vehicle. Further, the target edge correction 160 brings an escape trajectory closer to the target vehicle while analyzing a target edge correction so as to optimize the escape trajectory with respect to lateral maneuver deviation. In an embodiment, the target edge collision correction 160 receives as input a front selected target position and orientation 174. The target edge collision correction is performed based on the determined trajectory regression, and a current position and orientation of the front target vehicle. Information on the front selected target vehicle position and orientation 174 may be received from the perception, the sensor fusion and the target selection block 142b which determines current position and orientation of the target vehicle. Further, the target edge collision correction 160 is an iterative step where the trajectory is dynamically obtained from the trajectory regression model 158.

[00054] In an embodiment, during maneuver selection 120, the processing unit 106 performs the maneuver selection 162 to generate trajectory way points. The trajectory way points may be generated based on inputs related to the situation and threat analysis 152, driving passage assessment for lane availability, traffic regulation, motion of the host vehicle, and lateral deviation and direction of the front target vehicle motion based on the front selected target trajectory estimation 178. The maneuver selection 162 of the host vehicle is based on the performed target edge collision correction 160, one or more parameters of surroundings of the host vehicle, motion of the host vehicle and the estimated trajectory of the target vehicle. Further, the maneuver selection 162 receives front selected target trajectory estimation 178 as input that estimates a target vehicle for which the evasive maneuver of the host vehicle is initiated. The front selected target trajectory estimation 178 captures data from the image sensors, RADAR, LIDAR and camera. The captured data is post processed for tracking and estimation of the maneuver via perception, sensor fusion and target selection 142b.

[00055] In an embodiment, the trajectory initialization 156, the trajectory modeling 158, the trajectory collision corrector 160, and the maneuver selection 162 estimates the evasive maneuver 154a, 146a for the host vehicle.

[00056] In an embodiment, during adaptive road profiling 122, the processing unit 106 performs adaptive road profiling 164, where the host vehicle’s trajectory adapts the road profile along with a designed emergency maneuver trajectory to update the trajectory. Dynamic changes in the road profile are determined and considered for online adaptation of the trajectory such as when the trajectory transitions from a curvature to a straight or vice versa or transitions between different curves. The determination of the adaptive road profiling 164 is based on a road trajectory 176 that is determined based on information received from the perception, sensors, RADARs, and LIDARs.

[00057] In an embodiment, the front selected target position and orientation 174, the front selected target trajectory estimation 178 and the road trajectory 176 are based on input from the perception, sensor fusion and target selection 180, 142b.

[00058] In an embodiment, at maneuver fusion 124, the processing unit 106 performs maneuver fusion 166 to determine a fused trajectory by performing a maneuver fusion of estimated trajectory for the target vehicle and the adapted trajectory for the host vehicle. The determined fused trajectory is used to optimize the trajectory of the host vehicle for dynamic evasive maneuver. The maneuver fusion 166 fuses the evasive maneuver trajectory of the host vehicle with the target vehicle to bring out a higher order polynomial of fused trajectory for the emergency steering of the host vehicle. Further, the fused target vehicle trajectory enables the host vehicle to adapt a path with same characteristics as that of a pre-planned path in terms of minimum lateral deviation and keeps the host vehicle closest to the target vehicle during the escape path while ensuring no collision. Further, the maneuver fusion 166 receives as input the front selected target trajectory estimation 178 that estimates the target vehicle for which the evasive maneuver of the host vehicle is initiated. The front selected target trajectory estimation 178 captures data from the image sensors, RADAR, LIDAR and camera. The data is post processed for tracking and estimation of the maneuver via perception, sensor fusion and target selection 142b.

[00059] In an embodiment, at fused trajectory optimization 126, the processing unit 106 performs fused trajectory optimization 168 to generate an optimized fused trajectory that depends on the fused maneuver, maneuver way points and situation and threat analysis 152 parameters. The fused trajectory optimization 168 optimizes the trajectory of the host vehicle using an iterative loop that receives dynamic evasive maneuver trajectory of the host vehicle fused with the target vehicle, to bring out the optimized fused trajectory for emergency maneuver of the host vehicle. Further, the fused trajectory optimization 168 determines the trajectory maneuver for the host vehicle while performing better smoothened curvy trajectory thereby optimizing lateral acceleration of the designed trajectory.

[00060] In an embodiment, the adaptive road profiling 164, the maneuver fusion 166, and the fused trajectory optimization 168 enables determining optimized adaptive trajectory 154b and 146b.

[00061] In an embodiment, the evasive maneuver estimation for the host vehicle 146a and the adaptive trajectory optimization 146b facilitates trajectory planning 146 of the host vehicle. [00062] Furthermore, during trajectory control and steering actuation 110, the trajectory control 170 receives the optimized adaptive trajectory 154b to perform evasive steering of the host vehicle. The trajectory control 170, 148a being operatively coupled with the steering actuation unit 148b to follow the dynamic evasive trajectory of the host vehicle.

[00063] FIG. 2 illustrates exemplary functional components of a processing unit in accordance with an embodiment of the present disclosure.

[00064] In an aspect, the processing unit 106 may comprise one or more processor(s) 202. The one or more processor(s) 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the one or more processor(s) 202 are configured to fetch and execute computer-readable instructions stored in a memory 206 of the processing unit 106. The memory 206 may store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service. The memory 206 may comprise any non-transitory storage device including, for example, volatile memory such as RAM, or non volatile memory such as EPROM, flash memory, and the like.

[00065] The processing unit 106 may also comprise an interface(s) 204. The interface(s) 204 may comprise a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) 204 may facilitate communication of processing unit 106 with various devices coupled to the processing unit 106 such as the input unit 104 and the output unit 108. The interface(s) 204 may also provide a communication pathway for one or more components of the processing unit 106. Examples of such components include, but are not limited to, processing engine(s) 208 and data 210.

[00066] The processing engine(s) 208 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) 208. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) 208 may be processor executable instructions stored on a non-transitory machine -readable storage medium and the hardware for the processing engine(s) 208 may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine -readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 208. In such examples, the processing unit 106 may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the processing unit 106 and the processing resource. In other examples, the processing engine(s) 208 may be implemented by electronic circuitry.

[00067] The database 210 may comprise data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) 208. [00068] In an exemplary embodiment, the processing engine(s) 208 may comprise a situation and threat analysis module 212, a trajectory initialization module 214, a trajectory regression module 216, a target edge collision correction module 218, a maneuver selection module 220, an adaptive road profiling module 222, a maneuver fusion module 224, a fused trajectory optimization module 226, and supplementary module(s) 228.

[00069] It would be appreciated that modules being described are only exemplary modules and any other module or sub-module may be included as part of the system 100 or the processing unit 106. These modules too may be merged or divided into super-modules or sub-modules as may be configured.

[00070] In an aspect, one or more pre -processors of an input unit operatively coupled with the processing unit 106 perform camera, RADAR and LIDAR measurement and pre-processing of raw data captured by the input perception and sensor unit 102 to receive input signals comprising a sequence of images, information related to presence, location, and velocity of target vehicles, and information related to surrounding environment.

Situation and Threat Analysis Module 212

[00071] According to an embodiment, the situation and threat analysis module 212 estimates a free drive passage and assesses collision probability for the host vehicle. The situation and threat analysis module 212 perform a collision and threat assessment for the host vehicle based on the surrounding environment and the drive passage estimation of the host vehicle.

[00072] In an example, the evasive maneuver scenario with sharp deceleration of the target vehicle is illustrated in FIG. 3. As illustrated in FIG. 3 is a post maneuver position that represents a final position of the host vehicle; a pre-maneuver position that represents an initial position of the host vehicle, and a during maneuver position that represents an intermediate position of the host vehicle. Those skilled in the art would appreciate that the movement of the host vehicle from the pre-maneuver position to the post maneuver position involved multiple risks such as collision with the target vehicles present in both the lateral and in longitudinal directions, due to corresponding movement of the target vehicles based on their velocities, various road conditions etc.

[00073] In an example, the free drive passage may be estimated as per Table 1 below with respect to the Fig. 4 that illustrates exemplary representation for free drive passage estimation around the host vehicle. Further, the free drive passage estimation is based on front clearance and rear clearance parameters in either of left and right side of HV.

Table 1: Drive Passage Estimation for the Host Vehicle in an Exemplary Scenario as represented in FIG.4

[00074] According to an embodiment, the situation and threat analysis module 212 performs a collision and threat assessment for the host vehicle. The assessment is performed based on determined information related to availability of an emergency lane, a road partition between on coming and outgoing traffic, extreme or non-extreme lanes, a cross traffic condition, a road sign, a toll booth, a merge-demerger. The information is used for evasive maneuver planning. The situation and threat analysis module 212 determine a time to collision and anticipates a risk of collision of the host vehicle with front and rear target vehicles. Further, the time to collision and the anticipated risk of collision is used for trajectory planning of the host vehicle.

Trajectory Initialization Module 214

[00075] In an embodiment, the processor analyses an initial trajectory for the host vehicle. The initial trajectory is determined as part of an evasive maneuver trajectory estimation for performing an emergency steering operation of the host vehicle for an emergency collision escape. The initial trajectory is generated using polynomials based on fifth order polynomial equation which comprises kinematics model of the host vehicle. The initial trajectory is determined using the drive passage estimation coupled with a drive passage clearance determination, the collision and threat assessment determined at situation and threat analysis module 212. Further, the trajectory of the host vehicle may be generated based on the determined collision and threat assessment. For example, if time to collision of the host vehicle with the target vehicle is less than a certain threshold corresponds to emergency condition, the trajectory is generated such as to escape collision. Also, while generating trajectory, stability of the host vehicle during transition and while finally bringing the host vehicle to a stable path is taken care of. Further, the situation and threat analysis parameters are used to determine the maneuver start point and end point initialization for the host vehicle.

[00076] In an embodiment, the trajectory initialization is performed as follows: y(t) = a ₀ t ⁰ + a ₁ t ¹ + a ₂ t ² + a ₂ t ² + a ₃ t ³ + a ₄ t ⁴ + a ₅ t ⁵ ... (1) x(t) = b ₀ t ⁰ + ₁ ¹ ... (2) where, a ₀ , a ₁ a ₂ , a ₃ , a ₄ , a ₅ are coefficients of polynomial for y(t) of the trajectory b ₀ , b ₁ are coefficients of polynomial for x(t) of the trajectory x{t),y(t) are longitudinal and lateral points respectively which depend on time t

Trajectory Regression Modeling Module 216

[00077] In an embodiment, the trajectory regression modeling module 216 determines a trajectory regression for the host vehicle by analyzing and optimizing the trajectory of the host vehicle while keeping the trajectory for the evasive maneuver laterally closer to the target vehicle. The target vehicle may be located in front of the host vehicle and may lead to evasive maneuver of the host vehicle. The trajectory regression for the host vehicle is determined based on the initialized evasive maneuver trajectory, iteration constraints for trajectory generation and the free drive passage. Further, the trajectory regression modeling module 216 tunes the trajectory polynomial using iterative loops. The constraints for the iterative loop are longitudinal distance which is an available distance in the free driving passage for trajectory generation, available lateral distance, radius of curvature of the optimized trajectory and lateral acceleration of the host vehicle.

[00078] In an embodiment, the trajectory regression modeling module 216 converges the trajectory within predefined limits of the constraints. Furthermore, the radius of curvature of the optimized trajectory may be determined as a function of speed of the host vehicle. The trajectory regression modeling module 216 may facilitate finding the optimized trajectory for the evasive maneuver of the host vehicle, where focus is for the host vehicle to escape from collision in an emergency condition rather than a lane change maneuver. The optimized trajectory is focused to have a minimal lateral acceleration and thereby limiting steer rate demand while the maneuver selection.

[00079] In an embodiment, the trajectory regression modeling module 216 may perform a trajectory regression on an initial trajectory to optimize the trajectory for evasive maneuver, to keep the predicted vehicle’s lateral acceleration and the longitudinal distance requirement for trajectory generation within a predefined threshold limit. Further, maximum lateral acceleration and maximum radius of curvature of the host vehicle, following the generated trajectory, are subject to velocity of the host vehicle.

[00080] In an embodiment, the trajectory regression modeling module 216 performs a lateral acceleration regression analysis and further a drive passage regression analysis.

[00081] The lateral acceleration regression analysis is determined as:

Thereafter, the lateral acceleration regression analysis may be performed with a _y as based on a regression analysis loop such that R ^Min £ R ^Updt £ R ^Max is satisfied. where, a _y is lateral acceleration of the trajectory points is maximum lateral acceleration or upper threshold of the maximum lateral acceleration is lateral acceleration updated @ lateral acceleration regression analysis R is a radius of curvature used in trajectory planning (inputfrom other module or previous iteration for regression analysis)

R ^Updt is a radius of curvature updated during lateral acceleration regression analysis. R ^Min ' R ^Max are minimum and maximum limits of radius of curvature respectively T _ay is lateral acceleration regression ratio (refer above equation (3)) v is velocity of the host vehicle

[00082] The drive passage regression analysis is determined as:

The drive passage regression analysis may be performed with a _y as based on a regression analysis loop (discussed in subsequent description below). where, is longitudinal clearance or an estimated drive passage

P _x is longitudinal distance to preform evasive maneuver w.r.t start point of maneuver s lateral acceleration updated @ drive passage regression analysis T _sx is drive passage regression ratio (refer above equation (4))

[00083] In an embodiment, the regression analysis loop for the trajectory regression modeling module 216 may be determined. The regression analysis loop may be executed based on following equations:

Real roots of above equation defined the maneuver time t _m v _y u _y + a _y t _m ... (6)

Thereby derive v _x and a _x where, aismagnification gain factor and greater than 1 p _x , v _x and a _x are estimated longitudinal distance, velocity and acceleration respectively of the host vehicle for evasive maneuver p _y , v _y and a _y are estimated lateral distance, velocity and acceleration respectively of the host vehicle for evasive maneuver u _x , u _y are initial longitudinal and lateral velocity of the host vehicle respectively at start of evasive maneuver

[00084] In an exemplary embodiment, the trajectory regression modeling module 216 may deter the constraints such as the lateral acceleration, the lateral distance, and the longitudinal distance to reach a maximum value, leading to comfort in driving for the host vehicle even in emergency conditions. Various steps for performing the trajectory regression modeling of the evasive maneuver for the host vehicle are illustrated in Fig. 5. The host vehicle’s velocity vector determined from vehicle sensors at block 502 and constraints for trajectory generation at block 506 are received as input at a parameter initialization block 504, where, R ^Min , R ^max , are min and max radius of the curvature of planned trajectory, maximum lateral acceleration and maximum driving passage limits respectively. The driving passage limits parameter may determine available longitudinal distance for the host vehicle for performing evasive maneuver. The parameters at the parameter initialization block 504 are initialized based on the defined constraints of the trajectory generation and the host vehicle’s velocity vector (lateral and longitudinal velocity), thus R ^Min , R ^max , parameters are defined and other parameters of p _x , v _x and a _x , p _y v _y and a are initialized. Based on the parameter initialization block 504, the lateral acceleration is determined at a computing lateral acceleration block 508. At block 508, the lateral acceleration a _y is computed based on velocity of the host vehicle v and the regression loop. If at block 510 it is determined that position, velocity and acceleration parameters of the host vehicle are computed at block 512, else the lateral acceleration regression analysis is performed at block 520. At block 520, the lateral acceleration a _y is computed based on the velocity of the host vehicle v and the regression loop. Further, at block 520, the lateral acceleration regression analysis is performed using the above discussed equation (3). After computing the position, velocity and acceleration of the host vehicle at block 512, it is determined at block 514, whether the trajectory is generated using fifth order polynomial equation based on computed(p _x ,p _y ) (aiming it as last trajectory waypointjat block 516. The drive passage regression analysis is determined at block 522 if .The drive passage regression analysis is performed using the above discussed equations (4) and (9). The generated trajectory at block 516 is then used to compute a lateral collision at a lateral collision computation block 518. The intermittent trajectory waypoints generated at 516 for the lateral collision computation at block 518 are used to determine the edge collision clearance, and further checking edge intersection with the target vehicle for trajectory finalization is performed at block 526. Upon the checking at block 526, if it is determined that the waypoints are outside an intersection range (i.e. the portion inside target vehicle or M _y ) then the final trajectory waypoints for evasive maneuver selection is generated in an updated trajectory at block 528. Further, if the determined waypoints are within an intersection range (i.e. the portion inside target vehicle or M _y ) a target edge collision correction regression analysis is performed at block 524. Furthermore, the lateral acceleration regression analysis at block 520, the drive passage regression analysis at block 522, and the target edge collision regression analysis at block 524 may be collated to compute lateral acceleration a _y at block 508.

Target Edge Collision Correction Module 218

[00085] In an embodiment, the target edge collision correction module 218 performs the trajectory correction based on the determined trajectory regression for the host vehicle, and current position and orientation of the target vehicle. The target edge collision correction module 218 may determine an escape trajectory for the host vehicle by considering an edge avoidance and body collision of the host vehicle with the target vehicle. Further, the target edge collision correction module 218 may perform the escape trajectory while considering avoidance of the edge or body collision of the host vehicle with an intended target vehicle responsible for evasive maneuver. The target edge correction module may further bring the escape trajectory closer to the target vehicle while analyzing the edge correction thereby suggesting the optimized trajectory for the host vehicle with respect to the minimum lateral maneuver deviation requirements. Multiple exemplary positions for the host vehicle during evasive maneuver for edge collision avoidance are represented in FIG. 6. As represented in FIG. 6, is an initial phase of evasive maneuver, followed by an intermittent phase of maneuver, and thereafter an end phase of the evasive maneuver. The target edge collision corrector module 218 may enable the host vehicle to avoid side collision with the target vehicles. Further, the module 218 facilitates determining a minimized lateral deviation in collaboration with the trajectory regression modeling to avoid collision of the host vehicle with the target vehicle.

[00086] In an embodiment, the trajectory is generated for the evasive maneuver using the updated parameter values of p _x , v _x , a _x and p _y , v _y , a _y . The trajectory is generated using the Equation (3)-(9) as discussed above and the target edge collision correction module, in the regression analysis loop section.

[00087] Furthermore, an exemplary FIG. 7 is represented, which computes the target edge collision correction. As represented in FIG. 7, verticals of the host vehicle may be derived based on a calculated q which is further computed from a derivative of the trajectory at point P ₁ . The points closest of the target vehicle i.e. may be used to derive an equation of a line comprehending the inner side of the host vehicle. Further, a point of intersection P ₂ (l _x , I _y ) with a vertical line drawn at rear of the target vehicle may be computed. Also, a clearance (I _y — M _y ) may be computed. In case, the I _y lies within an edge of the target vehicle i.e. if (I _y < M _y ) the I _y may substantiate a probability of edge or body collision of the host vehicle with the target vehicle and thereby the trajectory may be rejected. The trajectory regression modeling module 216 may be required to re-iterate the trajectory again with adjustments in the lateral clearance. The target edge collision corrector evaluation may be performed on the trajectory way points within a zone where a probability of the host vehicle colliding with the target vehicle is known, that is the zone in between following positions of the host vehicle: position of the host vehicle which may be located (W _Front ) _HV (i.e. distance of reference point of the host vehicle, commonly center of rear wheel axis and front extreme position of the host vehicle) distance ahead of target vehicle I _x , and position of the host vehicle which may be located (W _Rear ) _HV or(i.e. distance of the reference point of the host vehicle commonly center of the rear wheel axis and rear extreme position of the host vehicle) distance crossing target vehicle I _x .

[00088] In an embodiment, the trajectory may be generated using the updated parameter values of p _x , v _x and a _x .The trajectory may be generated using the Equation (5)-(9) as discussed above, in the regression analysis loop section.

[00089] In an embodiment, the lateral collision may be computed by determining a bandwidth between BW ₁ and BW ₂ as shown in FIG. 7 (with dotted line). The bandwidth may be computed by calculating BW ₁ and BW ₂ as(I _x — (W _Front ) _HV )and (I _x + (W _Front ) _HV respectively. An intersection clearance(/ _y — M _y ) may be computed within boundary of aforesaid bandwidth to ensure body collision or edge avoidance of the host vehicle with target vehicle. The generated waypoints may be evaluated for minimum clearance of the edge collision as discussed above in the target edge collision correction module 218 and the edge intersection checking with the target vehicle at block 526 of the FIG 5.

[00090] In an embodiment, the edge intersection with the target vehicle may be determined. The determination may be done by checking whether the edge of the host vehicle lies inside the edge of the target vehicle, while considering the front target vehicle’s position and orientation.

[00091] In an embodiment, the regression analysis loop may be executed to optimize the lateral deviation for evasive maneuver trajectory based on , and the = T _sy p _y , where T _sy is a weightage factorwhich is determined based on lateral deviation optimization requirement of trajectory i.e. T _sy may bechosenbasedon requirement of change in lateral distance to optimize trajectory in regression analysis loop.

Maneuver Selection Module 220

[00092] In an embodiment, the module 220 performs a maneuver selection for the host vehicle to determine an adaptive road profile for adaptation of the trajectory for the host vehicle based on road trajectory. The adaptation enables a collision escape during the evasive maneuver of the host vehicle. The maneuver selection of the host vehicle may be performed using the target edge collision corrector, the parameters of the host vehicle’ s surroundings, motion of the host vehicle and the estimated trajectory of the target vehicle.

[00093] In an embodiment, the trajectory may be generated based on the above discussed situation and threat analysis module 212. Trajectory points may be generated for left or right side of the target vehicle based on below mentioned inputs and priorities such as (a) situation and threat analysis - available for emergency lane, road partition between on-coming and out-going traffic, extreme or non-extreme lanes, cross traffic condition, road sign, toll booth, merge/demerger, (b) driving passage assessment for lane availability that are used for determining available adjacent lane, lateral clearance, longitudinal clearance, (c) traffic regulation for determining whether right side or left side traffic is having high speed traffic, (d) motion of the host vehicle for determining maneuver motion, longitudinal motion, and (e) lateral direction of the front target vehicle motion based on from the target trajectory estimation. [00094] In an embodiment, the module 220 determines the evasive maneuver to generate the trajectory way points based on the trajectory regression modeling module 216 and the target edge collision correction module 218. The trajectory may be generated with respect to an initialized point of trajectory, which is an Autonomous Emergency Steering (AES) or an evasive maneuver activation point where the waypoint intervals are variants of velocity of the host vehicle.

Adaptive Road Profiling Module 222

[00095] In an embodiment, the module 222 determines an adaptive road profile for adaptation of trajectory for the host vehicle based on available road trajectory. The adaptation enables the collision escape during the evasive maneuver of the host vehicle. The host vehicle may adapt the road’s profile along with a designed emergency maneuver trajectory to ensure a similar performance of a designed trajectory, in case the road is straight while maintaining clearance of the host vehicle with the target vehicle.

[00096] In an embodiment, online adaptation of the trajectory for dynamic changes in the road profile such as a transition from a straight road to a curvy road, or transition from the curvature road to the straight road, or a transition between curvatures with varied radius during the evasive maneuver are presented. The online adaptation of the trajectory for dynamic changes in the road profile may be challenging and complex in terms of the trajectory optimization as the transition may not be accurately estimated by perception and sensor fusion unit and there is always a chance of the host vehicle to loose control due to uncertain trajectory switching to aid surrounding condition or the road profile during the evasive maneuver. Furthermore, the module 222 may determine the adapted road profile with ARP _i (x,y) as ARP _i (y) = SM _i (y) + R _i ; and ARP _i (x) = SM _i (x) .

The adaptive road profiling is illustrated in an exemplary chart in FIG. 8 shows an adaptive road profiling with respect to a transitioning from a straight-line road segment to a curved road segment in accordance with an embodiment of the present disclosure. As shown in the FIG. 8 is an exemplary representation showing performance of the maneuver selection trajectory, reference straight road, road profile (straight road followed by curvature road), and adaptive road profiling trajectory, with respect to their performance in the straight-line road segment and the curved road segment. The comparison chart further shows a comparison of the initial position of the host vehicle maneuver ARP ₁ (x,y), transition of straight to curvature maneuver with ARP ₂ (x,y), trajectory position based on maneuver selectionSM(x,y), road deviation from reference road R _i , and intermediate position of the host vehicle maneuver ARP _i (x,y) with respect to their performance in the straight line road segment and the curved road segment.

Maneuver Fusion Module 224

[00097] In an embodiment, the maneuver fusion module 224 may perform a maneuver fusion of the estimated trajectory for the target vehicle and the adapted trajectory for the host vehicle to determine a fused trajectory such that the fused trajectory is used to optimize the trajectory of the host vehicle for dynamic evasive maneuver. The determined fused trajectory may direct the host vehicle to a path on the drive passage where the host vehicle has minimum lateral deviation and escapes collision.

[00098] In an embodiment, the module 224 may fuse the evasive maneuver trajectory of the host vehicle with the target vehicle to bring out a higher order polynomial of the fused trajectory for emergency maneuver. The module 224 may generate a trajectory fusion where non-linear characteristics of the host vehicle trajectory are fused with linear or non-linear trajectory of the target vehicle. In maneuver fusion, the trajectory waypoints of the host vehicle may be fused with the estimated positions of the target vehicle which is particularly useful in case of aggressively maneuvering intended front target vehicle (responsible for causing evasive maneuver activation). In the trajectory fusion, the module 224 may ensure merging of two trajectories with vehicle dynamics as constraints. The constraints may be updated online dynamically during the maneuver to perform a convergence of regression trajectory. The module 224 may also consider - uncertainty of the target vehicle’s motion during convergence of regression trajectory. The trajectory of the target vehicle may be estimated based on history of the target vehicle’s information related to position and velocity.

[00099] The module 224 may facilitate determining a nearest position estimation of the target vehicle during the evasive maneuver of the host vehicle. The position estimation may be precisely accurate, as nearest position may be accurately estimated based on previous target position and velocity history of the target vehicle. The position may be estimated using a front target trajectory estimation technique which uses perception sensors to determine position of the target vehicle. Also, those skilled in the art would appreciate that position accuracy of the perception sensor for nearby target vehicles is accurate than as compared to a distant target. Additionally, the estimated trajectory of the target vehicle may be transformed while altering origin of the estimated trajectory as the start point of an evasive maneuver and is illustrated in an exemplary chart in FIG. 9. The exemplary chart or representation shows a maneuver fusion with respect to varying positions of the host vehicle and the target vehicle during evasive maneuver in accordance with an embodiment of the present disclosure.

[000100] As illustrated in FIG. 9, where A ₀ (x,y) represents initial/origin point, the adapted road profiling waypoints A _i (x, y) between A ₁ (x, y) and A ₂ (x, y) may be represented as follows:

A _i (x) = B _i (x) + C _i (x); and A _i (y) = B _i (y) + C _i (y)

The adapted road profile with waypoints between A ₂ (x, y) and A ₃ (x, y) are represented as follows:

A _j (x) = B _j (x) + C _j (x); and A _j (y) = B _j (y) + C _j (y), however the limits to A _j (y) is A ₂ (y) i.e. the lateral position of A _j (y) shall not be less than A ₂ (y). where, C(x, y) is an estimated trajectory position of an intended target vehicle which is responsible for causing evasive maneuver activation.

As represented in the FIG. 9 is a comparison representation showing an adaptive road profiling trajectory, transformed traffic trajectory, maneuver fusion trajectory, fused trajectory optimization to determine the maneuver fusion. Further represented is an initial position of the host vehicle maneuver, transformed starting position of the target vehicle maneuver, anticipated position of collision, point at which the host vehicle’s rear position escapes longitudinally front part of the target vehicle intended to avoid collision, merging of the maneuver fusion with actual selected maneuver, and a final position of the host vehicle maneuver with respect to longitudinal axis and lateral axis.

Fused Trajectory Optimization Modules 226

[000101] In an embodiment, the module 226 generates an optimized trajectory depending on output of the maneuver fusion, the maneuver waypoints and the surrounding situation assessment. The module ensures smoothening of the trajectory while transitioning from a fused trajectory to the trajectory corresponding to the maneuver waypoints. The module 226 further determines the trajectory maneuver while performing a better smoothened curvy trajectory and optimizing the lateral acceleration of designed trajectory. The module 226 optimizes the trajectory to ensure safety and comfort of the target vehicle even in extreme conditions.

[000102] In an exemplary embodiment, FIG. 10 illustrates implementation of fused trajectory optimization. In an example, the determined maneuver fusion at block 1006 and the selected maneuver at block 1002 are collated to determine a transitional path generation from maneuver fusion to maneuver selection at block 1008. The module 226 at the block 1008 may generate a path during transition from A ₃ (x, y) to A ₄ (x, y)or transition from the maneuver fusion to the maneuver selection trajectory, and smoothen the waypoints using averaging of the lateral difference between the points and A ₄ to avoid sharp transitions for the host vehicle. When, an average value falls below a predefined threshold, the host vehicle may be completely shifted to the selected maneuver.

[000103] In an exemplary embodiment, at block 1010 a path rejection for non-free passageway may receive situation and threat analysis information from block 1004. The module 226 may check for a generated path with respect to a free drive passage at the waypoint, or any rear threat to the host vehicle or sideways threat to the host vehicle based on a situation interpretation. Upon, anticipation of the threat the trajectory may be rejected.

[000104] In an exemplary embodiment, at block 1012 a maneuver trajectory may be optimized. The module 226 may optimize trajectory control at block 1012 based on the lateral acceleration constraints and may perform iterative check of constraints of maneuver fusion. The operations at the block 1012 are re-iterated in collaboration with maneuver fusion to optimize the dynamic evasive trajectory to satisfy the defined constraints to the possible extent during the maneuver.

[000105] The block 1012 may determine that the trajectory never violates the maximum lateral acceleration when upper maximum lateral acceleration corresponds to a predefined maximum lateral acceleration threshold and lower maximum lateral acceleration corresponds to lateral acceleration which is higher than acceleration met during normal driving but less than upper threshold of maximum lateral acceleration. Bandwidth of the maximum and the minimum lateral acceleration is created to ensure that the trajectory never violates the maximum lateral acceleration threshold. When the lateral acceleration of the host vehicle reaches beyond limits or the constraint’s value, the fused maneuver trajectory retains previously scaled lateral deviation (in which lateral acceleration is within a limit or below a lower max. lateral acceleration threshold) and iterates the path to maintain smoothness while limiting the trajectory within the constraints. Further, when the lateral acceleration goes above the lower threshold, the above- mentioned projection of the trajectory may be adapted. However, when the lateral acceleration falls below the lower threshold of the maximum lateral acceleration, the trajectory may start adapting points of the maneuver fusion. Furthermore, to smoothen the trajectory, weighted average of the previous maneuver trajectory optimization waypoints and the fused maneuver trajectory waypoints may be conducted to avoid the lateral acceleration of the host vehicle beyond a permissible limit. The trajectory control block at 1014 may receive the trajectory waypoints to perform maneuver control in collaboration with steering actuation system. Supplementary Modules 228

[000106] In an aspect, supplementary modules 228 implement functionalities that supplement applications or functions performed by the system 100, processing unit 106 or the processing engine(s) 208.

[000107] Although the proposed system has been elaborated as above to include all the main modules, it is completely possible that actual implementations may include only a part of the proposed modules or a combination of those or a division of those into sub-modules in various combinations across multiple devices that may be operatively coupled with each other, including in the cloud. Further the modules may be configured in any sequence to achieve objectives elaborated. Also, it may be appreciated that proposed system may be configured in a computing device or across a plurality of computing devices operatively connected with each other, wherein the computing devices may be any of a computer, a smart device; an Internet enabled mobile device and the like. Therefore, all possible modifications, implementations and embodiments of where and how the proposed system is configured are well within the scope of the present invention.

[000108] FIG. 11 is a flow diagram illustrating a method for optimizing a trajectory for a host vehicle for dynamic evasive maneuver in a drive passage to avoid collision of the host vehicle with a target vehicle in accordance with an embodiment of the present disclosure. [000109] In an aspect, the proposed method may be described in general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types. The method can also be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, computer executable instructions may be located in both local and remote computer storage media, including memory storage devices. [000110] The order in which the method as described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement the method or alternate methods. Additionally, individual blocks may be deleted from the method without departing from the spirit and scope of the subject matter described herein. Furthermore, the method may be implemented in any suitable hardware, software, firmware, or combination thereof. However, for ease of explanation, in the embodiments described below, the method may be considered to be implemented in the above described system.

[000111] In an aspect, present disclosure elaborates upon a method for optimizing a trajectory for a host vehicle for dynamic evasive maneuver in a drive passage that comprises, at block 1102, receiving an input signal comprising one or more parameters of surroundings of the host vehicle from an input unit, the input unit comprising one or more one or more sensors mounted on the host vehicle. The method comprises at block 1104, initializing an evasive maneuver trajectory for the host vehicle by receiving the one or more parameters, wherein the initialization is performed for steering the host vehicle in an emergency operation for a collision escape. The method further comprises at block 1106, determining a trajectory regression for the host vehicle and performing a target edge collision correction to avoid collision with a target vehicle, selected from one or more target vehicles, by analyzing and optimizing the trajectory of the host vehicle while keeping trajectory for evasive maneuver laterally closer to the target vehicle, wherein the target vehicle is located in front of the host vehicle and causes evasive maneuver of the host vehicle, and at block 1108 performing a maneuver selection of the host vehicle based on a set of attributes to determine an adaptive road profile for adaptation of the trajectory for the host vehicle based on road trajectory, wherein the adaptation enables the collision escape during the evasive maneuver of the host vehicle. Further, the method comprises at block 1110 performing a maneuver fusion of estimated trajectory for the target vehicle and the adapted trajectory for the host vehicle to determine a fused trajectory so that the fused trajectory is used to optimize the trajectory of the host vehicle for dynamic evasive maneuver based on the determined fused trajectory for the host vehicle.

[000112] Those skilled in the art would appreciate that the embodiments of the present disclosure provide dynamic evasive trajectory planning of the host vehicle and enhances the possibility of performing a smooth and safe maneuver. Embodiments herein deal with the maneuver planning in an emergency condition to avoid collision and further enables generating the trajectory iteratively while simultaneously adapting the trajectory to dynamic changes in the environment such as lateral and longitudinal target vehicle motion, road profile/trajectory even after starting of the evasive maneuver of the host vehicle. Furthermore, the embodiments herein facilitates determining an optimized trajectory for high speed evasive maneuver so as to escape collision rather than just change lane.

[000113] Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification claims refer to at least one of something selected from the group consisting of A, B, C ... .and N, the text should be interpreted as requiring only one element from the group, not A plus N, or B plus N, etc.

[000114] While some embodiments of the present disclosure have been illustrated and described, those are completely exemplary in nature. The disclosure is not limited to the embodiments as elaborated herein only and it would be apparent to those skilled in the art that numerous modifications besides those already described are possible without departing from the inventive concepts herein. All such modifications, changes, variations, substitutions, and equivalents are completely within the scope of the present disclosure. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims.

ADVANTAGES OF THE INVENTION

[000115] The present disclosure provides a system and method for planning an online dynamic trajectory with constraints for evasive maneuver.

[000116] The present disclosure provides a system and method for evasive maneuver planning of a host vehicle in an emergency condition.

[000117] The present disclosure provides a system and method for evasive maneuver planning of a host vehicle in an emergency condition to avoid collision.

[000118] The present disclosure provides a system and method for assessing free clearance surrounding of the host vehicle. [000119] The present disclosure provides a system and method to adapt the evasive maneuver trajectory based on a road profile.

[000120] The present disclosure provides a system and method to dynamically adapt the trajectory based on drive passage estimation and emergency collision assessment.

[000121] The present disclosure provides a system and method to adapt the dynamic evasive maneuver trajectory based on position and motion of front selected target, which is responsible for causing evasive maneuver activation.