BACKGROUND

[0001] Environments in which objects are managed, such as retail facilities, warehousing and distribution facilities, and the like, may store such objects in regions such as aisles of shelf modules or the like. For example, a retail facility may include objects such as products for purchase, and a distribution facility may include objects such as parcels or pallets.

[0002] A mobile automation apparatus may be deployed within such facilities to perform tasks at various locations. For example, a mobile automation apparatus may be deployed to capture data representing an aisle in a retail facility for use in identifying products that are out of stock, incorrectly located, and the like. The dynamic nature of environments such as the retail facility may complicate data capture. For example, illumination employed by the apparatus to aid in data capture may interfere with customers, staff or the like within the facility.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0003] The accompanying figures, where like reference numerals refer to identical or functionally similar elements throughout the separate views, together with the detailed description below, are incorporated in and form part of the specification, and serve to further illustrate embodiments of concepts that include the claimed invention, and explain various principles and advantages of those embodiments.

[0004] FIG. 1 is a schematic of a mobile automation system.

[0005] FIG. 2 is a side view of a mobile automation apparatus in the system of FIG. 1. [0006] FIG. 3 is a diagram of the mobile automation apparatus of FIG. 2 illustrating fields of illumination of the apparatus.

[0007] FIG. 4 is a block diagram of certain internal components of the mobile automation apparatus in the system of FIG. 1.

[0008] FIG. 5 is a flowchart of a method of illumination control in the system of FIG.

1. [0009] FIG. 6 is a diagram of a performance of block 505 of the method of FIG. 5. [0010] FIG. 7 is a diagram illustrating a performance of block 510 of the method of FIG. 5.

[0011] FIG. 8 is a diagram illustrating a performance of block 525 of the method of FIG. 5.

[0012] FIG. 9 is a diagram illustrating a performance of block 535 of the method of FIG. 5.

[0013] FIG. 10 is a flowchart of a method of selecting illumination control actions. [0014] FIG. 11 is a diagram illustrating a performance of block 1005 of the method of FIG. 10.

[0015] Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help to improve understanding of embodiments of the present invention.

[0016] The apparatus and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

DETAILED DESCRIPTION

[0017] Examples disclosed herein are directed to a method in a navigational controller, the method comprising: obtaining image data and depth data from sensors of a mobile automation apparatus; detecting an obstacle from the depth data, for classification as a human or non-human obstacle; in response to classification of the obstacle as a human obstacle, selecting a portion of the image data that corresponds to the obstacle; detecting, from the selected image data, a feature of the obstacle; based on a detected position of the detected feature, selecting an illumination control action; and controlling an illumination subsystem of the mobile automation apparatus according to the selected illumination control action. [0018] Additional examples disclosed herein are directed to a mobile automation apparatus, comprising: an image sensor; a depth sensor; a chassis supporting an illumination subsystem configured to emit light; a navigational controller connected to the image sensor, the depth sensor, and the illumination subsystem, the navigational controller configured to: obtain image data and depth data from the image sensor and the depth sensor; detect an obstacle from the depth data, for classification as a human or non-human obstacle; in response to classification of the obstacle as a human obstacle, select a portion of the image data that corresponds to the obstacle; detect, from the selected image data, a feature of the obstacle; based on a detected position of the detected feature, select an illumination control action; and control the illumination subsystem according to the selected illumination control action.

[0019] FIG. 1 depicts a mobile automation system 100 in accordance with the teachings of this disclosure. The system 100 includes a server 101 in communication with at least one mobile automation apparatus 103 (also referred to herein simply as the apparatus 103) and at least one client computing device 104 via communication links 105, illustrated in the present example as including wireless links. In the present example, the links 105 are provided by a wireless local area network (WLAN) deployed via one or more access points (not shown). In other examples, the server 101, the client device 104, or both, are located remotely (i.e. outside the environment in which the apparatus

103 is deployed), and the links 105 therefore include wide-area networks such as the Internet, mobile networks, and the like. The system 100 also includes a dock 106 for the apparatus 103 in the present example. The dock 106 is in communication with the server 101 via a link 107 that in the present example is a wired link. In other examples, however, the link 107 is a wireless link.

[0020] The client computing device 104 is illustrated in FIG. 1 as a mobile computing device, such as a tablet, smart phone or the like. In other examples, the client device

104 is implemented as another type of computing device, such as a desktop computer, a laptop computer, another server, a kiosk, a monitor, and the like. The system 100 can include a plurality of client devices 104 in communication with the server 101 via respective links 105.

[0021] The system 100 is deployed, in the illustrated example, in a retail facility including a plurality of support structures such as shelf modules 110-1, 110-2, 110-3 and so on (collectively referred to as shelf modules 110 or shelves 110, and generically referred to as a shelf module 110 or shelf 110 - this nomenclature is also employed for other elements discussed herein). Each shelf module 110 supports a plurality of products 112. Each shelf module 110 includes a shelf back 116-1, 116-2, 116-3 and a support surface (e.g. support surface 117-3 as illustrated in FIG. 1) extending from the shelf back 116 to a shelf edge 118-1, 118-2, 118-3.

[0022] The shelf modules 110 (also referred to as sub-regions of the facility) are typically arranged in a plurality of aisles (also referred to as regions of the facility), each of which includes a plurality of modules 110 aligned end-to-end. In such arrangements, the shelf edges 118 face into the aisles, through which customers in the retail facility, as well as the apparatus 103, may travel. As will be apparent from FIG. 1, the term “shelf edge” 118 as employed herein, which may also be referred to as the edge of a support surface (e.g., the support surfaces 117) refers to a surface bounded by adjacent surfaces having different angles of inclination. In the example illustrated in FIG. 1, the shelf edge 118-3 is at an angle of about ninety degrees relative to the support surface 117-3 and to the underside (not shown) of the support surface 117-3. In other examples, the angles between the shelf edge 118-3 and the adjacent surfaces, such as the support surface 117-3, is more or less than ninety degrees.

[0023] The apparatus 103 is equipped with a plurality of navigation and data capture sensors 108, such as image sensors (e.g. one or more digital cameras) and depth sensors (e.g. one or more Light Detection and Ranging (LIDAR) sensors, one or more depth cameras employing structured light patterns, such as infrared light, or the like). The apparatus 103 is deployed within the retail facility and, via communication with the server 101 and use of the sensors 108, navigates autonomously or partially autonomously along a length 119 of at least a portion of the shelves 110.

[0024] While navigating among the shelves 110, the apparatus 103 can capture images, depth measurements and the like, representing the shelves 110 (generally referred to as shelf data or captured data). Navigation may be performed according to a frame of reference 102 established within the retail facility. The apparatus 103 therefore tracks its pose (i.e. location and orientation) in the frame of reference 102. The apparatus 103 can navigate the facility by generating paths from origin locations to destination locations. For example, to traverse an aisle while capturing data representing the shelves 110 of that aisle, the apparatus 103 can generate a path that traverses the aisle. [0025] The apparatus 103 can be configured to detect obstacles during traversal of an aisle, such as customers and/or workers in the retail facility, objects on a floor of the facility, and the like. The apparatus 103 may, with or without assistance from the server 101, modify the above-mentioned path in response to detecting such obstacles, e.g. to avoid collisions.

[0026] During travel along a path (e.g. to traverse an aisle in the retail facility) the apparatus 103 may control an illumination subsystem, discussed below in greater detail, to illuminate the shelves 110 for data capture. As will be discussed in greater detail below, the apparatus 103 may control the illumination subsystem based in part on the above-mentioned obstacle detections, to avoid interfering with the activities of customers, workers and the like in the facility.

[0027] The server 101 includes a special purpose controller, such as a processor 120, specifically designed to control and/or assist the mobile automation apparatus 103 to navigate the environment and to capture data. The processor 120 is interconnected with a non-transitory computer readable storage medium, such as a memory 122, having stored thereon computer readable instructions for performing various functionality, including control of the apparatus 103 to navigate the modules 110 and capture shelf data, as well as post-processing of the shelf data. The memory 122 can also store data for use in the above-mentioned control of the apparatus 103, such as a repository 123 containing a map of the retail environment and any other suitable data (e.g. operational constraints for use in controlling the apparatus 103, data captured by the apparatus 103, and the like).

[0028] The memory 122 includes a combination of volatile memory (e.g. Random Access Memory or RAM) and non-volatile memory (e.g. read only memory or ROM, Electrically Erasable Programmable Read Only Memory or EEPROM, flash memory). The processor 120 and the memory 122 each comprise one or more integrated circuits. In some embodiments, the processor 120 is implemented as one or more central processing units (CPUs) and/or graphics processing units (GPUs). [0029] The server 101 also includes a communications interface 124 interconnected with the processor 120. The communications interface 124 includes suitable hardware (e.g. transmitters, receivers, network interface controllers and the like) allowing the server 101 to communicate with other computing devices - particularly the apparatus 103, the client device 104 and the dock 106 - via the links 105 and 107. The links 105 and 107 may be direct links, or links that traverse one or more networks, including both local and wide-area networks. The specific components of the communications interface 124 are selected based on the type of network or other links that the server 101 is required to communicate over. In the present example, as noted earlier, a wireless local-area network is implemented within the retail facility via the deployment of one or more wireless access points. The links 105 therefore include either or both wireless links between the apparatus 103 and the mobile device 104 and the above-mentioned access points, and a wired link (e.g. an Ethernet-based link) between the server 101 and the access point.

[0030] The processor 120 can therefore obtain data captured by the apparatus 103 via the communications interface 124 for storage (e.g. in the repository 123) and subsequent processing (e.g. to detect objects such as shelved products in the captured data, and detect status information corresponding to the objects). The server 101 may also transmit status notifications (e.g. notifications indicating that products are out-of- stock, in low stock or misplaced) to the client device 104 responsive to the determination of product status data. The client device 104 includes one or more controllers (e.g. central processing units (CPUs) and/or field-programmable gate arrays (FPGAs) and the like) configured to process (e.g. to display) notifications received from the server 101.

[0031] Turning now to FIG. 2, the mobile automation apparatus 103 is shown in greater detail. The apparatus 103 includes a chassis 201 containing a locomotive assembly 203 (e.g. one or more electrical motors driving wheels, tracks or the like). The apparatus 103 further includes a sensor mast 205 supported on the chassis 201 and, in the present example, extending upwards (e.g., substantially vertically) from the chassis 201. The mast 205 supports the sensors 108 mentioned earlier. In particular, the sensors 108 include at least one imaging sensor 207, such as a digital camera. In the present example, the mast 205 supports seven digital cameras 207-1 through 207-7 oriented to face the shelves 110.

[0032] The mast 205 also supports at least one depth sensor 209, such as a 3D digital camera capable of capturing both depth data and image data. The apparatus 103 also includes additional depth sensors, such as LIDAR sensors 211. In the present example, the mast 205 supports two LIDAR sensors 211-1 and 211-2. As shown in FIG. 2, the cameras 207 and the LIDAR sensors 211 are arranged on one side of the mast 205, while the depth sensor 209 is arranged on a front of the mast 205. That is, the depth sensor 209 is forward-facing (i.e. captures data in the direction of travel of the apparatus 103), while the cameras 207 and LIDAR sensors 211 are side-facing (i.e. capture data alongside the apparatus 103, in a direction perpendicular to the direction of travel). In other examples, the apparatus 103 includes additional sensors, such as one or more RFID readers, temperature sensors, and the like.

[0033] The mast 205 also supports a plurality of illumination assemblies 213, configured to illuminate the fields of view of the respective cameras 207. The illumination assemblies 213 may be referred to collectively as an illumination subsystem. That is, the illumination assembly 213-1 illuminates the field of view of the camera 207-1, and so on. The cameras 207 and lidars 211 are oriented on the mast 205 such that the fields of view of the sensors each face a shelf 110 along the length 119 of which the apparatus 103 is traveling. The apparatus 103 is configured to track a pose of the apparatus 103 (e.g. a location and orientation of the center of the chassis 201) in the frame of reference 102, permitting data captured by the apparatus 103 to be registered to the frame of reference 102 for subsequent processing.

[0034] FIG. 3 illustrates a simplified view of the apparatus 103, including the illumination assemblies 213-1 and 213-2 with respective fields of illumination 300-1 and 300-6. As shown in FIG. 3, the fields of illumination 300 are substantially perpendicular to a direction of travel 304 of the apparatus 103. Certain sensors, such as the depth camera 209, may have a field of view 308 that extends forward of the apparatus 103, in the direction of travel 304. In other examples, the field of view 308 can be angled at an intermediate angle between the fields of illumination 300 and the field of view 308 as illustrated in FIG. 3. Other sensors (e.g. the LIDAR sensors 211) may have fields of view that are perpendicular to the direction of travel 304. At least one of the cameras 207 may also have a field of view that is angled in the direction of travel 304, rather than being perpendicular to the direction of travel 304.

[0035] Referring to FIG. 4, certain components of the mobile automation apparatus 103 are shown, in addition to the cameras 207, depth sensor 209, lidars 211, and illumination assemblies 213 mentioned above. The apparatus 103 includes a special-purpose controller, such as a processor 400, interconnected with a non-transitory computer readable storage medium, such as a memory 404. The memory 404 includes a suitable combination of volatile memory (e.g. Random Access Memory or RAM) and non volatile memory (e.g. read only memory or ROM, Electrically Erasable Programmable Read Only Memory or EEPROM, flash memory). The processor 400 and the memory 404 each comprise one or more integrated circuits. The memory 404 stores computer readable instructions for execution by the processor 400. In particular, the memory 404 stores an illumination control application 408 which, when executed by the processor 400, configures the processor 400 to perform various functions related to controlling the illumination assemblies 213 based on detection and classification of obstacles in the vicinity of the apparatus 103 during a data capture operation.

[0036] The processor 400, when so configured by the execution of the application 408, may also be referred to as a navigational controller 400. Those skilled in the art will appreciate that the functionality implemented by the processor 400 via the execution of the application 408 may also be implemented by one or more specially designed hardware and firmware components, such as FPGAs, ASICs and the like in other embodiments.

[0037] The memory 404 may also store a repository 412 containing, for example, a map of the environment in which the apparatus 103 operates, for use during the execution of the application 408. The apparatus 103 also includes a communications interface 416 enabling the apparatus 103 to communicate with the server 101 (e.g. via the link 105 or via the dock 106 and the link 107), for example to receive instructions to navigate to specified locations and initiate data capture operations.

[0038] In addition to the sensors mentioned earlier, the apparatus 103 can also include a motion sensor 418, such as one or more wheel odometers coupled to the locomotive assembly 203. The motion sensor 418 can also include, in addition to or instead of the above-mentioned wheel odometer(s), an inertial measurement unit (IMU) configured to measure acceleration along a plurality of axes.

[0039] FIG. 4 also illustrates certain example components of the application 408. In other examples, the illustrated components of the application 408 can be implemented as distinct applications.

[0040] The components of the application 408, in the illustrated example, include an obstacle detector and classifier 420, a feature detector 424, and an illumination controller 428. The detector and classifier 420 is configured to detect obstacles based on image and/or depth data, and to classify the obstacles as human or non-human obstacles. The detector and classifier 420 may also classify detected obstacles as static or dynamic (i.e. obstacles in motion). The obstacle feature detector 424 receives indications of human-classified obstacles from the detector and classifier 420, detects certain features (e.g. human faces) associated with the detected obstacles, and passes such detections to the illumination controller 428. The illumination controller 428 receives the above-mentioned feature detections (and may also receive obstacle positions and classifications from the detector 420), and selects illumination control actions accordingly.

[0041] The actions performed by the apparatus 103, and specifically by the processor 400 as configured via execution of the application 408, to control the illumination assemblies based on obstacle detections will now be discussed in greater detail with reference to FIG. 5. FIG. 5 illustrates a method 500 of illumination control during data capture tasks. The method 500 will be described in conjunction with its performance in the system 100, and in particular by the apparatus 103 , with reference to the components illustrated in FIGS. 2, 3 and 4. As will be apparent in the discussion below, in other examples, some or all of the processing performed by the server 101 may be performed by the apparatus 103, and some or all of the processing performed by the apparatus 103 may be performed by the server 101.

[0042] Beginning at block 505, the processor 400 is configured to obtain image data and depth data via the sensors mentioned earlier (e.g. the depth camera 209, the cameras 207 and the LIDAR sensors 211). For example, the processor 400 can control the depth camera 209, the cameras 207 and the LIDARs 211 to capture image and depth data at each of a sequence of instances in time as the apparatus 103 travels along an aisle of shelves 110. Data capture at block 505 can be performed at various suitable frequencies, e.g. 30 Hz (although capture frequencies below and above 30 Hz are also contemplated).

[0043] Turning briefly to FIG. 6, an overhead view of the apparatus 103 is shown travelling along a path 600 to traverse an aisle formed by modules 604-1, 604-2 and 604-3, which may each have similar structural features to the modules 110 discussed in connection with FIG. 1. The field of view 308 of the depth camera 209 is also illustrated, as is the fields of illumination 300 of the illumination assemblies 213 (which coincide with each other when viewed from above). The fields of view of the cameras 207 may coincide with the fields of illumination 300. In some examples, the field of view of at least one camera 207 may be angled towards the direction of travel of the apparatus 103, e.g. in alignment with the field of view 308, or intermediate between the field of view 308 and the fields of illumination 300.

[0044] At a current performance of block 505, therefore, the apparatus 103 is configured to capture image and depth data depicting at least a portion of the module 604-1, as well as an obstacle 608.

[0045] Returning to FIG. 5, at block 510 the processor 400 (and particularly the obstacle detector and classifier 420) is configured to detect and classify obstacles in the data obtained at block 505. In general, an obstacle is an object detected in the data obtained at block 505 that does not appear in the map of the facility stored in the repository 412. The processor 400 can therefore be configured, at block 510, to detect objects in the captured data via any suitable object detection mechanism (e.g. detecting clusters in point cloud data, detecting edges in image data, and the like). The positions of such objects can be determined in the frame of reference 102 and compared to the above-mentioned map. Any detected objects that do not appear in the map can be stored as obstacles.

[0046] In the present example, the obstacle 608 is assumed to be an unmapped object, and is therefore detected as an obstacle at block 510. At block 510, the processor 400 is also configured to classify any detected obstacles. Obstacle classification, in the present example, includes determining whether the obstacle is a human obstacle. Various suitable human detection mechanisms can be implemented by the detector / classifier 420 at block 510. Examples of such mechanisms include support- vector machine (SVM) classification, decision tree classification, bag of words classification, and detection based on the use of local surface normals in the depth data. The detector / classifier 420 can generate an object boundary corresponding to each detected obstacle, as well as a classification associated with each detected obstacle indicating whether the obstacle is a human obstacle.

[0047] For example, referring to FIG. 7, a bounding box 700 is illustrated indicating a detected obstacle that has been classified as a human obstacle (i.e. the obstacle 608 shown in FIG. 6). Returning to FIG. 5, at block 515 the processor 400 is configured to determine, for each detected obstacle, whether the obstacle was classified as a human obstacle. When the determination at block 515 is affirmative, the processor 400 implements additional functionality as discussed below to control the illumination assemblies 213, in order to mitigate interference with the activities of customers, workers and the like within the facility.

[0048] At block 520, the processor 400, and particularly the feature detector 424, is configured to retrieve a portion of the image data that corresponds to the boundary (e.g. the bounding box 700) of the human-classified obstacle. Referring again to FIG. 7, image data 704 is illustrated, as captured at block 505. As will be apparent to those skilled in the art, the image data 704 may represent images captured by a plurality of sensors (e.g. at least one of the cameras 207 and/or the camera 209). The image data 704 is illustrated as a single combined image for simplicity, but may be processed as separate images in other implementations.

[0049] As noted earlier, captured image and depth data may be registered to the frame of reference 102, and the processor 400 can therefore determine, according to the frame of reference 102, which portion of the image data depicts the same region as is contained within the bounding box 700. Thus, in the present example performance of block 520, the processor 400 retrieves a portion 708 of the image data 704.

[0050] At block 525, the processor 400 (and particularly the feature detector 424) is configured to detect a predetermined feature of the obstacle. In the present example, the feature detected at block 525 is a human face. Human faces may be detected from image data according to any of a variety of suitable facial detection mechanisms. For example, the feature detector 424 can implement a convolutional neural network (CNN) accepting the portion 708 of the image data as input, and generating as output a feature boundary (e.g. a two-dimensional bounding box) and a confidence level. The confidence level indicates the probability that the feature (e.g. a face) is present in the boundary. Various forms of facial detection mechanisms may be employed, including a multi-scale cascade CNN, Regions with CNN features (R-CNN), You Only Look Once (YOLO) face detection, and the like.

[0051] Turning to FIG. 8, example output of a performance of block 525 is shown in the form of a bounding box 800 indicating a face detected by the feature detector 424. As will be apparent to those skilled in the art, various other features may be detected by the feature detector in addition to, or instead of, human faces. For example, the feature detector 424 may be configured to detect eyes (whether human or not). Also shown in FIG. 8 is a confidence level “C” associated with the detected bounding box 800, indicating that a probability of 80% that the box 800 contains a human face. [0052] When the determination at block 525 is affirmative, the processor 400 (and specifically the illumination controller 428) is configured to select an illumination control action at block 530. The illumination control action selected at block 530 serves to mitigate interference by the illumination assemblies 213 with the activities of humans such as customers or workers in the facility in which the apparatus 103 is deployed.

[0053] In some examples, the illumination control action selected at block 530 is to dim (i.e. reduce the intensity of) the illumination assemblies 213, or to disable the illumination assemblies 213. In other examples, however, only a subset of the illumination assemblies 213 are dimmed or disabled, according to the position of the feature detected at block 525. For example, the illumination controller 428 can store a range of heights (e.g. as measured from a floor of the facility, according to the frame of reference 102) for each illumination assembly 213. At block 530, the processor 400 can select any illumination assembly 213 with a height range than overlaps with a height range of the feature detected at block 525.

[0054] For example, referring again to FIG. 8, the processor 400 can select any illumination assembly 213 that corresponds to a height range that overlaps with the height range “H” defined by the lower edge of the bounding box 800 (at a height HI) and the upper edge of the bounding box 800 (at a height H2). The apparatus 103 is shown in FIG. 8 with five illumination assemblies 213-1 to 213-5, each with a corresponding height range 804-1, 804-2, 804-3, 804-4, and 804-5. The ranges 804 correspond to the extents of the fields of illumination 300 of the illumination assemblies 213. As shown in FIG. 8, the height range H of the feature boundary 800 overlaps with the height ranges 804-2 and 804-3. Therefore, at block 530 the processor 400 can select an illumination control action to dim or disable the illumination assemblies 213-2 and 213-3. Whether the illumination control includes dimming or disabling the selected illumination assemblies can be configured within the illumination controller 428. [0055] Selecting an illumination control action at block 530 can include comparing the confidence level associated with the detected feature to a threshold (e.g. 40%, although various other thresholds may also be employed). If the confidence level exceeds the threshold, the illumination control action is to dim or disable certain illumination assemblies 213. If the confidence level does not exceed the threshold, however, the illumination control action is to return (or maintain) the relevant illumination assemblies 213 to default illumination parameters, discussed below.

[0056] Following selection of the illumination control action at block 530, at block 535 the illumination controller 428 is configured to apply the selected illumination control action to the illumination subsystem. That is, the selected illumination assemblies 213 are dimmed or disabled at block 535. FIG. 9 illustrates an example performance of block 535, in which the illumination assemblies 213-2 and 213-3 have been disabled. The performance of the method 500 can then be repeated for the next data capture at block 505. As will be apparent to those skilled in the art, the processor 400 may also update the path 600 to navigate around any detected obstacles (both human and non human).

[0057] When the determination at block 525 is negative, rather than selecting an illumination control action at block 530, the processor 400 proceeds to block 540 and selects default illumination parameters for the illumination assemblies 213. The default parameters may be stored in the memory 404, and define a greater intensity of illumination for each assembly 213 than the illumination control actions selected at block 530. The processor 400 also proceeds to block 540 following a negative determination at block 515.

[0058] In some examples, the processor 400 can implement additional functionality in the selection of an illumination control action. Rather than selecting illumination assemblies for dimming or disabling based on a single detected height of the feature boundary 800, the processor 400 can maintain a persistent set of feature probabilities. The set of probabilities is updated with each feature detection, and the illumination control action is selected based on the set of probabilities. In other words, selection of an illumination control action at block 530 is based not only on the current capture (i.e. the data from the most recent performance of block 505), but also on feature detections from earlier captures. This process may mitigate rapid cycling of illumination assemblies 213 in response to occasional data captures in which an obstacle is not correctly detected. For example, in a series of thirty frames (i.e. thirty performances of block 505) while the apparatus 103 travels along an aisle, a person may be present in the vicinity of the apparatus 103 for all thirty frames but may only be detected in twenty of the frames. The remaining ten frames, lacking a feature detection, may result in illumination assemblies 213 being enabled or increased in intensity, only to be disabled again a fraction of a second later.

[0059] Turning to FIG. 10, a method 1000 of selecting illumination control actions following the detection of human obstacles at block 515 and of obstacle features at block 525 is illustrated. At block 1005, having detected a feature and generated a confidence level associated with the detected feature, the processor 400 is configured to update a set of feature probabilities. In particular, turning to FIG. 11, the processor 400 is configured to maintain a set of probabilities 1100 corresponding to respective positions relative to the apparatus 103. The set of probabilities 1100 is illustrated in FIG. 11 as a grid, parallel to the plane of the modules 604 and extending from a trailing edge 1104 at a predefined distance behind the current location of the apparatus 103 to a leading edge 1106 at a predefined distance ahead of the current location of the apparatus 103. The trailing edge 1104 may be, for example, 10 cm behind the current location (that is, 10 cm opposite the direction of travel of the apparatus 103). The leading edge 1106 may be 50 cm ahead of the current location of the apparatus 103. A wide variety of other distances for the trailing and leading edges 1104 and 1106 may also be employed.

[0060] The set of probabilities 1100 includes a subset 1108 corresponding to each height range 804 of the illumination assemblies 213. Thus, in the example shown in FIG. 11, five subsets 1108-1, 1108-2, 1108-3, 1108-4, and 1108-5 are illustrated. Each subset 1108 is further divided into a plurality of cells 1112. Each cell 1112 therefore corresponds to a position along the direction of travel of the apparatus 103, and to a height determined by the subset 1108 of which it is a member. As the apparatus 103 traverses an aisle, the trailing cells 1112 are dropped and additional cells 1112 are generated at the leading edge 1106.

[0061] To update the set 1100 responsive to a feature detection, the processor 400 is configured to identify the cells 1112 that correspond to the detected position of the feature (i.e. the boundary 800 shown in FIG. 8). As shown in FIG. 11, the shaded cells 1112 that intersect with the boundary 800 (illustrated overlaid on the set 1100) are updated at block 1005.

[0062] The update applied to each corresponding cell 1112 can take various forms. For example, a previous probability stored in each cell 1112 (e.g. a default of zero, prior to any updates) can be adjusted according to the confidence level associated with the boundary 800. For example, a previous value in a given cell 1112 can be modified by a difference between the previous value and the current value (e.g. the value of 0.8 shown in FIG. 8). The difference may, in some examples, be weighted by a predefined factor (e.g. 0.6, although smaller and larger factors may also be employed). Thus, if the previous value was zero, the updated value may be 0.48 (that is, the difference between 0.8 andO, multiplied by the predefined factor of 0.6). Thus, each cell 1112 that is shaded in FIG. 11 may be updated to contain the probability 0.48. In other examples, the factor mentioned above may be omitted, and various other adjustment mechanisms may be employed to update the cells 1112.

[0063] As will now be apparent, the set of probabilities 1100 is also updated in the absence of a feature detection (e.g. following a negative determination at block 525), and in the absence of a human obstacle classification (e.g. following a negative determination at block 515). Any cell 1112 that does not correspond to a detected feature (e.g. all the cells 1112 when no human obstacle has been detected) is updated with a current value of zero. Thus, a cell 1112 that previously contained a non-zero probability is adjusted downwards by the current value of zero.

[0064] Returning to FIG. 10, at block 1010 the processor 400 is configured to select a subset 1108 from the set 1100. At block 1015 the processor 400 is configured to generate a combined probability from the selected subset 1108. The combined probability can be an average of the values in each cell 1112 of the selected subset 1108. In other examples, the combined probability can be the maximum value among the cells 1112 of the selected subset 1108. In further examples, the processor 400 can generate a weighted average of the cells 1112 of the selected subset 1108, according to any of a variety of weighting functions. For example, cells 1112 at greater distances from the current location of the apparatus 103 may be weighted lower than cells 1112 at smaller distances from the current location of the apparatus 103.

[0065] The processor is configured to compare the combined probability to a threshold (e.g. the 40% mentioned above). When the combined probability exceeds the threshold, the processor 400 proceeds to block 1020, at which the illumination assembly 213 corresponding to the selected subset 1008 is disabled or dimmed. When the determination at block 1015 is negative, the illumination assembly 213 corresponding to the selected subset 1008 is enabled or increased in intensity (e.g. to a default intensity) at block 1025.

[0066] At block 1030, the processor 400 is configured to return to block 1010 until all subsets 1108 have been processed.

[0067] In the foregoing specification, specific embodiments have been described. However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the invention as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings.

[0068] The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential features or elements of any or all the claims. The invention is defined solely by the appended claims including any amendments made during the pendency of this application and all equivalents of those claims as issued.

[0069] Moreover in this document, relational terms such as first and second, top and bottom, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," “has”, “having,” “includes”, “including,” “contains”, “containing” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, has, includes, contains a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “comprises ...a”, “has ...a”, “includes ...a”, “contains ...a” does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, has, includes, contains the element. The terms “a” and “an” are defined as one or more unless explicitly stated otherwise herein. The terms “substantially”, “essentially”, “approximately”, “about” or any other version thereof, are defined as being close to as understood by one of ordinary skill in the art, and in one non-limiting embodiment the term is defined to be within 10%, in another embodiment within 5%, in another embodiment within 1% and in another embodiment within 0.5%. The term “coupled” as used herein is defined as connected, although not necessarily directly and not necessarily mechanically. A device or structure that is “configured” in a certain way is configured in at least that way, but may also be configured in ways that are not listed.

[0070] It will be appreciated that some embodiments may be comprised of one or more specialized processors (or “processing devices”) such as microprocessors, digital signal processors, customized processors and field programmable gate arrays (FPGAs) and unique stored program instructions (including both software and firmware) that control the one or more processors to implement, in conjunction with certain non-processor circuits, some, most, or all of the functions of the method and/or apparatus described herein. Alternatively, some or all functions could be implemented by a state machine that has no stored program instructions, or in one or more application specific integrated circuits (ASICs), in which each function or some combinations of certain of the functions are implemented as custom logic. Of course, a combination of the two approaches could be used.

[0071] Moreover, an embodiment can be implemented as a computer-readable storage medium having computer readable code stored thereon for programming a computer (e.g., comprising a processor) to perform a method as described and claimed herein. Examples of such computer-readable storage mediums include, but are not limited to, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory) and a Flash memory. Further, it is expected that one of ordinary skill, notwithstanding possibly significant effort and many design choices motivated by, for example, available time, current technology, and economic considerations, when guided by the concepts and principles disclosed herein will be readily capable of generating such software instructions and programs and ICs with minimal experimentation.

[0072] The Abstract of the Disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separately claimed subject matter.