Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DISCRETE DECISION ARCHITECTURE FOR MOTION PLANNING SYSTEM OF AN AUTONOMOUS VEHICLE
Document Type and Number:
WIPO Patent Application WO/2019/140367
Kind Code:
A1
Abstract:
The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system (105) that generates constraints (834, 836) as part of determining a motion plan for an autonomous vehicle (10). In particular, a scenario generator (206) within a motion planning system (105) can generate constraints (834, 862) based on where objects of interest (814, 816) are predicted to be relative to an autonomous vehicle (10). A constraint solver (420) can identify navigation decisions (435) for each of the constraints (834, 836) that provide a consistent solution across all constraints (834, 836). The solution provided by the constraint solver (420) can be in the form of a trajectory path (425, 850, 865, 866, 867, 945) determined relative to constraint areas (834, 836) for all objects of interest (814, 816). The trajectory path (425, 850, 865, 866, 867, 945) represents a set of navigation decisions (435) such that a navigation decision relative to one constraint (836) doesn't sacrifice an ability to satisfy a different navigation decision relative to one or more other constraints (834, 836).

Inventors:
PHILLIPS MICHAEL LEE (US)
BURNETTE DON (US)
GOCHEV KALIN VASILEV (US)
LIEMHETCHARAT SOMCHAYA (US)
DAYANIDHI HARISHMA (US)
PERKO ERIC MICHAEL (US)
WILKINSON ERIC LLOYD (US)
GREEN COLIN JEFFREY (US)
LIU WEI (US)
STENTZ ANTHONY JOSEPH (US)
BRADLEY DAVID MCALLISTER (US)
MARDEN SAMUEL PHILIP (US)
Application Number:
PCT/US2019/013464
Publication Date:
July 18, 2019
Filing Date:
January 14, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UBER TECHNOLOGIES INC (US)
International Classes:
B60W30/095; B60W30/12; B60W30/16; B60W30/18; B60W50/00; G05D1/00; G05D1/02
Foreign References:
US20150073663A12015-03-12
EP2945140A12015-11-18
US9120484B12015-09-01
US201816058364A2018-08-08
US201816058430A2018-08-08
Other References:
ALESIANI FRANCESCO ET AL: "Locally Growing Rapid Tree (LGRT) motion planning for autonomous driving", 2016 IEEE 19TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), IEEE, 1 November 2016 (2016-11-01), pages 1120 - 1125, XP033028480, DOI: 10.1109/ITSC.2016.7795697
Attorney, Agent or Firm:
ULSH, Jennifer L. et al. (US)
Download PDF: