A computer-implemented method of determining a trajectory of an autonomous vehicle

Planning trajectory for an AV 10 by receiving a route 102 and sensing positions of surrounding objects 104, defining multiple passing strategies (fig 8) around the obstructions 104 as travel envelope 106 being a polygon in space-time having boundary lines formed from intersection points the AV inter...

Full description

Saved in:
Bibliographic Details
Main Authors Alex Stewart, Chi Hay Tong
Format Patent
LanguageEnglish
Published 27.12.2023
Subjects
CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION
CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES
PERFORMING OPERATIONS
ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT
TRANSPORTING
VEHICLES IN GENERAL
Online AccessGet full text

Cover

More Information
Summary:Planning trajectory for an AV 10 by receiving a route 102 and sensing positions of surrounding objects 104, defining multiple passing strategies (fig 8) around the obstructions 104 as travel envelope 106 being a polygon in space-time having boundary lines formed from intersection points the AV intersects with the objects, ranking the strategies, and selecting the highest ranked strategy. When ranking the strategies, the geometric features of the polygons, such as their areas, and a width of a pinch point bottleneck, may be compared. The AV may pass ahead or behind the objects (fig 6). Unreachable regions due to kinematic constraints of the AV may include top speed, maximum acceleration, or deceleration limit. The unreachable regions may be excluded from the travel envelope. Infeasible strategies may be disregarded. The future trajectories 105 of the objects may be predicted.
Bibliography:Application Number: GB20230003095