US 11,884,294 B2
Lane change planning and control in autonomous machine applications
Zhenyi Zhang, Los Altos, CA (US); Yizhou Wang, San Jose, CA (US); David Nister, Bellevue, WA (US); and Neda Cvijetic, East Palo Alto, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Dec. 22, 2020, as Appl. No. 17/130,667.
Claims priority of provisional application 62/955,233, filed on Dec. 30, 2019.
Prior Publication US 2021/0197858 A1, Jul. 1, 2021
Int. Cl. B60W 60/00 (2020.01); B60W 30/18 (2012.01); B60W 30/095 (2012.01); B60W 40/105 (2012.01)
CPC B60W 60/0011 (2020.02) [B60W 30/0956 (2013.01); B60W 30/18163 (2013.01); B60W 40/105 (2013.01); B60W 2420/42 (2013.01); B60W 2420/52 (2013.01); B60W 2552/53 (2020.02)] 23 Claims
OG exemplary drawing
 
1. A method comprising:
identifying, based at least on a representation of an environment indicating at least an ego-lane and a target lane adjacent the ego-lane, candidate lane change gaps within the target lane for an ego-vehicle to maneuver into;
determining one or more first scores for a first speed profile candidate of a plurality of longitudinal speed profile candidates for a lane change gap of the candidate lane change gaps;
determining one or more second scores for a second speed profile candidate of the plurality of longitudinal speed profile candidates for the lane change gap;
computing an aggregate score for the lane change gap based at least on an aggregation of the one or more first scores and the one or more second scores;
selecting the lane change gap from the candidate lane change gaps based at least on the aggregate score; and
executing a lane change according to a longitudinal speed profile selected from the plurality of longitudinal speed profile candidates and the selected lane change gap.