Risk-aware motion planning for automated vehicle among human-driven cars
Abstract
We consider the maneuver planning problem for automated vehicles when they share the road with human-driven cars and interact with each other using a finite set of maneuvers. Each maneuver is calculated considering input constraints, actuator disturbances and sensor noise, so that we can use a maneuver automaton to perform higher-level planning that is robust against lower-level effects. In order to model the behavior of human-driven cars in response to the intent of the automated vehicle, we use control improvisation to build a probabilistic model. To accommodate for potential mismatches between the learned human model and human driving behaviors, we use a conditional value-at-risk objective function to obtain the optimal policy for the automated vehicle. We demonstrate through simulations that our motion planning framework consisting of an interactive human driving model and risk-aware motion planning strategy makes it possible to adapt to different traffic conditions and confidence levels.
Additional Information
© 2019 AACC. This work is supported by NSF VeHiCal project (Grant Number 1545126) and by the European Commission UnCoVerCPS project (Grant Number 643921).Attached Files
Submitted - gsma19-acc_s.pdf
Files
Name | Size | Download all |
---|---|---|
md5:c0f1b0ff4924a9a0beada60dd40fa9b4
|
627.9 kB | Preview Download |
Additional details
- Eprint ID
- 98446
- Resolver ID
- CaltechAUTHORS:20190905-152940342
- NSF
- CNS-1545126
- European Research Council (ERC)
- 643921
- Created
-
2019-09-05Created from EPrint's datestamp field
- Updated
-
2019-10-25Created from EPrint's last_modified field
- Caltech groups
- Center for Autonomous Systems and Technologies (CAST)