On Infusing Reachability-Based Safety Assurance within Planning Frameworks for Human-Robot Vehicle Interactions
| Autor: | Edward Schmerling, Mo Chen, J. Christian Gerdes, Mengxuan Zhang, John Talbot, Karen Leung, Marco Pavone |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Process management Computer science Applied Mathematics Mechanical Engineering 02 engineering and technology Proactivity Systems and Control (eess.SY) Electrical Engineering and Systems Science - Systems and Control Human–robot interaction Computer Science - Robotics 020901 industrial engineering & automation Action (philosophy) Artificial Intelligence Anticipation (artificial intelligence) Reachability Modeling and Simulation Safety assurance 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Electrical and Electronic Engineering Robotics (cs.RO) Software |
| DOI: | 10.48550/arxiv.2012.03390 |
| Popis: | Action anticipation, intent prediction, and proactive behavior are all desirable characteristics for autonomous driving policies in interactive scenarios. Paramount, however, is ensuring safety on the road -- a key challenge in doing so is accounting for uncertainty in human driver actions without unduly impacting planner performance. This paper introduces a minimally-interventional safety controller operating within an autonomous vehicle control stack with the role of ensuring collision-free interaction with an externally controlled (e.g., human-driven) counterpart while respecting static obstacles such as a road boundary wall. We leverage reachability analysis to construct a real-time (100Hz) controller that serves the dual role of (i) tracking an input trajectory from a higher-level planning algorithm using model predictive control, and (ii) assuring safety by maintaining the availability of a collision-free escape maneuver as a persistent constraint regardless of whatever future actions the other car takes. A full-scale steer-by-wire platform is used to conduct traffic weaving experiments wherein two cars, initially side-by-side, must swap lanes in a limited amount of time and distance, emulating cars merging onto/off of a highway. We demonstrate that, with our control stack, the autonomous vehicle is able to avoid collision even when the other car defies the planner's expectations and takes dangerous actions, either carelessly or with the intent to collide, and otherwise deviates minimally from the planned trajectory to the extent required to maintain safety. Comment: arXiv admin note: text overlap with arXiv:1812.11315 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|