TR2020-165

Reachability-based Decision Making for Autonomous Driving: Theory and Experiment


    •  Ahn, H., Berntorp, K., Inani, P., Ram, A.J., Di Cairano, S., "Reachability-based Decision Making for Autonomous Driving: Theory and Experiment", IEEE Transactions on Control Systems Technology, December 2020.
      BibTeX TR2020-165 PDF
      • @article{Ahn2020dec,
      • author = {Ahn, Heejin and Berntorp, Karl and Inani, Pranav and Ram, Arjun Jagdish and Di Cairano, Stefano},
      • title = {Reachability-based Decision Making for Autonomous Driving: Theory and Experiment},
      • journal = {IEEE Transactions on Control Systems Technology},
      • year = 2020,
      • month = dec,
      • url = {https://www.merl.com/publications/TR2020-165}
      • }
  • MERL Contacts:
  • Research Areas:

    Control, Robotics

We describe the design and validation of a decision making system in the guidance and control architecture for automated driving. The decision making system determines the timing of transitions through a sequence of driving modes, such as lane following and stopping, for the vehicle to eventually arrive at the destination without colliding with obstacles, hence achieving safety and liveness. The decision making system commands a transition to the next mode only when it is possible for an underlying motion planner to generate a feasible trajectory that reaches the target region of such next mode. Using forward and backward reachable sets based on a simplified dynamical model, the decision making system determines the existence of a trajectory that reaches the target region, without actually computing it. Thus, the decision making system achieves fast computation, resulting in reactivity to a varying environment and reduced computational burden. To handle the discrepancy between the dynamical model and actual vehicle motion, we model it as a bounded disturbance set and guarantee robustness against it. We prove the safety and liveness of the decision making system, and validate it using small-scale car-like robots.