Guaranteed Safe Reachability-based Trajectory Design for a High-Fidelity Model of an Autonomous Passenger Vehicle
Sean Vaskov · Utkarsh Sharma · Shreyas Kousik · Matthew Johnson-Roberson · Ramanarayan Vasudevan
TL;DR
Reachability-based Trajectory Design is applied to a full-dynamics passenger car in simulation, planning safe trajectories in real time where NMPC and RRT comparisons fall short.
BRIEF
Self-driving cars must plan trajectories while sensing only part of the road ahead, so they re-plan continuously as new obstacles appear. Reachability-based Trajectory Design (RTD) precomputes the set of places a vehicle could reach when tracking parameterized trajectories, then uses it online to turn obstacles into constraints that guarantee safety. Until now RTD had only been used on small mobile robots. Here it is applied to a passenger vehicle in CarSim with full powertrain, chassis, and tire dynamics, driving up to 15 m/s among randomly placed obstacles, and compared with NMPC and RRT.
Abstract
Trajectory planning is challenging for autonomous cars since they operate in unpredictable environments with limited sensor horizons. To incorporate new information as it is sensed, planning is done in a loop, with the next plan being computed as the previous plan is executed. The recent Reachability-based Trajectory Design (RTD) is a provably safe, real-time algorithm for trajectory planning. RTD consists of an offline component, where a Forward Reachable Set (FRS) is computed for the vehicle tracking parameterized trajectories; and an online part, where the FRS is used to map obstacles to constraints for trajectory optimization in a provably-safe way. In the literature, RTD has only been applied to small mobile robots. The contribution of this work is applying RTD to a passenger vehicle in CarSim, with a full powertrain model, chassis and tire dynamics. RTD produces safe trajectory plans with the vehicle traveling up to 15 m/s on a two-lane road, with randomly-placed obstacles only known to the vehicle when detected within its sensor horizon. RTD is compared with a Nonlinear Model-Predictive Control (NMPC) and a Rapidly-exploring Random Tree (RRT) approach. The experiment demonstrates RTD's ability to plan safe trajectories in real time, in contrast to the existing state-of-the-art approaches.