Safe and Non-Conservative Trajectory Planning for Autonomous Driving Handling Unanticipated Behaviors of Traffic Participants

TL;DR

The paper addresses safe trajectory planning for autonomous driving in the presence of unanticipated behaviors of traffic participants. It proposes a novel SMPC+CVPM framework that uses optimistic SMPC planning for efficiency and a safety-certification step based on constraint violation probability minimization to handle deviations from predictions. The main contributions are a cascaded yet computation-friendly integration of SMPC with CVPM, a robust feasibility check to certify safety, and a probabilistic fallback that minimizes collision risk when robustness is infeasible. Validation on benchmark scenarios demonstrates reduced conservatism without sacrificing safety, enabling practical, non-conservative planning in uncertain traffic environments.

Abstract

Trajectory planning for autonomous driving is challenging because the unknown future motion of traffic participants must be accounted for, yielding large uncertainty. Stochastic Model Predictive Control (SMPC)-based planners provide non-conservative planning, but do not rule out a (small) probability of collision. We propose a control scheme that yields an efficient trajectory based on SMPC when the traffic scenario allows, still avoiding that the vehicle causes collisions with traffic participants if the latter move according to the prediction assumptions. If some traffic participant does not behave as anticipated, no safety guarantee can be given. Then, our approach yields a trajectory which minimizes the probability of collision, using Constraint Violation Probability Minimization techniques. Our algorithm can also be adapted to minimize the anticipated harm caused by a collision. We provide a thorough discussion of the benefits of our novel control scheme and compare it to a previous approach through numerical simulations from the CommonRoad database.

Theorems & Definitions (2)

• Definition 1
• Remark 1