Safe planning and control under uncertainty for self-driving

TL;DR

This paper presents a unified framework for safe self-driving motion planning that accounts for uncertainties in vehicle motion and obstacle prediction, integrating trajectory prediction, robust control, and online uncertainty estimation.

Contribution

It introduces a novel obstacle avoidance framework combining trajectory prediction, tube MPC control, and online uncertainty estimation for safer autonomous driving.

Findings

Effective in CARLA simulator demonstrating safety and real-time performance.

Combines short-term and long-term prediction for better obstacle handling.

Robust control guarantees safety despite uncertainties.

Abstract

Motion Planning under uncertainty is critical for safe self-driving. In this paper, we propose a unified obstacle avoidance framework that deals with 1) uncertainty in ego-vehicle motion; and 2) prediction uncertainty of dynamic obstacles from environment. A two-stage traffic participant trajectory predictor comprising short-term and long-term prediction is used in the planning layer to generate safe but not over-conservative trajectories for the ego vehicle. The prediction module cooperates well with existing planning approaches. Our work showcases its effectiveness in a Frenet frame planner. A robust controller using tube MPC guarantees safe execution of the trajectory in the presence of state noise and dynamic model uncertainty. A Gaussian process regression model is used for online identification of the uncertainty's bound. We demonstrate effectiveness, safety, and real-time performance of our framework in the CARLA simulator.