Prediction-Based Reachability for Collision Avoidance in Autonomous Driving

TL;DR

This paper introduces a prediction-based reachability framework for autonomous driving that reduces conservatism in collision avoidance by using trajectory prediction and mode classification, improving safety and operational efficiency.

Contribution

It proposes a novel approach combining trajectory prediction and mode clustering with reachability to enhance collision avoidance in autonomous vehicles.

Findings

Reduces conservatism in safety controllers

Largely avoids collisions in simulated scenarios

Maintains vehicle operation efficiency

Abstract

Safety is an important topic in autonomous driving since any collision may cause serious injury to people and damage to property. Hamilton-Jacobi (HJ) Reachability is a formal method that verifies safety in multi-agent interaction and provides a safety controller for collision avoidance. However, due to the worst-case assumption on the cars future behaviours, reachability might result in too much conservatism such that the normal operation of the vehicle is badly hindered. In this paper, we leverage the power of trajectory prediction and propose a prediction-based reachability framework to compute safety controllers. Instead of always assuming the worst case, we cluster the car's behaviors into multiple driving modes, e.g. left turn or right turn. Under each mode, a reachability-based safety controller is designed based on a less conservative action set. For online implementation, we first utilize the trajectory prediction and our proposed mode classifier to predict the possible modes, and then deploy the corresponding safety controller. Through simulations in a T-intersection and an 8-way roundabout, we demonstrate that our prediction-based reachability method largely avoids collision between two interacting cars and reduces the conservatism that the safety controller brings to the car's original operation.