Risk-Constrained Interactive Safety under Behavior Uncertainty for Autonomous Driving

TL;DR

This paper introduces a risk-constrained interactive planning method for autonomous driving that balances safety and efficiency by modeling behavior uncertainty and using a probabilistic safety objective, demonstrated through simulation.

Contribution

It formalizes a safety objective based on probabilistic risk, models it with a novel Bayesian game, and solves it using a new Multi-Agent Monte Carlo Tree Search variant.

Findings

Outperforms baseline approaches in simulation

Achieves specified violation risk levels

Provides interpretable and tunable safety control

Abstract

Balancing safety and efficiency when planning in dense traffic is challenging. Interactive behavior planners incorporate prediction uncertainty and interactivity inherent to these traffic situations. Yet, their use of single-objective optimality impedes interpretability of the resulting safety goal. Safety envelopes which restrict the allowed planning region yield interpretable safety under the presence of behavior uncertainty, yet, they sacrifice efficiency in dense traffic due to conservative driving. Studies show that humans balance safety and efficiency in dense traffic by accepting a probabilistic risk of violating the safety envelope. In this work, we adopt this safety objective for interactive planning. Specifically, we formalize this safety objective, present the Risk-Constrained Robust Stochastic Bayesian Game modeling interactive decisions satisfying a maximum risk of violating a safety envelope under uncertainty of other traffic participants' behavior and solve it using our variant of Multi-Agent Monte Carlo Tree Search. We demonstrate in simulation that our approach outperforms baselines approaches, and by reaching the specified violation risk level over driven simulation time, provides an interpretable and tunable safety objective for interactive planning.