Driving is a Game: Combining Planning and Prediction with Bayesian Iterative Best Response

TL;DR

This paper introduces BIBeR, a novel framework that unifies motion prediction and game-theoretic planning through iterative best response, improving autonomous driving performance in complex urban scenarios by modeling agent interactions.

Contribution

BIBeR is the first to integrate a state-of-the-art predictor into an iterative game-theoretic planning loop, enabling bidirectional adaptation and improved decision-making in autonomous driving.

Findings

Achieves 11% improvement over state-of-the-art planners in lane-change scenarios.

Outperforms existing approaches on nuPlan benchmarks.

Provides a unified, transparent framework combining prediction and planning.

Abstract

Autonomous driving planning systems perform nearly perfectly in routine scenarios using lightweight, rule-based methods but still struggle in dense urban traffic, where lane changes and merges require anticipating and influencing other agents. Modern motion predictors offer highly accurate forecasts, yet their integration into planning is mostly rudimental: discarding unsafe plans. Similarly, end-to-end models offer a one-way integration that avoids the challenges of joint prediction and planning modeling under uncertainty. In contrast, game-theoretic formulations offer a principled alternative but have seen limited adoption in autonomous driving. We present Bayesian Iterative Best Response (BIBeR), a framework that unifies motion prediction and game-theoretic planning into a single interaction-aware process. BIBeR is the first to integrate a state-of-the-art predictor into an Iterative Best Response (IBR) loop, repeatedly refining the strategies of the ego vehicle and surrounding agents. This repeated best-response process approximates a Nash equilibrium, enabling bidirectional adaptation where the ego both reacts to and shapes the behavior of others. In addition, our proposed Bayesian confidence estimation quantifies prediction reliability and modulates update strength, more conservative under low confidence and more decisive under high confidence. BIBeR is compatible with modern predictors and planners, combining the transparency of structured planning with the flexibility of learned models. Experiments show that BIBeR achieves an 11% improvement over state-of-the-art planners on highly interactive interPlan lane-change scenarios, while also outperforming existing approaches on standard nuPlan benchmarks.