Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning

2026-07-08

AI Summary

Existing motion planners perform well in-distribution but exhibit limited generalization and robustness when confronted with novel urban topologies and actuation perturbations. This work proposes the first zero-shot evaluation framework that integrates cross-domain semantic transfer with dynamic perturbation injection, establishing a dual-track benchmark to systematically assess planner performance. The framework leverages 3D scenario transfer from DeepScenario to nuPlan, multi-city scene testing, and randomized dynamics perturbations. Experimental results reveal that imitation learning methods are prone to failure in pedestrian-dense scenarios and highly sensitive to execution noise, whereas reinforcement learning approaches demonstrate superior safety and closed-loop robustness under distribution shifts and disturbances.

Abstract

While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel urban topologies and recovery mechanisms following execution perturbations remain under-explored. To address this, we present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift: (1) The Semantic Shift Track leverages a novel conversion pipeline that transforms the aerial, DeepScenario Open 3D dataset into the nuPlan simulation framework. This enables zero-shot evaluation of planners trained on North American and Singaporean data against 1,182 scenarios spanning four German cities and the US city of San Francisco featuring dense pedestrian-cyclist interactions. (2) The State-Distribution Drift Track injects stochastic perturbations into the ego vehicle's dynamics to quantify robustness against compounding execution errors. Based on this, we systematically evaluate the failure modes of diverse planning paradigms under semantic and state-distribution shifts. While imitation learning methods achieve high scores in ID benchmarks, they exhibit significant failures under semantic shift, particularly in pedestrian-dense environments, and suffer from persistent drift when subjected to temporally correlated actuation noise. In contrast, the evaluated reinforcement-learning-based planner demonstrates more graceful degradation, maintaining higher safety and progress metrics across both tracks. Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.

Problem

• distribution shift
• motion planning
• autonomous driving
• generalization
• robustness

Innovation

• zero-shot benchmark
• semantic shift
• state-distribution drift
• motion planning
• generalizable autonomous driving