Sequence of Expert: Boosting Imitation Planners for Autonomous Driving through Temporal Alternation
This addresses a critical robustness issue in autonomous driving for safer and more efficient systems, though it is incremental as it builds on existing imitation learning frameworks.
The paper tackles the problem of imitation learning planners in autonomous driving degrading in closed-loop due to error accumulation, proposing a temporal alternation method that improves performance without increasing model size or data, achieving state-of-the-art results on the nuPlan benchmark.
Imitation learning (IL) has emerged as a central paradigm in autonomous driving. While IL excels in matching expert behavior in open-loop settings by minimizing per-step prediction errors, its performance degrades unexpectedly in closed-loop due to the gradual accumulation of small, often imperceptible errors over time.Over successive planning cycles, these errors compound, potentially resulting in severe failures.Current research efforts predominantly rely on increasingly sophisticated network architectures or high-fidelity training datasets to enhance the robustness of IL planners against error accumulation, focusing on the state-level robustness at a single time point. However, autonomous driving is inherently a continuous-time process, and leveraging the temporal scale to enhance robustness may provide a new perspective for addressing this issue.To this end, we propose a method termed Sequence of Experts (SoE), a temporal alternation policy that enhances closed-loop performance without increasing model size or data requirements. Our experiments on large-scale autonomous driving benchmarks nuPlan demonstrate that SoE method consistently and significantly improves the performance of all the evaluated models, and achieves state-of-the-art performance.This module may provide a key and widely applicable support for improving the training efficiency of autonomous driving models.