Sequence of Expert: Boosting Imitation Planners for Autonomous Driving through Temporal Alternation

• URL: http://arxiv.org/abs/2512.13094v1
• Date: Mon, 15 Dec 2025 08:50:23 GMT
• Title: Sequence of Expert: Boosting Imitation Planners for Autonomous Driving through Temporal Alternation
• Authors: Xiang Li, Gang Liu, Weitao Zhou, Hongyi Zhu, Zhong Cao,
• Abstract summary: Imitation learning (IL) has emerged as a central paradigm in autonomous driving.<n>IL excels in matching expert behavior in open-loop settings by minimizing per-step prediction errors.<n>Over successive planning cycles, small, often imperceptible errors compound, potentially resulting in severe failures.<n>We propose Sequence of Experts (SoE) to enhance closed-loop performance without increasing model size or data requirements.
• Score: 12.450883696383878
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs [22.486083545585984]
  Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting.<n>Existing approaches typically employ a naive autoregressive generation strategy.<n>We propose textbfF-LLM, a novel closed-loop framework.
  arXiv  Detail & Related papers  (2026-02-13T09:35:12Z)
• Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning [61.380634253724594]
  Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL)<n>We show that it is possible to overcome this problem by acting and exploring within the internal representations of an autoregressive model.
  arXiv  Detail & Related papers  (2025-12-23T18:51:50Z)
• Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving [17.533465904228844]
  We propose Mimir, a novel hierarchical dual-system framework capable of generating robust trajectories relying on goal points with uncertainty estimation.<n>Mimir surpasses previous state-of-the-art methods with a 20% improvement in the driving scoreS, while achieving 1.6 times improvement in high-level module inference speed.
  arXiv  Detail & Related papers  (2025-12-08T03:31:25Z)
• Learning Depth from Past Selves: Self-Evolution Contrast for Robust Depth Estimation [42.74561859065153]
  SEC-Depth is a self-evolution contrastive learning framework for self-supervised robust depth estimation tasks.<n>Our method integrates seamlessly into diverse baseline models and significantly enhances robustness in zero-shot evaluations.
  arXiv  Detail & Related papers  (2025-11-19T06:42:40Z)
• DAP: A Discrete-token Autoregressive Planner for Autonomous Driving [34.32497598431514]
  We introduce DAP, a discrete-token autoregressive planner that jointly forecasts BEV semantics and ego trajectories.<n>We incorporate a reinforcement-learning-based fine-tuning, which preserves supervised behavior cloning priors while injecting reward-guided improvements.<n>DAP achieves state-of-the-art performance on open-loop metrics and delivers competitive closed-loop results on the NAVSIM benchmark.
  arXiv  Detail & Related papers  (2025-11-17T12:31:33Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Lightweight Temporal Transformer Decomposition for Federated Autonomous Driving [11.79541267274746]
  We propose a method that processes sequential image frames and temporal steering data by breaking down large attention maps into smaller matrices.<n>This approach reduces model complexity, enabling efficient weight updates for convergence and real-time predictions.<n>Experiments on three datasets demonstrate that our method outperforms recent approaches by a clear margin while achieving real-time performance.
  arXiv  Detail & Related papers  (2025-06-30T05:14:16Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
  ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• Centaur: Robust End-to-End Autonomous Driving with Test-Time Training [84.78837437133234]
  We propose Centaur, which updates a planner's behavior via test-time training without relying on hand-engineered rules or cost functions.<n>We develop a novel uncertainty measure, called Cluster Entropy, which is simple, interpretable, and compatible with state-of-the-art planning algorithms.
  arXiv  Detail & Related papers  (2025-03-14T17:59:41Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Transient Fault Tolerant Semantic Segmentation for Autonomous Driving [44.725591200232884]
  We introduce ReLUMax, a simple activation function designed to enhance resilience against transient faults. Our experiments demonstrate that ReLUMax effectively improves robustness, preserving performance and boosting prediction confidence.
  arXiv  Detail & Related papers  (2024-08-30T00:27:46Z)
• Enhancing End-to-End Autonomous Driving with Latent World Model [78.22157677787239]
  We propose a novel self-supervised learning approach using the LAtent World model (LAW) for end-to-end driving.<n> LAW predicts future scene features based on current features and ego trajectories.<n>This self-supervised task can be seamlessly integrated into perception-free and perception-based frameworks.
  arXiv  Detail & Related papers  (2024-06-12T17:59:21Z)
• Self-Supervised Multi-Object Tracking For Autonomous Driving From Consistency Across Timescales [53.55369862746357]
  Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short compared to their supervised counterparts. We propose a training objective that enables self-supervised learning of re-identification features from multiple sequential frames.
  arXiv  Detail & Related papers  (2023-04-25T20:47:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.