CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving

• URL: http://arxiv.org/abs/2603.15771v1
• Date: Mon, 16 Mar 2026 18:03:21 GMT
• Title: CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
• Abstract summary: CorrectionPlanner is an autoregressive planner with self-correction.<n>It reduces collision rate by over 20% on Waymax and achieves state-of-the-art planning scores on nuPlan.
• Score: 55.88697462014118
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous driving requires safe planning, but most learning-based planners lack explicit self-correction ability: once an unsafe action is proposed, there is no mechanism to correct it. Thus, we propose CorrectionPlanner, an autoregressive planner with self-correction that models planning as motion-token generation within a propose, evaluate, and correct loop. At each planning step, the policy proposes an action, namely a motion token, and a learned collision critic predicts whether it will induce a collision within a short horizon. If the critic predicts a collision, we retain the sequence of historical unsafe motion tokens as a self-correction trace, generate the next motion token conditioned on it, and repeat this process until a safe motion token is proposed or the safety criterion is met. This self-correction trace, consisting of all unsafe motion tokens, represents the planner's correction process in motion-token space, analogous to a reasoning trace in language models. We train the planner with imitation learning followed by model-based reinforcement learning using rollouts from a pretrained world model that realistically models agents' reactive behaviors. Closed-loop evaluations show that CorrectionPlanner reduces collision rate by over 20% on Waymax and achieves state-of-the-art planning scores on nuPlan.

Related papers

• World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning [60.88859946006306]
  Adversa World Modeling is a theoretically grounded multi-agent self-play fine-tuning framework.<n>In inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions.<n> Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions.
  arXiv  Detail & Related papers  (2026-07-12T07:44:16Z)
• Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling [74.41886258801209]
  We propose a two-stage trajectory planning framework that decouples principle alignment from behavior learning.<n>Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-23T09:22:19Z)
• 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)
• Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling [21.45039811922009]
  We advocate a self-refining scheme that iteratively refines a draft plan until an equilibrium is reached.<n>A nested equilibrium sequence modeling procedure is devised for efficient closed-loop planning.<n>Our method is evaluated on the VirtualHome-Env benchmark, showing advanced performance with improved scaling w.r.t. inference-time computation.
  arXiv  Detail & Related papers  (2024-10-02T11:42:49Z)
• Model Checking for Closed-Loop Robot Reactive Planning [0.0]
  We show how model checking can be used to create multistep plans for a differential drive wheeled robot so that it can avoid immediate danger. Using a small, purpose built model checking algorithm in situ we generate plans in real-time in a way that reflects the egocentric reactive response of simple biological agents.
  arXiv  Detail & Related papers  (2023-11-16T11:02:29Z)
• Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior [135.78858513845233]
  STRIVE is a method to automatically generate challenging scenarios that cause a given planner to produce undesirable behavior, like collisions. To maintain scenario plausibility, the key idea is to leverage a learned model of traffic motion in the form of a graph-based conditional VAE. A subsequent optimization is used to find a "solution" to the scenario, ensuring it is useful to improve the given planner.
  arXiv  Detail & Related papers  (2021-12-09T18:03:27Z)
• Deep Structured Reactive Planning [94.92994828905984]
  We propose a novel data-driven, reactive planning objective for self-driving vehicles. We show that our model outperforms a non-reactive variant in successfully completing highly complex maneuvers.
  arXiv  Detail & Related papers  (2021-01-18T01:43:36Z)
• Enhancing Lattice-based Motion Planning with Introspective Learning and Reasoning [3.2689702143620143]
  This work is concerned with introspective learning and reasoning about controller performance over time. Normal controller execution of the different actions is learned using reliable and uncertainty-aware machine learning techniques. Reasoning takes place to both verify that the learned models stays safe and to improve collision checking effectiveness in the motion planner.
  arXiv  Detail & Related papers  (2020-05-15T07:16:51Z)

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.