Research map / Reinforcement learning / Visual and representation RL
CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
Yihong Guo, Dongqiangzi Ye, Sijia Chen, Anqi Liu, Xianming Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add self-correction at inference (ablation) | CorrectionPlanner · Waymo collision | collision rate: 2.20 -> 1.68 | Improved |
| add self-correction at inference (ablation) | CorrectionPlanner · nuPlan collision | collision rate: 2.45 -> 2.04 | Improved |
| add self-correction at inference to IL policy (ablation) | IL · Waymo collision | collision rate: 2.34 -> 2.31 | No clear effect |
| add RL training (ablation) | IL · Waymo collision | collision rate: 2.34 -> 2.21 | Improved |
| add correction-trace aggregation instead of conditioning on last unsafe token (ablation) | Alternate Self-Correction · Waymo collision | collision rate: 2.01 -> 1.68 | Improved |
| use self-correction instead of rejection sampling (RL) (ablation) | Rej. Sampling RL · Waymo collision | collision rate: 2.09 -> 1.68 | Improved |
| use self-correction instead of candidate selection (RL) (ablation) | Candidate Sel. RL · Waymo collision | collision rate: 2.14 -> 1.68 | Improved |
| lower collision critic threshold from 0.75 to 0.7 (CL=5) (ablation) | CorrectionPlanner · Waymo | collision rate / progression: 1.68 -> 1.47; 94.23 -> 77.50 | Mixed |
| raise correction length from 1 to 5 (threshold 0.75) (ablation) | CorrectionPlanner · Waymo | collision rate: 2.02 -> 1.68 | Improved |
| raise critic horizon k from 1 to 5 (ablation) | collision critic · Waymo collision | collision rate: 2.19 -> 1.68 | Improved |
| raise critic horizon k from 5 to 7 (ablation) | collision critic · Waymo | collision rate / progression: 1.68 -> 1.63; 94.23 -> 91.42 | Mixed |
| add self-correction to policy trained on nuPlan (zero-shot to Waymax) (ablation) | CorrectionPlanner · Waymax zero-shot | collision rate: 2.93 -> 2.62 | Improved |
Closest papers by meaning
- ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving (NeurIPS 2026 · similarity 0.89)
- Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving (NeurIPS 2026 · similarity 0.87)
- CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-Scale Reinforcement Learning in Autonomous Driving (CVPR 2025 · similarity 0.87)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.86)
- AdaWM: Adaptive World Model based Planning for Autonomous Driving (ICLR 2025 · similarity 0.86)
- Diffusion-Based Planning for Autonomous Driving with Flexible Guidance (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
