Research map / Label-efficient and robust learning / Recognition and long-tail
Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
Bozhou Zhang, Jingyu Li, Nan Song, Li Zhang
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 |
|---|---|---|---|
| use position-guided attention with anchor guiding points instead of vanilla attention in perception (ablation) | VeteranAD · NAVSIM navtest | PDMS: 87.5 -> 90.2 | Improved |
| predict offsets from anchored guiding points instead of direct trajectory output (ablation) | VeteranAD · NAVSIM navtest | PDMS: 88.4 -> 90.2 | Improved |
| add BEV cross-attention (ablation) | VeteranAD · NAVSIM navtest | PDMS: 89.1 -> 90.2 | Improved |
| use all three attentions (image, BEV, agent) vs any pair (ablation) | VeteranAD · NAVSIM navtest | PDMS: 89.1-89.7 -> 90.2 | Improved |
| use autoregressive instead of non-autoregressive trajectory decoding (ablation) | VeteranAD · NAVSIM navtest | PDMS: 88.6 -> 90.2 | Improved |
| integrate VeteranAD design into VAD | VAD · nuScenes val | Average L2 (m): 0.72 -> 0.62 | Improved |
| integrate VeteranAD design into VAD | VAD · nuScenes val | Average collision rate (%): 0.22 -> 0.16 | Improved |
| integrate VeteranAD design into VAD | VAD · nuScenes val | FPS: 4.5 -> 4.3 | Hurt |
| VeteranAD vs DiffusionDrive latency | VeteranAD · NAVSIM efficiency | latency (ms): 18.4 -> 22.3 | Hurt |
| VeteranAD closed-loop vs DriveTransformer | VeteranAD · Bench2Drive closed-loop | Success Rate (%): 35.01 -> 33.85 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DriveTransformer — DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving (ICLR 2025) · better on 2 of 3 shared results
- DriveAdapter — DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving (ICCV 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- $AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning (ICLR 2026 · similarity 0.91)
- Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving (CVPR 2025 · similarity 0.90)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.90)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.90)
- Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning (AAAI 2026 · similarity 0.88)
- DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking (ICLR 2026 · similarity 0.88)
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.
