Research map / Vision-language and multimodal / Robot action and navigation
DriveVLN: Towards Mapless Vision-and-Language Navigation in Autonomous Driving
Dongqian Guo, Haoran Wei, Wencheng Han, Runzhou Tao, Zhongying Qiu, Jianfei Yang, Jianbing Shen
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 Policy Tempering (GRPO reinforcement learning) after SFT (ablation) | DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner) | Driving Score: 0.49 -> 0.67 | Improved |
| add Policy Tempering after SFT (ablation) | DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner) | Success Rate: 0.21 -> 0.44 | Improved |
| add Policy Tempering after SFT (ablation) | DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner) | Avg. L2 (m): 0.457 -> 0.283 | Improved |
| add Policy Tempering after SFT (ablation) | DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner) | Avg. collision rate (%): 0.107 -> 0.096 | Improved |
| add Policy Tempering with expert-trajectory planner (ablation) | DriveVLN selector · DriveVLN benchmark (Expert planner) | Success Rate: 0.23 -> 0.51 | Improved |
| replace DiffusionDrive planner with expert trajectories (ablation) | DriveVLN SFT+RL · DriveVLN benchmark | Success Rate: 0.44 -> 0.51 | Improved |
| use the small fine-tuned DriveVLN selector instead of large VLMs | navigation selector · DriveVLN benchmark | Driving Score: 0.60 -> 0.67 (vs Seed-1.6) | Improved |
| use DriveVLN instead of GPT-5 for exit and entrance trajectory selection | navigation selector · Real-world data, exit and entrance | trajectory selection accuracy (%): 63.19 -> 56.24 | Hurt |
Closest papers by meaning
- VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation (AAAI 2024 · similarity 0.91)
- Less Language, More Latents: Annotation-Efficient VLAs for Driving (NeurIPS 2026 · similarity 0.89)
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning (NeurIPS 2025 · similarity 0.88)
- Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving (CVPR 2026 · similarity 0.88)
- Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning (AAAI 2026 · similarity 0.88)
- SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving (CVPR 2026 · similarity 0.87)
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.
