AI Paper Atlas

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

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation

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 changedWhereMeasuredEffect
add Policy Tempering (GRPO reinforcement learning) after SFT (ablation)DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner)Driving Score: 0.49 -> 0.67Improved
add Policy Tempering after SFT (ablation)DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner)Success Rate: 0.21 -> 0.44Improved
add Policy Tempering after SFT (ablation)DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner)Avg. L2 (m): 0.457 -> 0.283Improved
add Policy Tempering after SFT (ablation)DriveVLN selector · DriveVLN benchmark (DiffusionDrive planner)Avg. collision rate (%): 0.107 -> 0.096Improved
add Policy Tempering with expert-trajectory planner (ablation)DriveVLN selector · DriveVLN benchmark (Expert planner)Success Rate: 0.23 -> 0.51Improved
replace DiffusionDrive planner with expert trajectories (ablation)DriveVLN SFT+RL · DriveVLN benchmarkSuccess Rate: 0.44 -> 0.51Improved
use the small fine-tuned DriveVLN selector instead of large VLMsnavigation selector · DriveVLN benchmarkDriving Score: 0.60 -> 0.67 (vs Seed-1.6)Improved
use DriveVLN instead of GPT-5 for exit and entrance trajectory selectionnavigation selector · Real-world data, exit and entrancetrajectory selection accuracy (%): 63.19 -> 56.24Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy