Research map / Label-efficient and robust learning / Recognition and long-tail
Toward Collaborative Autonomous Driving: Simulation Platform and End-to-End System
Genjia Liu, Yue Hu, Chenxin Xu, Weibo Mao, Junhao Ge, Zhengxiang Huang, Yifan Lu, Yinda Xu, Junkai Xia, Yafei Wang, Siheng Chen
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 V2X collaboration to LiDAR end-to-end driving (ablation) | CoDriving · V2Xverse closed-loop driving | Driving score: 33.81 -> 77.15 | Improved |
| add V2X collaboration to camera end-to-end driving (ablation) | CoDriving · V2Xverse closed-loop driving | Driving score: 38.88 -> 45.06 | Improved |
| add collaboration to LiDAR perception (ablation) | CoDriving · V2Xverse town5 test | mAP30: 0.57 -> 0.68 | Improved |
| add collaboration to camera perception (ablation) | CoDriving · V2Xverse town5 test | mAP30: 0.45 -> 0.62 | Improved |
| add collaboration to camera planning (ablation) | CoDriving · V2Xverse town5 test | FDE: 1.531 -> 1.375 | Improved |
| add collaboration to LiDAR planning (ablation) | CoDriving · V2Xverse town5 test | FDE: 1.460 -> 1.413 | Improved |
| use LiDAR instead of camera input with collaboration (ablation) | CoDriving · V2Xverse closed-loop driving | Driving score: 45.06 -> 77.15 | Improved |
| use CoDriving instead of single-agent end-to-end TCP | end-to-end driving · V2Xverse closed-loop driving | Driving score: 47.48 -> 77.15 | Improved |
| use CoDriving instead of Coopernaut | collaborative driving · V2Xverse closed-loop driving | Driving score: 8.36 -> 77.15 | Improved |
| use driving-request-aware selection instead of perception-only selection (ablation) | CoDriving · V2Xverse bandwidth trade-off | Driving score | Improved |
| use CoDriving instead of late fusion | collaborative driving · V2Xverse closed-loop driving | Driving score: 52.40 -> 77.15 | Improved |
| use CoDriving instead of early fusion | collaborative driving · V2Xverse closed-loop driving | Driving score: 59.12 -> 77.15 | Improved |
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.
- Coopernaut — Coopernaut: End-to-End Driving With Cooperative Perception for Networked Vehicles (CVPR 2022) · better on 1 of 1 shared result
- TransFuser — TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving (TPAMI 2022) · better on 1 of 1 shared result
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
- End-to-End Autonomous Driving Through V2X Cooperation (AAAI 2025 · similarity 0.91)
- Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving (NeurIPS 2024 · similarity 0.90)
- MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving (NeurIPS 2026 · similarity 0.88)
- Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI 2025 · similarity 0.87)
- Autonomous Driving Research Requires a Community-Driven Data Paradigm (NeurIPS 2026 · similarity 0.87)
- SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving (CVPR 2025 · 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.
