Research map / Label-efficient and robust learning / Recognition and long-tail
End-to-End Driving with Online Trajectory Evaluation via BEV World Model
Yingyan Li, Yuqi Wang, Yang Liu, Jiawei He, Lue Fan, Zhaoxiang 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 |
|---|---|---|---|
| add trajectory evaluation (reward model on current state only) (ablation) | TransFuser baseline · NAVSIM test (ablation, 20 epochs) | PDMS: 81.0 -> 83.2 | Improved |
| add BEV world model future states to reward model (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 83.2 -> 85.6 | Improved |
| add simulation rewards to imitation reward (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 83.5 -> 85.6 | Improved |
| add imitation reward to simulation rewards (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 83.6 -> 85.6 | Improved |
| predict future recurrently with 2s step (0s->2s->4s) instead of one 4s step (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 84.0 -> 85.6 | Improved |
| increase trajectories from 64 to 128 (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 84.5 -> 85.4 | Improved |
| increase trajectories from 128 to 256 (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 85.4 -> 85.6 | Improved |
| increase trajectories from 64 to 256 (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | Latency: 17.2 ms -> 18.7 ms | Hurt |
| use 1024 unseen trajectory anchors at test time (trained on 256) (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 84.0 -> 85.3 | Improved |
| feed refined trajectories to world model instead of raw anchors (ablation) | WoTE · NAVSIM test (ablation, 20 epochs) | PDMS: 84.0 -> 85.6 | Improved |
| model-based trajectory evaluation instead of model-free (Hydra-MDP) | WoTE · NAVSIM test | PDMS: 86.5 -> 88.3 | Improved |
| add WoTE trajectory evaluation to TCP | TCP · Bench2Drive | Driving Score: 59.90 -> 61.71 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 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
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.88)
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.86)
- Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving (NeurIPS 2024 · similarity 0.85)
- Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving (CVPR 2024 · similarity 0.85)
- Enhancing End-to-End Autonomous Driving with Latent World Model (ICLR 2025 · similarity 0.85)
- Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability (NeurIPS 2024 · similarity 0.85)
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.
