EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917403052474368 |
|---|---|
| author | Yagudin, Zakhar Mebrahtu, Murad Jin, Ren Huang, Jiaqi Yue, Yujia Tsetserukou, Dzmitry Dias, Jorge Khonji, Majid |
| author_facet | Yagudin, Zakhar Mebrahtu, Murad Jin, Ren Huang, Jiaqi Yue, Yujia Tsetserukou, Dzmitry Dias, Jorge Khonji, Majid |
| contents | High-speed autonomous racing presents extreme perception challenges, including large relative velocities and substantial domain shifts from conventional urban-driving datasets. Existing benchmarks do not adequately capture these high-dynamic conditions. We introduce EagleVision, a unified LiDAR-based multi-task benchmark for 3D detection and trajectory prediction in high-speed racing, providing newly annotated 3D bounding boxes for the Indy Autonomous Challenge dataset (14,893 frames) and the A2RL Real competition dataset (1,163 frames), together with 12,000 simulator-generated annotated frames, all standardized under a common evaluation protocol. Using a dataset-centric transfer framework, we quantify cross-domain generalization across urban, simulator, and real racing domains. Urban pretraining improves detection over scratch training (NDS 0.72 vs. 0.69), while intermediate pretraining on real racing data achieves the best transfer to A2RL (NDS 0.726), outperforming simulator-only adaptation. For trajectory prediction, Indy-trained models surpass in-domain A2RL training on A2RL test sequences (FDE 0.947 vs. 1.250), highlighting the role of motion-distribution coverage in cross-domain forecasting. EagleVision enables systematic study of perception generalization under extreme high-speed dynamics. The dataset and benchmark are publicly available at https://avlab.io/EagleVision |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11400 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing Yagudin, Zakhar Mebrahtu, Murad Jin, Ren Huang, Jiaqi Yue, Yujia Tsetserukou, Dzmitry Dias, Jorge Khonji, Majid Robotics Computer Vision and Pattern Recognition High-speed autonomous racing presents extreme perception challenges, including large relative velocities and substantial domain shifts from conventional urban-driving datasets. Existing benchmarks do not adequately capture these high-dynamic conditions. We introduce EagleVision, a unified LiDAR-based multi-task benchmark for 3D detection and trajectory prediction in high-speed racing, providing newly annotated 3D bounding boxes for the Indy Autonomous Challenge dataset (14,893 frames) and the A2RL Real competition dataset (1,163 frames), together with 12,000 simulator-generated annotated frames, all standardized under a common evaluation protocol. Using a dataset-centric transfer framework, we quantify cross-domain generalization across urban, simulator, and real racing domains. Urban pretraining improves detection over scratch training (NDS 0.72 vs. 0.69), while intermediate pretraining on real racing data achieves the best transfer to A2RL (NDS 0.726), outperforming simulator-only adaptation. For trajectory prediction, Indy-trained models surpass in-domain A2RL training on A2RL test sequences (FDE 0.947 vs. 1.250), highlighting the role of motion-distribution coverage in cross-domain forecasting. EagleVision enables systematic study of perception generalization under extreme high-speed dynamics. The dataset and benchmark are publicly available at https://avlab.io/EagleVision |
| title | EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.11400 |