EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yagudin, Zakhar, Mebrahtu, Murad, Jin, Ren, Huang, Jiaqi, Yue, Yujia, Tsetserukou, Dzmitry, Dias, Jorge, Khonji, Majid
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