构建高速自动驾驶竞速多任务基准，推动跨域感知研究。
EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing
- 基于激光雷达的统一多任务评估框架，涵盖真实与仿真数据。
- 真实赛道预训练使检测指标提升至NDS 0.726，优于仅用模拟数据。
- 适用于高动态场景下的感知模型泛化能力研究，适合自动驾驶研发者。
高速自动驾驶竞速面临巨大感知挑战，包括高相对速度和与常规城市驾驶数据集之间的显著领域差异。现有基准无法充分捕捉此类高动态条件。本文提出EagleVision，一个基于激光雷达的统一多任务基准，用于高速竞速中的3D检测与轨迹预测。该基准包含新标注的Indy Autonomous Challenge数据集（14,893帧）和A2RL Real竞赛数据集（1,163帧），以及12,000帧模拟生成的标注数据，并采用统一评估协议。通过数据驱动的迁移框架，量化了城市、模拟器与真实竞速领域的跨域泛化能力。城市数据预训练使检测性能优于从零训练（NDS 0.72 vs. 0.69），而真实竞速数据作为中间预训练可实现最佳迁移效果（NDS 0.726），优于仅使用模拟数据的适应。在轨迹预测方面，基于Indy训练的模型在A2RL测试序列上表现优于域内训练（FDE 0.947 vs. 1.250），凸显运动分布覆盖对跨域预测的重要性。EagleVision为极端高速动态下的感知泛化研究提供了系统平台。数据集与基准已公开，地址：https://avlab.io/EagleVision。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。