论文标题
学习赛事挑战2022：在自主赛车中基准测试安全学习和跨域概括
Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing
论文作者
论文摘要
我们根据新发行的学习竞赛（L2R）仿真框架介绍了我们自主赛车虚拟挑战的结果，该框架旨在鼓励自主驾驶方面的跨学科研究，并以现实的基准帮助提高最新技术。类似于赛车被用于测试尖端车辆的赛车，我们设想自主赛车成为自主剂的特别具有挑战性的证明基础，因为：（i）他们需要在复杂，快速变化的环境中做出次要的，安全关键的决定； （ii）感知和控制都必须适合分配变化，新颖的道路特征和看不见的障碍。因此，挑战的主要目标是通过两个阶段的过程评估强化学习剂对多模式感知的共同安全性，性能和概括能力。在挑战的第一阶段，我们评估了自治代理的尽可能快地驾驶的能力，同时遵守安全限制。在第二阶段，我们还要求代理通过安全探索适应看不见的赛马场。在本文中，我们用精致的指标和基线方法描述了新的L2R任务2.0基准。 We also provide an overview of deployment, evaluation, and rankings for the inaugural instance of the L2R Autonomous Racing Virtual Challenge (supported by Carnegie Mellon University, Arrival Ltd., AICrowd, Amazon Web Services, and Honda Research), which officially used the new L2R Task 2.0 benchmark and received over 20,100 views, 437 active participants, 46 teams, and 733 model提交 - 来自58个不同国家的88个独特机构。最后，我们从挑战中发布了排行榜的结果，并提供了跨多个传感器配置和模拟种族的跨域模型传输中两种顶级方法的描述。
We present the results of our autonomous racing virtual challenge, based on the newly-released Learn-to-Race (L2R) simulation framework, which seeks to encourage interdisciplinary research in autonomous driving and to help advance the state of the art on a realistic benchmark. Analogous to racing being used to test cutting-edge vehicles, we envision autonomous racing to serve as a particularly challenging proving ground for autonomous agents as: (i) they need to make sub-second, safety-critical decisions in a complex, fast-changing environment; and (ii) both perception and control must be robust to distribution shifts, novel road features, and unseen obstacles. Thus, the main goal of the challenge is to evaluate the joint safety, performance, and generalisation capabilities of reinforcement learning agents on multi-modal perception, through a two-stage process. In the first stage of the challenge, we evaluate an autonomous agent's ability to drive as fast as possible, while adhering to safety constraints. In the second stage, we additionally require the agent to adapt to an unseen racetrack through safe exploration. In this paper, we describe the new L2R Task 2.0 benchmark, with refined metrics and baseline approaches. We also provide an overview of deployment, evaluation, and rankings for the inaugural instance of the L2R Autonomous Racing Virtual Challenge (supported by Carnegie Mellon University, Arrival Ltd., AICrowd, Amazon Web Services, and Honda Research), which officially used the new L2R Task 2.0 benchmark and received over 20,100 views, 437 active participants, 46 teams, and 733 model submissions -- from 88+ unique institutions, in 58+ different countries. Finally, we release leaderboard results from the challenge and provide description of the two top-ranking approaches in cross-domain model transfer, across multiple sensor configurations and simulated races.
