The AI Driving Olympics at NeurIPS 2018
The AI Driving Olympics at NeurIPS 2018
复制标题
NeurIPS 2018 的人工智能驾驶奥运会
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
L. Paull
中科院分区：
文献类型：
--
作者：
J. Zilly;J. Tani;Breandan Considine;Bhairav Mehta;Andrea F. Daniele;Manfred Diaz;Gianmarco Bernasconi;Claudio Ruch;J. Hakenberg;Florian Golemo;A. K. Bowser;Matthew R. Walter;R. Hristov;S. Mallya;Emilio Frazzoli;A. Censi;L. Paull
尽管最近取得了突破性进展，但深度学习和强化学习在控制实体机器人代理方面优于传统方法的能力在很大程度上仍未得到证实。为了帮助弥合这一差距，我们创建了"AI驾驶奥运会"（AI-DO），这是一项旨在评估移动的机器人技术中机器学习和人工智能的最新技术水平的竞赛。基于简单且指定的自动驾驶和导航环境“Duckietown”，AI-DO包括一系列日益复杂的任务-从简单的车道跟踪到车队管理。对于每项任务，我们都为竞争对手提供工具，以模拟器、日志、代码模板、基线实现和低成本访问机器人硬件的形式使用。我们在标准化的硬件环境中在线评估提交的模拟，最后在比赛中进行评估。第一个AI-DO，AI-DO 1，发生在2018年12月的神经信息处理系统（NeurIPS）会议上。AI-DO 1的结果强调了需要更好的基准，这是机器人技术所缺乏的，以及改进的机制来弥合模拟和现实之间的差距。
Despite recent breakthroughs, the ability of deep learning and reinforcement learning to outperform traditional approaches to control physically embodied robotic agents remains largely unproven. To help bridge this gap, we created the 'AI Driving Olympics' (AI-DO), a competition with the objective of evaluating the state of the art in machine learning and artificial intelligence for mobile robotics. Based on the simple and well specified autonomous driving and navigation environment called 'Duckietown', AI-DO includes a series of tasks of increasing complexity -- from simple lane-following to fleet management. For each task, we provide tools for competitors to use in the form of simulators, logs, code templates, baseline implementations and low-cost access to robotic hardware. We evaluate submissions in simulation online, on standardized hardware environments, and finally at the competition event. The first AI-DO, AI-DO 1, occurred at the Neural Information Processing Systems (NeurIPS) conference in December 2018. The results of AI-DO 1 highlight the need for better benchmarks, which are lacking in robotics, as well as improved mechanisms to bridge the gap between simulation and reality.