arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.00636cs.ROcs.CVcs.LG
收藏

从一个轨道上的世界学习驾驶

Learning to drive from a world on rails

UT Austin(德克萨斯大学奥斯汀分校);Intel Labs(英特尔研究院)

Dian Chen, Vladlen Koltun, Philipp Krähenbühl

摘要:

我们通过基于模型的方法从预先记录的驾驶日志中学习交互式基于视觉的驾驶策略。世界的前向模型监督驾驶策略,预测任何潜在驾驶轨迹的结果。为了支持从预先记录的日志中学习,我们假设世界是在轨道上的,这意味着智能体及其行为都不会影响环境。这个假设极大地简化了学习问题,将动态分解为非反应性的世界模型和自我车辆的低维且紧凑的前向模型。我们的方法使用Bellman方程的表格动态编程评估来计算每个训练轨迹的动作值;这些动作值反过来监督最终的基于视觉的驾驶策略。尽管有世界在轨道上的假设,最终驾驶策略在动态和反应性世界中表现良好。在撰写本文时,我们的方法在CARLA排行榜上排名第一,获得了25%的驾驶分数,而使用的数据减少了40倍。在ProcGen基准测试中,我们的方法在导航任务上的样本效率也比最先进的无模型强化学习技术高出一个数量级。

英文摘要:

We learn an interactive vision-based driving policy from pre-recorded driving logs via a model-based approach. A forward model of the world supervises a driving policy that predicts the outcome of any potential driving trajectory. To support learning from pre-recorded logs, we assume that the world is on rails, meaning neither the agent nor its actions influence the environment. This assumption greatly simplifies the learning problem, factorizing the dynamics into a nonreactive world model and a low-dimensional and compact forward model of the ego-vehicle. Our approach computes action-values for each training trajectory using a tabular dynamic-programming evaluation of the Bellman equations; these action-values in turn supervise the final vision-based driving policy. Despite the world-on-rails assumption, the final driving policy acts well in a dynamic and reactive world. At the time of writing, our method ranks first on the CARLA leaderboard, attaining a 25% higher driving score while using 40 times less data. Our method is also an order of magnitude more sample-efficient than state-of-the-art model-free reinforcement learning techniques on navigational tasks in the ProcGen benchmark.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑