arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.06759cs.ROcs.AIcs.LG
收藏

从经验中学习机器人导航:原理,方法和最新结果

Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results

UC Berkeley(加州大学伯克利分校)

Sergey Levine, Dhruv Shah

摘要:

导航是机器人学中研究最多的问题之一,通常被视为几何映射和规划问题。然而,现实世界的导航提出了一组复杂的物理挑战,挑战简单的几何抽象。机器学习提供了一种超越几何和传统规划的有希望的方法,允许导航系统根据实际的先前经验做出决策。这样的系统可以以超越几何学的方式推理可穿越性,解释其行为的物理结果并利用现实世界环境中的模式。随着更多数据的收集,它们还可以得到改进,从而可能提供强大的网络效应。在这篇文章中,我们提出了一个通用的机器人导航技能的经验学习工具包,统一了最近的几种方法,描述了基本的设计原则,总结了我们最近的几篇论文的实验结果,并讨论了开放的问题和未来的工作方向。

英文摘要:

Navigation is one of the most heavily studied problems in robotics, and is conventionally approached as a geometric mapping and planning problem. However, real-world navigation presents a complex set of physical challenges that defies simple geometric abstractions. Machine learning offers a promising way to go beyond geometry and conventional planning, allowing for navigational systems that make decisions based on actual prior experience. Such systems can reason about traversability in ways that go beyond geometry, accounting for the physical outcomes of their actions and exploiting patterns in real-world environments. They can also improve as more data is collected, potentially providing a powerful network effect. In this article, we present a general toolkit for experiential learning of robotic navigation skills that unifies several recent approaches, describe the underlying design principles, summarize experimental results from several of our recent papers, and discuss open problems and directions for future work.

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。

↑