arXiv 2410.166662024-10-22cs.ROcs.LG

QuasiNav：基于约束准度量强化学习的非对称成本感知导航规划

QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning

University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）；Amazon Inc.（亚马逊公司）；DEVCOM Army Research Lab（DEVCOM陆军研究实验室）；Stormfish Scientific Corporation（斯托姆菲什科学公司）

Jumman Hossain, Abu-Zaher Faridee, Derrik Asher, Jade Freeman, Theron Trout, Timothy Gregory, Nirmalya Roy

备注：: Under Review for ICRA 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

QuasiNav 提出一种基于准度量嵌入的约束强化学习框架，通过将导航建模为 CMDP 并自适应收紧安全约束，有效解决非对称行进成本下的自主导航问题，在仿真与真实环境中均显著提升了成功率、能效和安全性。

摘要：

非结构化室外环境中的自主导航本质上具有挑战性，因为存在非对称行进成本，例如上坡与下坡运动所消耗的能量不同。传统强化学习方法通常假设成本是对称的，这可能导致导航路径次优，并在现实场景中增加安全风险。本文提出 QuasiNav，一种新颖的强化学习框架，该框架整合准度量嵌入以显式建模非对称成本，并引导高效、安全的导航。QuasiNav 将导航问题形式化为约束马尔可夫决策过程（CMDP），并利用准度量嵌入来捕捉方向相关成本，从而更准确地表示地形。该方法与约束策略优化框架中的自适应约束收紧相结合，在学习过程中动态执行安全约束。我们在三个具有挑战性的导航场景中验证了 QuasiNav——起伏地形、非对称坡道穿越和方向相关地形穿越——证明了其在仿真和现实环境中的有效性。实验结果表明，QuasiNav 显著优于传统方法，实现了更高的成功率、更好的能源效率以及更好地遵守安全约束。

英文摘要：

Autonomous navigation in unstructured outdoor environments is inherently challenging due to the presence of asymmetric traversal costs, such as varying energy expenditures for uphill versus downhill movement. Traditional reinforcement learning methods often assume symmetric costs, which can lead to suboptimal navigation paths and increased safety risks in real-world scenarios. In this paper, we introduce QuasiNav, a novel reinforcement learning framework that integrates quasimetric embeddings to explicitly model asymmetric costs and guide efficient, safe navigation. QuasiNav formulates the navigation problem as a constrained Markov decision process (CMDP) and employs quasimetric embeddings to capture directionally dependent costs, allowing for a more accurate representation of the terrain. This approach is combined with adaptive constraint tightening within a constrained policy optimization framework to dynamically enforce safety constraints during learning. We validate QuasiNav across three challenging navigation scenarios-undulating terrains, asymmetric hill traversal, and directionally dependent terrain traversal-demonstrating its effectiveness in both simulated and real-world environments. Experimental results show that QuasiNav significantly outperforms conventional methods, achieving higher success rates, improved energy efficiency, and better adherence to safety constraints.

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。