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 2210.00327cs.ROcs.LGcs.NE
收藏

面向带移动机器人的能量受限覆盖问题的深度循环Q学习

Deep Recurrent Q-learning for Energy-constrained Coverage with a Mobile Robot

University of North Florida(北佛罗里达大学);Kent State University(肯特州立大学)

Aaron Zellner, Ayan Dutta, Iliya Kulbaka, Gokarna Sharma

AI总结:

本文研究能量受限移动机器人的环境覆盖问题,提出一种结合循环神经网络记忆的深度Q学习框架,在含多充电站和障碍物的16x16网格环境中最大化覆盖范围并最小化预算违规,表现优于现有技术。

摘要:

本文研究了在存在多个充电站的情况下,使用能量受限机器人进行环境覆盖的问题。由于机器人的车载电源有限,它可能没有足够的能量在一次充电下覆盖环境中的所有点。相反,它需要在一个或多个充电站停留以间歇性地为电池充电。机器人不能违反能量约束,即不能在可用能量为负的情况下访问某个位置。为了解决这个问题,我们提出了一个深度Q学习框架,该框架产生一个策略以最大化覆盖范围并最小化预算违规。我们提出的框架还利用循环神经网络(RNN)的记忆来更好地适应这个多目标优化问题。我们在一个16 x 16的网格环境中测试了所提出的框架,该环境具有充电站和各种障碍物配置。结果表明,我们提出的方法找到了可行的解决方案,并且优于一种可比较的现有技术。

英文摘要:

In this paper, we study the problem of coverage of an environment with an energy-constrained robot in the presence of multiple charging stations. As the robot's on-board power supply is limited, it might not have enough energy to cover all the points in the environment with a single charge. Instead, it will need to stop at one or more charging stations to recharge its battery intermittently. The robot cannot violate the energy constraint, i.e., visit a location with negative available energy. To solve this problem, we propose a deep Q-learning framework that produces a policy to maximize the coverage and minimize the budget violations. Our proposed framework also leverages the memory of a recurrent neural network (RNN) to better suit this multi-objective optimization problem. We have tested the presented framework within a 16 x 16 grid environment having charging stations and various obstacle configurations. Results show that our proposed method finds feasible solutions and outperforms a comparable existing technique.

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。

↑