arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05066cs.RO
收藏

无需地图的移动机器人探索:通过分布外深度强化学习

Mobile Robot Exploration Without Maps via Out-of-Distribution Deep Reinforcement Learning

Virginia Commonwealth University(弗吉尼亚联邦大学)

Shathushan Sivashangaran, Apoorva Khairnar, Azim Eskandarian

AI总结:

本文提出一种分布外深度强化学习方法,使移动机器人在无先验地图的动态环境中实现自主导航,通过加速模拟训练和内在探索行为,在紧凑的神经网络中实现高效的空间推理,减少仿真与现实物理差异,提升执行效率。

摘要:

自主移动机器人(AMR)在可能GPS失效的动态环境中无先验地图的导航是一个未解决的问题,具有提升人类能力的潜力。传统模块化方法计算效率低下,需要显式特征提取和工程,抑制了泛化和大规模部署。我们提出了一种分布外(OOD)深度强化学习(DRL)方法,包含无结构地形和动态障碍物避障功能。我们利用加速模拟训练在赛道中,通过转移概率参数化空间推理与内在探索行为,在紧凑且计算高效的神经网络中实现,通过奖励组件将模型转移到零样本,以缓解仿真与现实物理差异。我们的方法在无需单独高层规划器或实时制图的情况下实现实用性,并利用模块化方法的少量计算资源,使在不同嵌入式计算机负载的AMR上执行成为可能。

英文摘要:

Autonomous Mobile Robot (AMR) navigation in dynamic environments that may be GPS denied, without a-priori maps, is an unsolved problem with potential to improve humanity's capabilities. Conventional modular methods are computationally inefficient, and require explicit feature extraction and engineering that inhibit generalization and deployment at scale. We present an Out-of-Distribution (OOD) Deep Reinforcement Learning (DRL) approach that includes functionality in unstructured terrain and dynamic obstacle avoidance capabilities. We leverage accelerated simulation training in a racetrack with a transition probability to parameterize spatial reasoning with intrinsic exploratory behavior, in a compact, computationally efficient Artificial Neural Network (ANN), which we transfer zero-shot with a reward component to mitigate differences between simulation and real world physics. Our approach enables utility without a separate high-level planner or real-time cartography and utilizes a fraction of the computation resources of modular methods, enabling execution in a range of AMRs with different embedded computer payloads.

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。

↑