提出通用神经运动规划框架，解决机器人在复杂环境中的路径规划难题。
Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities
- 用神经网络替代传统规划模块，提升规划效率与多模态处理能力。
- 现有方法在未见场景中泛化能力差，难以应对分布外的障碍布局。
- 适合研究机器人自主导航与智能控制的学者参考。
当前先进的通用机械臂操作策略已使机器人可在非结构化人类环境中部署，但其在杂乱环境中表现不佳，主要因依赖辅助模块进行低层运动规划与控制。运动规划困难源于机器人构型空间高维度及工作空间障碍物的存在。神经运动规划器通过快速推理和有效处理运动规划的固有多模态性，提升了规划效率。然而，现有神经运动规划器往往难以泛化到未见的、分布外的规划场景。本文综述并分析了最先进的神经运动规划器，指出其优势与局限，并勾勒出构建能应对领域特定挑战的通用神经运动规划器的发展路径。相关论文列表详见 https://davoodsz.github.io/planning-manip-survey.github.io/。
原文摘要 · Abstract (English)
State-of-the-art generalist manipulation policies have enabled the deployment of robotic manipulators in unstructured human environments. However, these frameworks struggle in cluttered environments primarily because they utilize auxiliary modules for low-level motion planning and control. Motion planning remains challenging due to the high dimensionality of the robot's configuration space and the presence of workspace obstacles. Neural motion planners have enhanced motion planning efficiency by offering fast inference and effectively handling the inherent multi-modality of the motion planning problem. Despite such benefits, current neural motion planners often struggle to generalize to unseen, out-of-distribution planning settings. This paper reviews and analyzes the state-of-the-art neural motion planners, highlighting both their benefits and limitations. It also outlines a path toward establishing generalist neural motion planners capable of handling domain-specific challenges. For a list of the reviewed papers, please refer to https://davoodsz.github.io/planning-manip-survey.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。