Robot motion planning has made vast advances over the past decades, but the challenge remains: robot mobile manipulators struggle to plan long-range whole-body motion in common household environments in real time, because of high-dimensional robot configuration space and complex environment geometry. To tackle the challenge, this paper proposes Neural Randomized Planner (NRP), which combines a global sampling-based motion planning (SBMP) algorithm and a local neural sampler. Intuitively, NRP uses the search structure inside the global planner to stitch together learned local sampling distributions to form a global sampling distribution adaptively. It benefits from both learning and planning. Locally, it tackles high dimensionality by learning to sample in promising regions from data, with a rich neural network representation. Globally, it composes the local sampling distributions through planning and exploits local geometric similarity to scale up to complex environments. Experiments both in simulation and on a real robot show \NRP yields superior performance compared to some of the best classical and learning-enhanced SBMP algorithms. Further, despite being trained in simulation, NRP demonstrates zero-shot transfer to a real robot operating in novel household environments, without any fine-tuning or manual adaptation.

翻译：机器人运动规划在过去几十年中取得了巨大进展，但挑战依然存在：由于高维机器人构型空间和复杂的环境几何结构，移动操作机器人难以在常见家庭环境中实时规划长距离全身运动。为应对这一挑战，本文提出神经随机规划器（NRP），该方法将全局基于采样的运动规划（SBMP）算法与局部神经采样器相结合。直观而言，NRP利用全局规划器内部的搜索结构，将学习到的局部采样分布自适应地拼接成全局采样分布。该方法兼具学习与规划优势：从局部看，它通过从数据中学习的丰富神经网络表示，在有利区域进行采样以应对高维性；从全局看，它通过规划组合局部采样分布，并利用局部几何相似性扩展到复杂环境。仿真与真实机器人实验表明，NRP相比部分最优的经典及学习增强型SBMP算法展现出更优性能。此外，尽管仅在仿真环境中训练，NRP在无需任何微调或手动适配的情况下，即可零样本迁移至运行于新型家庭环境的真实机器人。