PhyPlan：基于物理先验技能网络的机器人操作器泛化与快速物理任务规划
PhyPlan: Generalizable and Rapid Physical Task Planning with Physics Informed Skill Networks for Robot Manipulators
AI总结：
本文提出PhyPlan框架，结合物理先验神经网络与改进的蒙特卡洛树搜索，使机器人能快速、高效地推理并执行动态物理任务，在降低遗憾值和提升数据效率上优于现有方法。
摘要：
给定将球状物体定位到直接触及范围之外的目标区域的任务，人类通常可以通过投掷、滑动或让物体在墙上反弹来达成目标。然而，让机器人具备类似的推理能力并非易事。现有的物理推理方法需要大量数据，并且难以应对现实世界中固有的复杂性和不确定性。本文提出了PhyPlan，一个新颖的物理先验规划框架，它将物理先验神经网络（PINNs）与改进的蒙特卡洛树搜索（MCTS）相结合，使具身智能体能够执行动态物理任务。PhyPlan利用PINNs以快速且准确的方式模拟和预测动作的结果，并使用MCTS进行规划。它动态地决定是参考基于PINN的模拟器（粗略但快速）还是直接与实际环境交互（精细但缓慢）来确定最优策略。面对未见过的任务，PhyPlan能够推断动作序列并学习潜在参数，从而形成一种可泛化的方法，能够快速学习执行新颖的物理任务。在模拟3D环境中对机器人进行的评估表明，我们的方法能够解决涉及动态技能组合的3D物理推理任务。定量地看，PhyPlan在以下几个方面表现优异：(i) 与现有最先进方法相比，在学习新任务时实现了更低的遗憾值；(ii) 它加速了技能学习并提升了物理推理的速度；(iii) 与物理非先验方法相比，它展现出更高的数据效率。
英文摘要：
Given the task of positioning a ball-like object to a goal region beyond direct reach, humans can often throw, slide, or rebound objects against the wall to attain the goal. However, enabling robots to reason similarly is non-trivial. Existing methods for physical reasoning are data-hungry and struggle with complexity and uncertainty inherent in the real world. This paper presents PhyPlan, a novel physics-informed planning framework that combines physics-informed neural networks (PINNs) with modified Monte Carlo Tree Search (MCTS) to enable embodied agents to perform dynamic physical tasks. PhyPlan leverages PINNs to simulate and predict outcomes of actions in a fast and accurate manner and uses MCTS for planning. It dynamically determines whether to consult a PINN-based simulator (coarse but fast) or engage directly with the actual environment (fine but slow) to determine optimal policy. Given an unseen task, PhyPlan can infer the sequence of actions and learn the latent parameters, resulting in a generalizable approach that can rapidly learn to perform novel physical tasks. Evaluation with robots in simulated 3D environments demonstrates the ability of our approach to solve 3D-physical reasoning tasks involving the composition of dynamic skills. Quantitatively, PhyPlan excels in several aspects: (i) it achieves lower regret when learning novel tasks compared to the state-of-the-art, (ii) it expedites skill learning and enhances the speed of physical reasoning, (iii) it demonstrates higher data efficiency compared to a physics un-informed approach.
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。
