让机器人在复杂约束下快速生成流畅动作，精度与速度双提升
Differentiable Motion Manifold Primitives for Reactive Motion Generation under Kinodynamic Constraints
- 用可微神经网络学习低维动作流形，支持连续时间轨迹生成
- 7自由度机械臂动态投掷任务中，规划速度更快、成功率更高
- 适合需要实时响应的高维系统运动规划，如机器人控制
高维系统在动力学约束下实现实时运动生成是关键但极具挑战的问题。本文提出一种两阶段方法：离线学习任务相关的、满足约束的低维轨迹流形，再在线快速搜索该流形。在离散时间运动流形基（MMP）基础上，提出可微运动流形基（DMMP），一种新型神经网络架构，能够编码并生成连续时间、可微轨迹，其训练数据来自离线轨迹优化，且通过策略保证约束满足——这是现有方法所缺失的。在7自由度机械臂动态投掷任务上的实验表明，相比先前方法，DMMP在规划速度、任务成功率和约束满足方面均有显著提升。
原文摘要 · Abstract (English)
Real-time motion generation -- which is essential for achieving reactive and adaptive behavior -- under kinodynamic constraints for high-dimensional systems is a crucial yet challenging problem. We address this with a two-step approach: offline learning of a lower-dimensional trajectory manifold of task-relevant, constraint-satisfying trajectories, followed by rapid online search within this manifold. Extending the discrete-time Motion Manifold Primitives (MMP) framework, we propose Differentiable Motion Manifold Primitives (DMMP), a novel neural network architecture that encodes and generates continuous-time, differentiable trajectories, trained using data collected offline through trajectory optimizations, with a strategy that ensures constraint satisfaction -- absent in existing methods. Experiments on dynamic throwing with a 7-DoF robot arm demonstrate that DMMP outperforms prior methods in planning speed, task success, and constraint satisfaction.
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。