DynaRetarget: 基于采样的轨迹优化的动态可行重定向
DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization
AI总结：
提出DynaRetarget框架，通过采样轨迹优化将人体运动重定向为人形机器人控制策略，实现长时域动态可行运动，在数百个演示中取得更高成功率。
摘要：
在本文中，我们介绍了DynaRetarget，一个将人体运动重定向到人形机器人控制策略的完整流程。其核心组件是一种新颖的基于采样的轨迹优化（SBTO）框架，该框架将不完美的运动学轨迹优化为动态可行的运动。SBTO逐步推进优化范围，从而能够对长时域任务的整个轨迹进行优化。我们通过成功重定向数百个人形物体演示并实现比现有技术更高的成功率来验证DynaRetarget。该框架还使用相同的跟踪目标，在不同物体属性（如质量、尺寸和几何形状）下泛化。这种鲁棒地重定向多样化演示的能力为生成大规模人形机器人操作轨迹合成数据集打开了大门，解决了真实世界数据收集的主要瓶颈。
英文摘要：
In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective. This ability to robustly retarget diverse demonstrations opens the door to generating large-scale synthetic datasets of humanoid loco-manipulation trajectories, addressing a major bottleneck in real-world data collection.
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。
