用采样优化方法让机器人动作更自然，还能适配不同物体。
DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization
- 通过逐步扩展优化范围的采样轨迹优化，生成符合物理规律的动作。
- 成功重定向数百个复杂人形操作演示，成功率高于现有最优方法。
- 可通用处理不同质量、大小和形状的物体，适合构建大规模仿真数据集。
本文提出DynaRetarget，一套完整的将人类运动重定向至人形机器人控制策略的流程。其核心是新型采样式轨迹优化（SBTO）框架，能将不准确的运动学轨迹优化为符合动力学约束的动作。该框架通过逐步推进优化时域，实现对长时序任务的全局优化。我们通过数百次人形-物体交互演示验证了该方法，其成功率显著优于当前最优方案。此外，该框架在保持相同跟踪目标的前提下，可泛化至不同质量、尺寸和几何形状的物体。这一鲁棒性为生成大规模人形移动与操作的合成数据集提供了可能，有效缓解真实世界数据采集的瓶颈。
原文摘要 · Abstract (English)
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.
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。