PyRoki是可跨平台的机器人运动优化工具，支持多种任务目标。
PyRoki: A Modular Toolkit for Robot Kinematic Optimization
- 模块化设计，灵活定义运动变量与代价函数
- 在优化速度和误差上比cuRobo快1.4-1.7倍，收敛更优
- 适合需要多目标优化的机器人研发人员
机器人运动可服务于多种目标：依据任务不同，需优化姿态误差、速度、避障或与人类示范的相似性。为此，我们提出 PyRoki——一个模块化、可扩展且跨平台的运动学优化工具包。PyRoki 将运动变量与代价函数的定义接口与高效的非线性最小二乘优化器结合，支持在 CPU、GPU、TPU 上原生运行。本文展示了 (i) PyRoki 的设计与实现，(ii) 运动重定向与规划案例，凸显其模块化优势，(iii) 优化基准测试结果：相比现有 GPU 加速逆运动学库 cuRobo，PyRoki 在相同条件下可实现 1.4–1.7 倍加速，且收敛至更低误差。
原文摘要 · Abstract (English)
Robot motion can have many goals. Depending on the task, we might optimize for pose error, speed, collision, or similarity to a human demonstration. Motivated by this, we present PyRoki: a modular, extensible, and cross-platform toolkit for solving kinematic optimization problems. PyRoki couples an interface for specifying kinematic variables and costs with an efficient nonlinear least squares optimizer. Unlike existing tools, it is also cross-platform: optimization runs natively on CPU, GPU, and TPU. In this paper, we present (i) the design and implementation of PyRoki, (ii) motion retargeting and planning case studies that highlight the advantages of PyRoki's modularity, and (iii) optimization benchmarking, where PyRoki can be 1.4-1.7x faster and converges to lower errors than cuRobo, an existing GPU-accelerated inverse kinematics library.
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。