arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2509.19545cs.RO

RoMoCo:用于双足和仿人机器人降阶模型运动控制的机器人运动控制工具箱

RoMoCo: Robotic Motion Control Toolbox for Reduced-Order Model-Based Locomotion on Bipedal and Humanoid Robots

Department of Mechanical and Civil Engineering, California Institute of Technology(机械与土木工程系,加州理工学院)

Min Dai, Aaron D. Ames

AI总结:

RoMoCo是一个开源C++工具箱,通过统一的API集成降阶模型规划器与全身控制器,支持双足和仿人机器人快速原型与可复现基准测试,并在多种机器人上经仿真和硬件验证。

摘要:

我们提出了RoMoCo,一个开源的C++工具箱,用于合成和评估双足及仿人机器人的降阶模型规划器和全身控制器。RoMoCo的模块化架构将最先进的规划器和全身运动控制器统一在一致的API下,支持快速原型设计和可复现的基准测试。通过利用降阶模型进行平台无关的步态生成,RoMoCo能够在不同机器人上实现灵活的控制器设计。我们通过在Cassie、Unitree H1和G1机器人上的广泛仿真展示了其通用性和性能,并通过在Cassie和G1人形机器人上的硬件实验验证了其实际有效性。

英文摘要:

We present RoMoCo, an open-source C++ toolbox for the synthesis and evaluation of reduced-order model-based planners and whole-body controllers for bipedal and humanoid robots. RoMoCo's modular architecture unifies state-of-the-art planners and whole-body locomotion controllers under a consistent API, enabling rapid prototyping and reproducible benchmarking. By leveraging reduced-order models for platform-agnostic gait generation, RoMoCo enables flexible controller design across diverse robots. We demonstrate its versatility and performance through extensive simulations on the Cassie, Unitree H1, and G1 robots, and validate its real-world efficacy with hardware experiments on the Cassie and G1 humanoids.

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。

↑