受果蝇启发的循环控制器实现的人形机器人 locomotion
Humanoid Locomotion with a Fly-Inspired Recurrent Controller
- The Hong Kong University of Science and Technology(香港科技大学)
- Zenbot
- Nanyang Technological University(南洋理工大学)
- The Hong Kong Polytechnic University(香港理工大学)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
本研究提出一种受果蝇启发的循环控制器,通过3,609个神经状态与Unitree G1机器人耦合,在多种地形和速度下完成61/63项测试,揭示直接身体输入和携带运动状态对运动支持的关键作用。
AI中文摘要:
我们研究了受果蝇启发的循环控制器在人形机器人 locomotion 中的应用,并识别了支持其部署行为的通路。该控制器通过身体观测投影、运动神经元标记的读出和关节伺服,将3,609个连续的神经状态与模拟的 Unitree G1 机器人耦合。我们公式化了这一神经-身体反馈系统,并在七个地形实例、三种速度和三种初始偏航偏移下评估了一个固定检查点。在生存和前进进度标准下,它完成了61/63个条件;一个特权参考完成了62/63个条件。在标称偏航下,在每次策略调用前重置循环运动状态将成功率从19/21变为0/21。相反,在252个记录状态下,深度和上游状态替换不改变动作,在整个完整的 rollout 中测量到的下行输出为零。记录轨迹和状态匹配图像将这些发现与持续运动、横向漂移和终止事件联系起来。该研究描述了一个具身循环控制系统,其测试的 locomotion 由直接的身体和命令输入以及携带的运动状态支持,为后续电路结构和控制资源的比较提供了具体基础。
英文摘要:
We investigate humanoid locomotion with a fly-inspired recurrent controller and identify the pathways supporting its deployed behavior. The controller couples 3,609 continuous neural states to a simulated Unitree G1 through body-observation projections, a motor-neuron-labelled readout, and joint servos. We formulate this neural-body feedback system and evaluate a fixed checkpoint across seven terrain instances, three speeds, and three initial yaw offsets. It completes 61/63 conditions under a survival-and-forward-progress criterion; a privileged reference completes 62/63. At nominal yaw, resetting the recurrent motor state before every policy call changes success from 19/21 to 0/21. Conversely, depth and upstream-state substitutions at 252 recorded states leave actions unchanged, with zero measured descending output throughout the intact rollouts. Recorded trajectories and state-matched images connect these findings to sustained movement, lateral drift, and termination events. The study characterizes an embodied recurrent control system whose tested locomotion is supported by direct body-and-command input and carried motor state, providing a concrete basis for subsequent comparisons of circuit structure and control resources.