Existing control methods for humanoid robots,such as Model Predictive Control(MPC)and Reinforcement Learning(RL),generally lack the modeling and exploitation of rhythmic mechanisms.As a result,they struggle to balance...Existing control methods for humanoid robots,such as Model Predictive Control(MPC)and Reinforcement Learning(RL),generally lack the modeling and exploitation of rhythmic mechanisms.As a result,they struggle to balance stability,energy efficiency,and gait transition capability during typical rhythmic motions like walking and running.To address this limitation,we propose Walk2Run,a unified control framework inspired by biological rhythmicity.The method introduces control priors based on the frequency modulation observed in human walk-run transitions.Specifically,we extract rhythmic parameters from motion capture data to construct a Rhythm Generator grounded in Central Pattern Generator(CPG)principles,which guides the policy to produce speed-adaptive periodic motion.This rhythmic guidance is further integrated with a constrained reinforcement learning framework using barrier function optimization,enhancing training stability and output feasibility.Experimental results demonstrate that our method outperforms traditional approaches across multiple metrics,achieving more natural rhythmic motion with improved energy efficiency in medium-to high-speed scenarios,while also enhancing gait stability and adaptability to the robotic platform.展开更多
The dynamic motion capability of humanoid robots is a key indicator for evaluating their performance.Jumping,as a typical dynamic motion,is of great significance for enhancing the robot’s flexibility and terrain adap...The dynamic motion capability of humanoid robots is a key indicator for evaluating their performance.Jumping,as a typical dynamic motion,is of great significance for enhancing the robot’s flexibility and terrain adaptability in unstructured environments.However,achieving high-dynamic jumping control of humanoid robots has become a challenge due to the high degree of freedom and strongly coupled dynamic characteristics.The idea for this paper originated from the human response process to jumping commands,aiming to achieve online trajectory optimization and jumping motion control of humanoid robots.Firstly,we employ nonlinear optimization in combination with the Single Rigid Body Model(SRBM)to generate a robot’s Center of Mass(CoM)trajectory that complies with physical constraints and minimizes the angular momentum of the CoM.Then,a Model Predictive Controller(MPC)is designed to track and control the CoM trajectory,obtaining the required contact forces at the robot’s feet.Finally,a Whole-Body Controller(WBC)is used to generate full-body joint motion trajectories and driving torques,based on the prioritized sequence of tasks designed for the jumping process.The control framework proposed in this paper considers the dynamic characteristics of the robot’s jumping process,with a focus on improving the real-time performance of trajectory optimization and the robustness of controller.Simulation and experimental results demonstrate that our robot successfully executed high jump motions,long jump motions and continuous jump motions under complex working conditions.展开更多
基金supported in part by the National Natural Science Foundation of China(Grant Numbers:U2013602)the National Key R&D Program of China(Grant Number:2022YFB4601802)+1 种基金the Self-Planned Task of the State Key Laboratory of Robotics and System(Grant Number:2023FRFK01001)the National Independent Project of China(Grant Number:SKLR202301A12).
文摘Existing control methods for humanoid robots,such as Model Predictive Control(MPC)and Reinforcement Learning(RL),generally lack the modeling and exploitation of rhythmic mechanisms.As a result,they struggle to balance stability,energy efficiency,and gait transition capability during typical rhythmic motions like walking and running.To address this limitation,we propose Walk2Run,a unified control framework inspired by biological rhythmicity.The method introduces control priors based on the frequency modulation observed in human walk-run transitions.Specifically,we extract rhythmic parameters from motion capture data to construct a Rhythm Generator grounded in Central Pattern Generator(CPG)principles,which guides the policy to produce speed-adaptive periodic motion.This rhythmic guidance is further integrated with a constrained reinforcement learning framework using barrier function optimization,enhancing training stability and output feasibility.Experimental results demonstrate that our method outperforms traditional approaches across multiple metrics,achieving more natural rhythmic motion with improved energy efficiency in medium-to high-speed scenarios,while also enhancing gait stability and adaptability to the robotic platform.
基金supported in part by the National Key Research and Development Program of China(2020YFB13134)Major Project of National Natural Science Foundation of China(U2013602)+2 种基金The National Nature Science Foundation of China(52075115)HIT Major Campus Cultivation Project(2023FRFK01001)National independent project(SKLRS202301A12).
文摘The dynamic motion capability of humanoid robots is a key indicator for evaluating their performance.Jumping,as a typical dynamic motion,is of great significance for enhancing the robot’s flexibility and terrain adaptability in unstructured environments.However,achieving high-dynamic jumping control of humanoid robots has become a challenge due to the high degree of freedom and strongly coupled dynamic characteristics.The idea for this paper originated from the human response process to jumping commands,aiming to achieve online trajectory optimization and jumping motion control of humanoid robots.Firstly,we employ nonlinear optimization in combination with the Single Rigid Body Model(SRBM)to generate a robot’s Center of Mass(CoM)trajectory that complies with physical constraints and minimizes the angular momentum of the CoM.Then,a Model Predictive Controller(MPC)is designed to track and control the CoM trajectory,obtaining the required contact forces at the robot’s feet.Finally,a Whole-Body Controller(WBC)is used to generate full-body joint motion trajectories and driving torques,based on the prioritized sequence of tasks designed for the jumping process.The control framework proposed in this paper considers the dynamic characteristics of the robot’s jumping process,with a focus on improving the real-time performance of trajectory optimization and the robustness of controller.Simulation and experimental results demonstrate that our robot successfully executed high jump motions,long jump motions and continuous jump motions under complex working conditions.
