Zhicheng He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zhicheng He has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Xiaokun Leng
Department of Computer Science, Harbin Institute of Technology, Harbin, China
5 shared publications - Yao Su
State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China
4 shared publications - Songhao Piao
Harbin Institute of Technology
3 shared publications - Hangxin Liu
State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China
2 shared publications - Jiayang Wu
State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China
2 shared publications - Jingwen Zhang
State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 33 (3) , 2-14
Dynamic Whole-Body Dancing With Humanoid Robots: A Model-Based Control Approach
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 33 (3) , 2-14
Dynamic Whole-Body Dancing With Humanoid Robots: A Model-Based Control Approach
- Open Access
Path and Motion Optimization for Efficient Multi-Location Inspection with Humanoid Robots
This paper proposes a novel framework for humanoid robots to execute inspection tasks with high efficiency and millimeter-level precision. The approach combines hierarchical planning, time-optimal standing position generation, and integrated \ac{mpc} to achieve high speed and precision. A hierarchical planning strategy, leveraging \ac{ik} and \ac{mip}, reduces computational complexity by decoupling the high-dimensional planning problem. A novel MIP formulation optimizes standing position selection and trajectory length, minimizing task completion time. Furthermore, an MPC system with simplified kinematics and single-step position correction ensures millimeter-level end-effector tracking accuracy. Validated through simulations and experiments on the Kuavo 4Pro humanoid platform, the framework demonstrates low time cost and a high success rate in multi-location tasks, enabling efficient and precise execution of complex industrial operations.
Open AccessPath and Motion Optimization for Efficient Multi-Location Inspection with Humanoid Robots
This paper proposes a novel framework for humanoid robots to execute inspection tasks with high efficiency and millimeter-level precision. The approach combines hierarchical planning, time-optimal standing position generation, and integrated \ac{mpc} to achieve high speed and precision. A hierarchical planning strategy, leveraging \ac{ik} and \ac{mip}, reduces computational complexity by decoupling the high-dimensional planning problem. A novel MIP formulation optimizes standing position selection and trajectory length, minimizing task completion time. Furthermore, an MPC system with simplified kinematics and single-step position correction ensures millimeter-level end-effector tracking accuracy. Validated through simulations and experiments on the Kuavo 4Pro humanoid platform, the framework demonstrates low time cost and a high success rate in multi-location tasks, enabling efficient and precise execution of complex industrial operations.
- 3 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (7) , 6672-6679
CDM-MPC: An Integrated Dynamic Planning and Control Framework for Bipedal Robots Jumping
Performing acrobatic maneuvers like dynamic jumping in bipedal robots presents significant challenges in terms of actuation, motion planning, and control. Traditional approaches to these tasks often simplify dynamics to enhance computational efficiency, potentially overlooking critical factors such as the control of centroidal angular momentum (CAM) and the variability of centroidal composite rigid body inertia (CCRBI). This letter introduces a novel integrated dynamic planning and control framework, termed centroidal dynamics model-based model predictive control (CDM-MPC), designed for robust jumping control that fully considers centroidal momentum and non-constant CCRBI. The framework comprises an optimization-based kinodynamic motion planner and an MPC controller for real-time trajectory tracking and replanning. Additionally, a centroidal momentum-based inverse kinematics (IK) solver and a landing heuristic controller are developed to ensure stability during high-impact landings. The efficacy of the CDM-MPC framework is validated through extensive testing on the full-sized humanoid robot KUAVO in both simulations and experiments.
- 3 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (7) , 6672-6679
CDM-MPC: An Integrated Dynamic Planning and Control Framework for Bipedal Robots Jumping
Performing acrobatic maneuvers like dynamic jumping in bipedal robots presents significant challenges in terms of actuation, motion planning, and control. Traditional approaches to these tasks often simplify dynamics to enhance computational efficiency, potentially overlooking critical factors such as the control of centroidal angular momentum (CAM) and the variability of centroidal composite rigid body inertia (CCRBI). This letter introduces a novel integrated dynamic planning and control framework, termed centroidal dynamics model-based model predictive control (CDM-MPC), designed for robust jumping control that fully considers centroidal momentum and non-constant CCRBI. The framework comprises an optimization-based kinodynamic motion planner and an MPC controller for real-time trajectory tracking and replanning. Additionally, a centroidal momentum-based inverse kinematics (IK) solver and a landing heuristic controller are developed to ensure stability during high-impact landings. The efficacy of the CDM-MPC framework is validated through extensive testing on the full-sized humanoid robot KUAVO in both simulations and experiments.
- 14 May 2024
- Published by Springer Nature in Journal of Bionic Engineering
- Vol. 21 (4) , 1707-1719
A Unified Motion Generation Approach for Quadruped L-S Walk and Trot Gaits Based on Linear Model Predictive Control
- 14 May 2024
- Published by Springer Nature in Journal of Bionic Engineering
- Vol. 21 (4) , 1707-1719
A Unified Motion Generation Approach for Quadruped L-S Walk and Trot Gaits Based on Linear Model Predictive Control
- Open Access
Uneven Terrain Walking with Linear and Angular Momentum Allocation
Uneven terrain walking is hard to achieve for most child-size humanoid robots, as they are unable to accurately detect ground conditions. In order to reduce the demand for ground detection accuracy, a walking control framework based on centroidal momentum allocation is studied in this paper, enabling a child-size humanoid robot to walk on uneven terrain without using ground flatness information. The control framework consists of three controllers: momentum decreasing controller, posture controller, admittance controller. First, the momentum decreasing controller is used to quickly stabilize the robot after disturbance. Then, the posture controller restores the robot posture to adapt to the unknown terrain. Finally, the admittance controller aims to decrease contact impact and adapt the robot to the terrain. Note that the robot uses a mems-based inertial measurement unit (IMU) and joint position encoders to calculate centroidal momentum and use force-sensitive resistors (FSR) on the robot foot to perform admittance control. None of these is a high-cost component. Experiments are conducted to test the proposed framework, including standing posture balancing, structured non-flat ground walking, and soft uneven terrain walking, with a speed of 2.8 s per step, showing the effectiveness of the momentum allocation method.
Open AccessUneven Terrain Walking with Linear and Angular Momentum Allocation
Uneven terrain walking is hard to achieve for most child-size humanoid robots, as they are unable to accurately detect ground conditions. In order to reduce the demand for ground detection accuracy, a walking control framework based on centroidal momentum allocation is studied in this paper, enabling a child-size humanoid robot to walk on uneven terrain without using ground flatness information. The control framework consists of three controllers: momentum decreasing controller, posture controller, admittance controller. First, the momentum decreasing controller is used to quickly stabilize the robot after disturbance. Then, the posture controller restores the robot posture to adapt to the unknown terrain. Finally, the admittance controller aims to decrease contact impact and adapt the robot to the terrain. Note that the robot uses a mems-based inertial measurement unit (IMU) and joint position encoders to calculate centroidal momentum and use force-sensitive resistors (FSR) on the robot foot to perform admittance control. None of these is a high-cost component. Experiments are conducted to test the proposed framework, including standing posture balancing, structured non-flat ground walking, and soft uneven terrain walking, with a speed of 2.8 s per step, showing the effectiveness of the momentum allocation method.
- Open Access
Learning 3D Bipedal Walking with Planned Footsteps and Fourier Series Periodic Gait Planning
Reinforcement learning provides a general framework for achieving autonomy and diversity in traditional robot motion control. Robots must walk dynamically to adapt to different ground environments in complex environments. To achieve walking ability similar to that of humans, robots must be able to perceive, understand and interact with the surrounding environment. In 3D environments, walking like humans on rugged terrain is a challenging task because it requires complex world model generation, motion planning and control algorithms and their integration. So, the learning of high-dimensional complex motions is still a hot topic in research. This paper proposes a deep reinforcement learning-based footstep tracking method, which tracks the robot’s footstep position by adding periodic and symmetrical information of bipedal walking to the reward function. The robot can achieve robot obstacle avoidance and omnidirectional walking, turning, standing and climbing stairs in complex environments. Experimental results show that reinforcement learning can be combined with real-time robot footstep planning, avoiding the learning of path-planning information in the model training process, so as to avoid the model learning unnecessary knowledge and thereby accelerate the training process.
Open AccessLearning 3D Bipedal Walking with Planned Footsteps and Fourier Series Periodic Gait Planning
Reinforcement learning provides a general framework for achieving autonomy and diversity in traditional robot motion control. Robots must walk dynamically to adapt to different ground environments in complex environments. To achieve walking ability similar to that of humans, robots must be able to perceive, understand and interact with the surrounding environment. In 3D environments, walking like humans on rugged terrain is a challenging task because it requires complex world model generation, motion planning and control algorithms and their integration. So, the learning of high-dimensional complex motions is still a hot topic in research. This paper proposes a deep reinforcement learning-based footstep tracking method, which tracks the robot’s footstep position by adding periodic and symmetrical information of bipedal walking to the reward function. The robot can achieve robot obstacle avoidance and omnidirectional walking, turning, standing and climbing stairs in complex environments. Experimental results show that reinforcement learning can be combined with real-time robot footstep planning, avoiding the learning of path-planning information in the model training process, so as to avoid the model learning unnecessary knowledge and thereby accelerate the training process.