Humanoid robots performing lifting and material-handling tasks must maintain balance despite unknown and varying payloads. However, payload uncertainty significantly affects whole-body dynamics and may destabilize conventional controllers. We propose an adaptive whole-body control architecture that integrates three components: (i) a centroidal model predictive controller (MPC) that generates dynamically feasible reference motions, (ii) an adaptive fuzzy balance controller that compensates for payload-induced model mismatch by generating corrective torques distributed across the supporting-leg joints, and (iii) a waypoint-based optimal posture planner built on a triple-integrator model that produces smooth sit-to-stand and stand-to-sit trajectories satisfying center-of-mass (CoM) stability constraints, joint limits, and whole-body feasibility requirements. Together, these components enable stable lowering, grasping, lifting, carrying, and placing behaviors under significant payload uncertainty. Extensive simulation and hardware experiments demonstrate that the proposed framework improves balance robustness and reduces tracking degradation during posture transitions and lifting tasks compared to non-adaptive baselines.
DFKI GmbH（德国人工智能研究中心）；University of Edinburgh（爱丁堡大学）；Alan Turing Institute（艾伦·图灵研究所）；LAAS-CNRS（法国国家科学研究中心系统分析与架构实验室）
Last decades of humanoid research has shown that humanoids developed for high dynamic performance require a stiff structure and optimal distribution of mass--inertial properties. Humanoid robots built with a purely tree type architecture tend to be bulky and usually suffer from velocity and force/torque limitations. This paper presents a novel series-parallel hybrid humanoid called RH5 which is 2 m tall and weighs only 62.5 kg capable of performing heavy-duty dynamic tasks with 5 kg payloads in each hand. The analysis and control of this humanoid is performed with whole-body trajectory optimiz…
In this paper, we propose a novel inverse Dynamic Reachability Map (iDRM) that allows a floating base system to find valid end-poses in complex and dynamically changing environments in real-time. End-pose planning for valid stance pose and collision-free configuration is an essential problem for humanoid applications, such as providing goal states for walking and motion planners. However, this is non-trivial in complex environments, where standing locations and reaching postures are restricted by obstacles. Our proposed iDRM customizes the robot-to-workspace occupation list and uses an online …
MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench
Technical University of Darmstadt（达姆施塔特工业大学）；German Research Center for AI (DFKI)（德国人工智能研究中心）；Centre for Cognitive Science（认知科学中心）；Hessian Center for Artificial Intelligence (Hessian.AI)（黑森州人工智能中心）
Fondazione Istituto Italiano di Tecnologia（意大利技术研究院基金会）；Università di Genova（热那亚大学）
Humanoid robots are machines built with an anthropomorphic shape. Despite decades of research into the subject, it is still challenging to tackle the robot locomotion problem from an algorithmic point of view. For example, these machines cannot achieve a constant forward body movement without exploiting contacts with the environment. The reactive forces resulting from the contacts are subject to strong limitations, complicating the design of control laws. As a consequence, the generation of humanoid motions requires to exploit fully the mathematical model of the robot in contact with the envir…
Posture control and balance are basic requirements for a humanoid robot performing motor tasks like walking and interacting with the environment. For this reason, posture control is one of the elements taken into account when evaluating the performance of humanoids. In this work, we describe and analyze a performance indicator based on the comparison between the body sway of a robot standing on a moving surface and the one of healthy subjects performing the same experiment. This approach is here oriented to the evaluation of human likeness. The measure is tested with three human-inspired human…
This work presents a system to benchmark humanoid posture control and balance performances under perturbed conditions. The specific benchmarking scenario consists, for example, of balancing upright stance while performing voluntary movements on moving surfaces. The system includes a motion platform used to provide the perturbation, an innovative body-tracking system suitable for robots, humans and exoskeletons, control software and a set of predefined perturbations, a humanoid robot used to test algorithms, and analysis software providing state of the art data analysis used to provide quantita…
Similarly to humans, humanoid robots require posture control and balance to walk and interact with the environment. In this work posture control in perturbed conditions is evaluated as a performance test for humanoid control. A specific performance indicator is proposed: the score is based on the comparison between the body sway of the tested humanoid standing on a moving surface and the sway produced by healthy subjects performing the same experiment. This approach is here oriented to the evaluation of a human-likeness. The measure is tested using a humanoid robot in order to demonstrate a ty…
PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation
Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Jiaotong University（上海交通大学）；Zhejiang University（浙江大学）；Tongji University（同济大学）；The Chinese University of Hong Kong（香港中文大学）；Humanoid Robot (Shanghai) Co., Ltd.（人形机器人（上海）有限公司）；Beihang University（北京航空航天大学）
Bio-inspired sensorimotor control systems may be appealing to roboticists who try to solve problems of multiDOF humanoids and human-robot interactions. This paper presents a simple posture control concept from neuroscience, called disturbance estimation and compensation, DEC concept [1]. It provides human-like mechanical compliance due to low loop gain, tolerance of time delays, and automatic adjustment to changes in external disturbance scenarios. Its outstanding feature is that it uses feedback of multisensory disturbance estimates rather than 'raw' sensory signals for disturbance compensati…
Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
Department of Electronic Engineering and Information Science (EEIS), University of Science and Technology of China（电子工程与信息科学系，中国科学技术大学）；LimX Dynamics（LimX动力学）；Hong Kong University of Science and Technology（香港科技大学）；School of Mechanics Engineering, Harbin Institute of Technology (HIT)（机械工程学院，哈尔滨工业大学）；Department of Computing, The Hong Kong Polytechnic University（计算学院，香港理工大学）；Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI)（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）
Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots
Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China（人形机器人研究院，精密机械与精密仪器系，中国科学技术大学）；School of Computer Science and Technology, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University（计算机科学与技术学院，电子与信息工程学院，西安交通大学）；School of Information Science and Engineering, Lanzhou University（信息科学与工程学院，兰州大学）
Istituto Italiano di Tecnologia（意大利理工学院）；The University of Manchester（曼彻斯特大学）
When a human and a humanoid robot collaborate physically, ergonomics is a key factor to consider. Assuming a given humanoid robot, several control architectures exist nowadays to address ergonomic physical human-robot collaboration. This paper takes one step further by considering robot hardware parameters as optimization variables in the problem of collaborative payload lifting. The variables that parametrize robot's kinematics and dynamics ensure their physical consistency, and the human model is considered in the optimization problem. By leveraging the proposed modelling framework, the ergo…
Neurological University Clinic, University of Freiburg（弗莱堡大学神经大学诊所）
This work presents a system identification procedure based on Convolutional Neural Networks (CNN) for human posture control using the DEC (Disturbance Estimation and Compensation) parametric model. The modular structure of the proposed control model inspired the design of a modular identification procedure, in the sense that the same neural network is used to identify the parameters of the modules controlling different degrees of freedom. In this way the presented examples of body sway induced by external stimuli provide several training samples at once.
Learning Humanoid Standing-up Control across Diverse Postures
Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；The University of Hong Kong（香港大学）；Zhejiang University（浙江大学）；The Chinese University of Hong Kong（香港中文大学）
NEXUS: Perceptive Whole-Body Control for Terrain-Adaptive Teleoperation
The Institute of Artificial Intelligence, China Telecom (TeleAI)（中国电信人工智能研究院（TeleAI））；Shanghai Jiao Tong University（上海交通大学）；The University of Hong Kong（香港大学）；Zhejiang University（浙江大学）
This study proposes a novel robotic hand that can achieve self-adaptive grasping and a large payload (over 20 kg) with a single actuator. Accordingly, two novel mechanisms, an actuation system with self-motion switching and a self-adaptive finger with a self-locking mechanism, are installed in a 1-degree-of-freedom robotic hand. The actuation system switches the output motion from translational to rotational according to the applied external load. The finger is bent by inserting a flexible shaft inside it. Its bending posture can conform to the shape of the object owing to the flexible shaft, …
Cognition to Control - Multi-Agent Learning for Human-Humanoid Collaborative Transport
Department of Electrical Engineering, the University of Texas at Arlington（电气工程系，德克萨斯大学阿灵顿分校）；Department of Mechanical Engineering, Carnegie Mellon University（机械工程系，卡内基梅隆大学）
TACT-ful: Multi-Channel Terrain Affordance and Compliance Training for Payload-Robust Perceptive Humanoid Locomotion
VinRobotics, Vietnam（越南VinRobotics）；Center for AI Research, VinUniversity, Vietnam（越南VinUniversity人工智能研究中心）；Intelligent Autonomous Systems, TU Darmstadt, Germany（德国达姆施塔特工业大学智能自主系统）
Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
Mondo Robotics；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；Artificial General Intelligence Institute, University of Science and Technology of China（中国科学技术大学通用人工智能研究院）
Learning Roller-Skating Motions of Humanoid Robots Based on Adversarial Motion Priors
Department of Automation, Tsinghua University（清华大学自动化系）；Beijing Key Laboratory of Embodied Intelligence Systems（北京具身智能系统重点实验室）；Institute for Embodied Intelligence and Robotics, Tsinghua University（清华大学具身智能与机器人研究所）
Pose estimation commonly refers to computer vision methods that recognize people's body postures in images or videos. With recent advancements in deep learning, we now have compelling models to tackle the problem in real-time. Since these models are usually designed for human images, one needs to adapt existing models to work on other creatures, including robots. This paper examines different state-of-the-art pose estimation models and proposes a lightweight model that can work in real-time on humanoid robots in the RoboCup Humanoid League environment. Additionally, we present a novel dataset …
Generating Humanoid Multi-Contact through Feasibility Visualization
Institute of Human and Machine Cognition (IHMC)（人类与机器认知研究所）；University of West Florida (UWF)（西佛罗里达大学）；Georgia Institute of Technology（佐治亚理工学院）；Figure AI, Inc.（Figure AI公司）
