This paper provides a comprehensive review of the current status, advancements, and future prospects of humanoid robots, highlighting their significance in driving the evolution of next-generation industries. By analyzing various research endeavors and key technologies, encompassing ontology structure, control and decision-making, and perception and interaction, a holistic overview of the current state of humanoid robot research is presented. Furthermore, emerging challenges in the field are identified, emphasizing the necessity for a deeper understanding of biological motion mechanisms, improved structural design, enhanced material applications, advanced drive and control methods, and efficient energy utilization. The integration of bionics, brain-inspired intelligence, mechanics, and control is underscored as a promising direction for the development of advanced humanoid robotic systems. This paper serves as an invaluable resource, offering insightful guidance to researchers in the field, while contributing to the ongoing evolution and potential of humanoid robots across diverse domains.

Enabling robots with uncertain dynamics to perform human-like adaptive operations in unknown environments remains a significant challenge in robotics research. Drawing inspiration from the dynamic modification of human arm muscles, we propose an innovative adaptive optimal control framework to address this issue. The framework integrates a variable optimal impedance adaptation (VOIA) method and an adaptive bias broad fuzzy neural network (ABBFNN) controller, facilitating adaptive manipulation behaviors in robot-environment interaction tasks. It can adaptively learn the impedance gain of unknown environment in the presence of uncertain robot dynamic model based on different task properties, simultaneously keeping the tracking error and interaction force optimized and minimized. The ABBFNN controller combines adaptive node increments to approximate uncertain dynamic model and introduces additional global bias and adaptive gain adjustment to improve the approximation accuracy and the rate of convergence significantly. VOIA seamlessly integrates a finely tuned proportional-integral-derivative (PID) variable target stiffness and an impact compensator, ensuring accurate responses to varying environmental conditions and improved disturbance rejection. Moreover, a momentum-based force observer is utilized within the framework for interaction force estimation, eliminating the need for force sensors and simplifying the system. Simulations and experiments validate the effectiveness and practicality of the proposed optimal interaction control framework, demonstrating its potential to propel robots toward interactions with unknown environments.

physical human–robot collaboration (pHRC) requires strict safety and efficiency guarantees, imposing heightened demands on accurate human intent estimation and adaptive control in a stable manner. To address these challenges, we propose a novel two-loop adaptive passive control framework guided by multistep human intent estimation to reduce human–robot disagreement and improve robot assistance level, facilitating safety-aware efficient pHRC. In the framework, outer loop’s intent estimation guides the inner loop’s adaptive passive controller, ensuring real-time robot behavior adjustment based on multistep intention. Specifically, the outer loop incorporates a transformer-based human intent estimator (THIE) that integrates the Transformer with a conditional variational autoencoder (CVAE) for multistep predictions, accurately estimating motion and force to guide the robot. The inner loop incorporates a goal-oriented reinforcement learning (GoRL)-based adaptive impedance control, which constructs multistep rewards based on prediction and probability from THIE to adjust impedance parameters, thereby balancing disagreement and assistance, and promoting locally optimal robot behaviors. Furthermore, an energy tank-based passive model predictive control (ET-PMPC) is employed to limit robot stored energy, avoiding the impact of variable impedance on safety. Experiments validate that our framework outperforms state-of-the-art (SOTA) methods, significantly improving intent estimation accuracy, robot assistance level, and safety, highlighting its potential to advance pHRC.

Image acquisition stands as a prerequisite for scrutinizing surfaces inspection in industrial high-end manufacturing. Current imaging systems often exhibit inflexibility, being confined to specific objects and encountering difficulties with diverse industrial structures lacking standardized computer-aided design (CAD) models or in instances of deformation. Inspired by the multidimensional observation of humans, our study introduces a universal image acquisition paradigm tailored for robotics, seamlessly integrating multi-objective optimization trajectory planning and control scheme to harness measured point clouds for versatile, efficient, and highly accurate image acquisition across diverse structures and scenarios. Specifically, we introduce an energy-based adaptive trajectory optimization (EBATO) method that combines deformation and deviation with dual-threshold optimization and adaptive weight adjustment to improve the smoothness and accuracy of imaging trajectory and posture. Additionally, a multi-optimization control scheme based on a meta-heuristic beetle antennal olfactory recurrent neural network (BAORNN) is proposed to track the imaging trajectory while addressing posture, obstacle avoidance, and physical constraints in industrial scenarios. Simulations, real-world experiments, and comparisons demonstrate the effectiveness and practicality of the proposed paradigm.

Multimanipulators exhibit excellence across various domains through collaboration, yet optimizing motion performance to fulfill task-specific requirements while tackling unknown kinematic models remains formidable challenges. This paper pioneers the integration of game theory into collaborative control for multi-manipulators with unknown kinematics, establishing a robust optimal framework through efficient distributed networks and strategic competition to achieve Nash equilibrium. An optimal collaboration scheme integrates hybrid multi-objective optimization and orthogonal projection repetitive motion generation (OPRMG) scheme to mitigate excessive and abrupt changes in joint velocity, enhance manipulability, and eliminate joint drift while decoupling errors between joint and Cartesian spaces. Furthermore, an adaptive power-exponentialtype neural network (APETNN) robust controller is proposed to solve the scheme, integrating learning and control components to enable manipulators to respond promptly with an optimal strategy even with incomplete or implicit kinematics. The efficacy, practicality, and superiority of the proposed framework for collaborative control of multimanipulators are demonstrated through theoretical analyses, simulations and experiments.

Inspired by the adaptive flexible motion coordination of biological systems, this study presents a bioinspired control strategy that enables robotic manipulators to achieve precise and compliant motion–force coordination for embodied intelligence and dexterous interaction in physically constrained environments. To this end, a learning-based motion–force hybrid control (LMFC) framework is proposed, which unifies learning and kinematic-level control to regulate both motion and interaction forces under incomplete or implicit kinematic information, thereby enhancing robustness and precision. The LMFC formulation recasts motion–force coordination as a time-varying quadratic programming (TVQP) problem, seamlessly incorporating multiple practical constraints—including joint limits, end-effector orientation maintenance, and obstacle avoidance—at the acceleration level, while determining control decisions at the velocity level. An RNN-based controller is further designed to integrate adaptive learning and control, enabling online estimation of uncertain kinematic parameters and mitigating joint drift. Simulation and experimental results demonstrate the effectiveness and practicality of the proposed framework, highlighting its potential for adaptive and compliant robotic control in constraint-rich environments.