The control of humanoid locomotion remains one of the most formidable challenges in robotics. Conventional model-based approaches not only rely extensively on manual design but also exhibit limited generalization across diverse tasks and environments. To overcome these limitations, a curriculum-enhanced reinforcement learning framework is proposed in this work for training robust locomotion. Given the strong temporal dependencies inherent in humanoid locomotion, Mamba-2 is employed as the backbone of the Actor-Critic network, enabling efficient temporal modeling of historical observations and content-based reasoning with linear spatiotemporal complexity. Furthermore, to eliminate the tendency of humanoid robots to favor low-speed motion in order to maintain gait stability and balance, which often leads to inaccurate velocity command tracking, a command-guided curriculum learning (CGCL) method is proposed to improve responsiveness to velocity commands. Experimental results demonstrate that the proposed Mamba-based framework achieves state-of-the-art (SOTA) performance, while CGCL significantly enhances the accuracy of velocity command tracking. Moreover, sim-to-real transfer experiments confirm both the robustness and the seamless deployability of the proposed framework on physical humanoid platforms.

Piano-playing tasks, which effectively demonstrate bimanual coordination capabilities in humanoid robots, are increasingly becoming a research focus. However, prior research has predominantly focused on Cartesian space trajectory planning without adequately addressing real-world obstacle avoidance constraints and manipulator acceleration limits. This paper proposes a hierarchical trajectory planning framework that systematically incorporates both obstacle avoidance and acceleration constraints. Firstly, discrete Cartesian path points are generated using a dynamic programming approach; secondly, joint space path points are derived considering obstacle avoidance and joint limit constraints through dynamic programming; thirdly, the joint space trajectory is interpolated using a Jacobian inverse-based method; finally, the trajectory is refined using Model Predictive Control (MPC). Experimental results demonstrate that the proposed method produces trajectories satisfying both obstacle avoidance and acceleration constraints, enabling fluent piano piece execution in real-world environments.

Grasping and manipulating various kinds of objects cooperatively is the core skill of a dual-arm robot when deployed as an autonomous agent in a human-centered environment. This requires fully exploiting the robot's versatility and dexterity. In this work, we propose a general framework for dual-arm manipulators that contains two correlative modules. The learning-based dexterity-reachability-aware perception module deals with vision-based bimanual grasping. It employs an end-to-end evaluation network and probabilistic modeling of the robot's reachability to deliver feasible and dexterity-optimum grasp pairs for unseen objects. The optimization-based versatility-oriented control module addresses the online cooperative manipulation control by using a hierarchical quadratic programming formulation. Self-collision avoidance and dual-arm manipulability ellipsoid tracking with high reliability and fidelity are simultaneously achieved based on a learned lightweight distance proxy function and a speed-level tracking technique on Riemannian manifold. Intrinsic system safety is guaranteed, and a novel interface for skill transfer is enabled. A long-horizon rearrangement experiment, a bimanual turnover manipulation, and multiple comparative performance evaluation verify the effectiveness of the proposed framework.

Visual servoing of robot manipulators can be viewed as an optimization problem and recurrent neural network is widely accepted as a powerful tool for solving optimization problems. Inspired by this, an adaptive neural network method is proposed for image-based visual servoing (IBVS) with uncertain parameters. It is the first work focused on IBVS simultaneously considering the uncertain camera configuration parameters and uncertain kinematics of robot manipulators in the framework of recurrent neural networks. Theoretical analysis including convergence and stability of the proposed method is presented. In order to verify the effectiveness of the theoretical results and the portability of the proposed method, simulations are conducted on different robot manipulators for different tracking tasks with excellent performance. In addition, comparisons with control schemes employing traditional gradient neural network (GNN), Kalman filter (KF) and model-based recurrent neural network highlight the great advantages of the proposed control system.

Tracking control of redundant and hyperredundant manipulators is a fundamental and critical problem in practical applications. In order to effectively decrease the end-effector position errors, a novel dual fuzzy-enhanced neurodynamic (DFEN) scheme is put forward for solving the position error accumulation problem followed by achieving accurate tracking control results. The proposed scheme is established based on a zeroing neurodynamic approach in conjunction with two fuzzy adjustment units that are capable of tuning the control parameters by monitoring the tracking error. Moreover, the DFEN scheme can effectively solve the tracking problem without requiring knowinga prioriknowledge of the kinematic model of the robot. The convergence and the stability of the proposed approach are demonstrated by theoretical analysis. The effectiveness, accuracy, and robustness of the proposed DFEN scheme are verified on the simulative redundant manipulator, continuum robot, and hybrid robot (integrating the redundant manipulator and the continuum robot). A practical experiment is provided to validate the proposed scheme as well.

Fault tolerance is a critical requirement for robust motion control of redundant robotic manipulators. This article aims to endow the redundant manipulator with the capability to achieve the required path of end-effector in the condition that one or some of its joints’ motion fail. Although many fault-tolerant control algorithms of redundant manipulator have been proposed in recent years. However, few of them are on the basis of the condition that the robotic model is unknown. The complexity of the calculation model limits the efficiency and portability of these algorithms. For the first time, we proposed a discrete model-free fault-tolerant tracking control scheme of redundant manipulator, which takes into account the fault tolerance in the control system of redundant manipulator by formulating it into a quadratic programming (QP) framework. The core of the proposed scheme consists of a discrete kinematic estimator and a discrete QP solver, powered by which the fault-tolerant control problem is transformed into a unified computing problem relaxing the need of knowing the redundant manipulator’s kinematic model. A discrete joint space observer is proposed for the detection of the happening of faulty states. Extensive simulations and experiments based on a redundant manipulator are performed and analyzed to support the verification of the efficiency and effectiveness of the proposed scheme.

Bio-inspired robots, e.g., soft continuum robots, have broad application prospects due to their structural dexterity and interaction safety. But these features also bring great challenges to the precise control of soft continuum robots. In this work, we investigate how to achieve the kinematic control of soft continuum robots without knowing model parameters of the robots. To this end, a model-free scheme based on varying-parameter recurrent neural networks (VP-RNN) is proposed. The scheme involves two components, one of which solves the inverse kinematics problem based on a VP-RNN model, and the other employs another VP-RNN model to estimate the pseudo-inverse of Jacobian matrix of continuum robots. Finally, the feasibility and robustness of the proposed control strategy are validated by simulations, including comparisons with other methods and case study with jammed actuation.

In the paper, a new method named Cartesian Space Synchronous Impedance Control (CSSIC) has been developed. The method combines the synchronous control and the impedance control together which can not only be used in the position control but can also realize the purpose of force control of the system with multi-manipulators. Therefore, if there are multi-manipulators grasping the same object, it can ensure the object will not fall and not be destroyed. The mathematical validation process and the stability proof of the method have been given. Besides, an experiment setup which has two 7-DOF robot arms has been established to testify the method. The testing result shows that the dual arm system, under disturbance, can ensure stable grasping of the object with the CSSIC method.

This paper gives an overview of the Chinese intelligent space robotic system. The system consists of a 6 DOF robot arm, a large-error tolerated gripper with two stereo cameras and onboard computer. The robot arm is composed of six identical modular joints, a big central hole in the modular joint was designed for the placement of the cables and plugs in the robot arm, which prevented them from damage of high temperature, radiation in the space environment and the motion of the robot. Joint torque sensor, joint position sensor and temperature sensors etc.., were integrated into the fully modular multi-sensory joint, which made the joint more intelligent. Also, a large-error tolerated gripper with two stereo cameras has been also designed to capture a microtarget satellite (MTS). A fault-tolerant onboard computer (OBC) with dual processing modules has been developed for the robot control. A zero gravity experimental system was developed to verify the functions of the robot arm under zero gravity environment