In this article, the trajectory planning of the two manipulators of the dual-arm robot is studied to approach the patient in a complex environment with deep reinforcement learning algorithms. The shape of the human body and bed is complex which may lead to the collision between the human and the robot. Because the sparse reward the robot obtains from the environment may not support the robot to accomplish the task, a neural network is trained to control the manipulators of the robot to prepare to hold the patient up by using a proximal policy optimization algorithm with a continuous reward function. Firstly, considering the realistic scene, the 3D simulation environment is built to conduct the research. Secondly, inspired by the idea of the artificial potential field, a new reward and punishment function was proposed to help the robot obtain enough rewards to explore the environment. The function is consisting of four parts which include the reward guidance function, collision detection, obstacle avoidance function, and time function. Where the reward guidance function is used to guide the robot to approach the targets to hold the patient, the collision detection and obstacle avoidance function are complementary to each other and are used to avoid obstacles, and the time function is used to reduce the number of training episode. Finally, after the robot is trained to reach the targets, the training results are analyzed. Compared with the DDPG algorithm, the PPO algorithm reduces about 4 million steps for training to converge. Moreover, compared with the other reward and punishment functions, the function used in this paper will obtain many more rewards at the same training time. Apart from that, it will take much less time to converge, and the episode length will be shorter; so, the advantage of the algorithm used in this paper is verified.

Teleoperation has been widely used to expand human working capability in remote, unstructured, and dangerous environments, such as explosive disposal and rescue tasks. In such scenarios, both large-scale flexible obstacle avoidance and small-scale refined operations are often required. However, existing teleoperation devices rarely manage to meet both of these requirements at the same time. This article proposes a new exoskeleton capable of functioning in homogeneous and heterogeneous teleoperation to achieve efficient and precise human-like teleoperation. Regarding hardware design, the exoskeleton fully considers the motion coordination of the human arm. It covers all degrees of freedom of the human arm, including the sternoclavicular motion. A new elbow structure and special overall layout are implemented to reduce the motion inertia and enhance the range of motion. Regarding teleoperation control, a novel teleoperation framework is proposed that seamlessly switches between homogeneous (phased posture mapping) and heterogeneous (workspace operation). With this, the operator can quickly avoid obstacles, approach the target position in a homogeneous manner, and then perform precise operations in a heterogeneous manner. Thorough analyses and experiments demonstrate that our proposed exoskeleton system and teleoperation method exhibit superior performance in rapidity with high success rates in complex teleoperation tasks.

Developing a human bionic manipulator to achieve certain humanoid behavioral skills is a rising problem. Enabling robots to operate the steering wheel to drive the vehicle is a challenging task. To address the problem, this work designs a novel 7-DOF (degree of freedom) humanoid manipulator based on the arm structure of human bionics. The 3-2-2 structural arrangement of the motors and the structural modifications at the wrist allow the manipulator to act more similar to a man. Meanwhile, to manipulate the steering wheel stably and compliantly, an admittance control approach is firstly applied for this case. Considering that the system parameters vary in configuration, we further introduce parameter fuzzification for admittance control. Designed simulations were carried out in Coppeliasim to verify the proposed control approach. As the result shows, the improved method could realize compliant force control under extreme configurations. It demonstrates that the humanoid manipulator can twist the steering wheel stably even in extreme configurations. It is the first exploration to operate a steering wheel similar to a human with a manipulator by using admittance control.

Developing an amphibious hip powered exoskeleton (AHPE) for lower limb augment in amphibious environments is crucial, which is facing the challenges, such as mechanical design, effective human-exoskeleton interaction, and simulating scenarios, for performance validations. To tackle these issues, this work proposes a design of a cable-driven AHPE named AmphiHip Exo for the hip flexion/extension assisting. To achieve an effective human-exoskeleton interaction, a physics-informed neural network named PILaN is proposed to realize hip motion intention perception (HMIP)-based control of the AmphiHip Exo. Trained by a self-collected small-scale dataset containing hip states of human activities, the proposed PILaN can automatically proceed HMIP, including joint trajectory and velocity estimations, with real-time dynamics parameter estimations and the Lagrangian dynamics model. Prototype tests are conducted on various wearers under four designed task scenarios: daily handling, climbing stairs, underwater gait assistance, and water rescue, and the performances are validated according to our designed evaluation metrics: HMIP accuracy, power assisting effect (PAE), and mechanical reliability. Experimental results prove the accuracy and efficiency of PILaN, the PAE among different wearers and task scenarios, and the waterproof effect as well as battery endurance, demonstrating the feasibility of the designed AmphiHip Exo.

In robotic teleoperation, the simultaneous realization of rapid tracking, compliance, and safe interaction presents a fundamental control challenge. This challenge stems from a critical trade-off: high-stiffness controllers achieve rapid tracking but compromise safety during physical interactions, whereas low-stiffness impedance controllers ensure compliant and safe interactions at the expense of responsiveness. To address this conflict, this study proposes a bio-inspired teleoperation control method (BITC) that integrates human withdrawal reflex mechanisms and the nonlinear stiffness characteristics of shear-thickening fluids. BITC features a dynamic force-feedback-driven collision reflex strategy, enabling rapid detection and disengagement from unintended contacts. Additionally, a nonlinear compliance control module is proposed to achieve both force fidelity during initial contact and adaptive stiffness modulation during progressively deeper contact in an emergency. By integrating full-state feedback tracking, the BITC teleoperation control framework is implemented to unify the performance of rapid tracking, compliance, and safety. Three experiments are conducted to demonstrate that the BITC method achieves accurate tracking performance, ensures compliant behavior during deep contact while maintaining force fidelity during initial contact, and enables safe reflexion for collision, respectively. The method is also validated to reduce peak contact forces by approximately 60% and minimizes contact duration to less than 120 ms, presenting comprehensive teleoperation performance.