This paper presents an innovative hybrid approach that integrates traditional control strategies with deep reinforcement learning for robotic assembly. By fusing multimodal information from visual and force feedback, the method leverages admittance control to ensure safe force feedback while using deep reinforcement learning to process visual input, enabling precise control and real-time correction of assembly actions. This multi-sensor feedback mechanism not only enhances the stability and accuracy of the assembly process but also improves the robot’s robustness and adaptability in uncertain environments. Additionally, a twin-delay deep deterministic policy gradient algorithm based on residual reinforcement learning is proposed. The design of a task-specific reward function, which simultaneously considers visual goals, force compliance, and contact stability, effectively addresses challenges such as difficult state information acquisition and sparse rewards in assembly tasks. This improves the robot’s interaction capabilities and task execution efficiency in real-world environments. Experimental results demonstrate that the method designed in this paper effectively reduces the training time for reinforcement learning from 400 epochs to 100 epochs, significantly decreases the magnitude of contact forces during the assembly process, and shortens the contact time.

The lower limb exoskeleton is a typical wearable robot designed to assist human motion. However, its system stability and performance are often compromised due to unknown model parameters and inadequate control strategies. Therefore, it is crucial to explore the parametric identification of the exoskeleton and the design of corresponding control strategies for human-exoskeleton cooperative motion. First, an exoskeleton platform is developed to provide experimental validation. Simultaneously, a two-degree-of-freedom (2-DOF) exoskeleton model is constructed using the Lagrange method. The neighborhood field optimization (NFO) technique is then applied to identify the unknown model parameters of the exoskeleton. Additionally, the excitation trajectories for the exoskeleton are developed by the NFO method, incorporating several motion constraints to enhance the accuracy of model identification. An admittance controller is implemented to enable active control of the exoskeleton, allowing it to align with human intention and thereby improving the wearability and comfort of the device. Finally, both simulation and experimental results are compared and verified on the platform. These results demonstrate that the NFO method achieves superior identification accuracy compared to particle swarm optimization (PSO) and genetic algorithm (GA).

Compliant interaction between robots and the environment is crucial for completing contact-rich tasks. However, obtaining and implementing optimal interaction behavior in complex unknown environments remains a challenge. This article develops a hybrid impedance and admittance control (HIAC) scheme for robots subjected to the second-order unknown environment. To obtain the second-order target impedance model that represents the optimal interaction behavior without the accurate environment dynamics and acceleration feedback, an impedance adaptation method with virtual inertia is proposed. Since impedance control and admittance control have complementary structures and result in unsatisfactory performance in a wide range of environmental stiffness due to their fixed causality, a hybrid system framework suitable for the second-order environment is proposed to generate a series of intermediate controllers which interpolate between the responses of impedance and admittance controls by using a switching controller and adjusting its switching duty cycle. In addition, the optimal intermediate controller is selected using a mapping of the optimal duty cycle to provide the optimal implementation performance for the target impedance model. The proposed HIAC scheme can achieve the desired interaction and impedance implementation performance while ensuring system stability. Simulation and experimental studies are performed to verify the effectiveness of our scheme with a 2-DOF manipulator and a 7-DOF Franka EMIKA panda robot, respectively.

Today, demandsin industrial manufacturing mandate humans to work with large-scale industrial robots, and this collaboration may result in dangerous conditions for humans. To deal with this situation, this work proposes a novel approach for redundant large-scale industrial robots. In the proposed approach, an admittance controller is designed to regulate the interaction between the end effector of the robot and the human. Additionally, an obstacle avoidance algorithm is implemented in the null space of the robot to prevent any possible unexpected collision between the human and the links of the robot. After safety performance of this approach is verified via simulations and experimental studies, the effect of the parameters of the admittance controller on the performance of collaboration in terms of both accuracy and total human effort is investigated. This investigation is carried out via 8 experiments by the participation of 10 test subjects in which the effect of different admittance controller parameters such as mass and damper are compared. As a result of this investigation, tuning insights for such parameters are revealed.

In this paper, we propose a novel unified framework for virtual guides. The human–robot interaction is based on a virtual robot, which is controlled by the admittance control. The unified framework combines virtual guides, control of the dynamic behavior, and path tracking. Different virtual guides and active constraints can be realized by using dead-zones in the position part of the admittance controller. The proposed algorithm can act in a changing task space and allows selection of the tasks-space and redundant degrees-of-freedom during the task execution. The admittance control algorithm can be implemented either on a velocity or on acceleration level. The proposed framework has been validated by an experiment on a KUKA LWR robot performing the Buzz-Wire task.