Hao An's research while affiliated with Harbin Institute of Technology and other places

Compared with traditional rigid objects’ dynamic throwing and catching by the robot, the in-flight trajectory of nonrigid objects (incredibly variable centroid objects) throwing is more challenging to predict and track. This article proposes a variable centroid trajectory tracking network (VCTTN) with the fusion of vision and force information by introducing force data of throw processing to the vision neural network. The VCTTN-based model-free robot control system is developed to perform highly precise prediction and tracking with a part of the in-flight vision. The flight trajectories dataset of variable centroid objects generated by the robot arm is collected to train VCTTN. The experimental results show that trajectory prediction and tracking with the vision-force VCTTN is superior to the ones with the traditional vision perception and has an excellent tracking performance.

Torque-based impedance control, a kind of classical active compliant control, is widely required in human–robot interaction, medical rehabilitation, and other fields. Adaptive impedance control effectively tracks the force when the robot comes in contact with an unknown environment. Conventional adaptive impedance control (AIC) introduces the force tracking error of the last moment to adjust the controller parameters online, which is an indirect method. In this paper, joint friction in the robot system is first identified and compensated for to enable the excellent performance of torque-based impedance control. Second, neural networks are inserted into the torque-based impedance controller, and a neural adaptive impedance control (NAIC) scheme with directly online optimized parameters is proposed. In addition, NAIC can be deployed directly without the need for data collection and training. Simulation studies and real-world experiments with a six link rotary robot manipulator demonstrate the excellent performance of NAIC.

Robot force control that needs to be customized for the robot structure in unstructured environments with difficult-to-tune parameters guarantees robots’ compliance and safe human–robot interaction in an increasingly expanding work environment. Although reinforcement learning provides a new idea for the adaptive adjustment of these parameters, the policy often needs to be trained from scratch when used in new robotics, even in the same task. This paper proposes the episodic Natural Actor-Critic algorithm with action limits to improve robot admittance control and transfer motor skills between robots. The motion skills learned by simple simulated robots can be applied to complex real robots, reducing the difficulty of training and time consumption. The admittance control ensures the realizability and mobility of the robot’s compliance in all directions. At the same time, the reinforcement learning algorithm builds up the environment model and realizes the adaptive adjustment of the impedance parameters during the robot’s movement. In typical robot contact tasks, motor skills are trained in a robot with a simple structure in simulation and used for a robot with a complex structure in reality to perform the same task. The real robot’s performance in each task is similar to the simulated robot’s in the same environment, which verifies the method’s effectiveness.

In this paper, a decoupled and adaptive polishing system without force sensors is designed for the industrial robot to track the rapid change of the contact force and eliminate dynamical nonlinearities in the polishing process. An identification method is proposed to obtain the dynamic model of this system. The system dynamic model is composed of the nominal linear model and the nonlinear model. The parameters of the system linear time-invariant (LTI) model is identified by frequency domain response with the disturbance observer in this paper. Regarding the high order differential terms and uncertain errors of the nonlinear part of the dynamic model, the Long-Short Term Memory (LSTM) is introduced for identifying system nonlinear characteristics. The bounds of the learning rate are discussed and the LSTM stability analysis result shows that the proposed method holds the Lyapunov stability. Finally, the experimental results show that a more accurate dynamic model can be established by combing frequency domain response and LSTM.