An exoskeleton force feedback dataglove is developed, which uses the pneumatic artificial muscles as actuators. On the basis of the simplified hand model, the motion equation is deduced according to the theory of Dena...An exoskeleton force feedback dataglove is developed, which uses the pneumatic artificial muscles as actuators. On the basis of the simplified hand model, the motion equation is deduced according to the theory of Denavit-Hartenberg. The model of the equivalent contact forces exerted by the object on the finger is proposed. By the principle of virtual work, the static equilibrium of finger is established. The force Jacobian matrix of finger is calculated, and then the joint torques of the finger when grasping objects are obtained. The theory and structure of the force feedback datagolve are introduced. Based on the theory of motion stabilization of four-bar linkage, the flexion angles of joints are measured. The torques on finger joints caused by the output forces of pneumatic artificial muscles are calculated. The output forces of pneumatic artificial muscle, whose values are controlled by its inner pressure, can be calculated by the joint torques of the finger when grasping objects. The arms of force, driving torques and the needed output forces of pneumatic muscle are calculated for each joint of the index finger. The criterion of output force of pneumatic muscle is given.展开更多
In this paper,an efficient skill learning framework is proposed for robotic insertion,based on one-shot demonstration and reinforcement learning.First,the robot action is composed of two parts:expert action and refine...In this paper,an efficient skill learning framework is proposed for robotic insertion,based on one-shot demonstration and reinforcement learning.First,the robot action is composed of two parts:expert action and refinement action.A force Jacobian matrix is calibrated with only one demonstration,based on which stable and safe expert action can be generated.The deep deterministic policy gradients(DDPG)method is employed to learn the refinement action,which aims to improve the assembly efficiency.Second,an episode-step exploration strategy is developed,which uses the expert action as a benchmark and adjusts the exploration intensity dynamically.A safety-efficiency reward function is designed for the compliant insertion.Third,to improve the adaptability with different components,a skill saving and selection mechanism is proposed.Several typical components are used to train the skill models.And the trained models and force Jacobian matrices are saved in a skill pool.Given a new component,the most appropriate model is selected from the skill pool according to the force Jacobian matrix and directly used to accomplish insertion tasks.Fourth,a simulation environment is established under the guidance of the force Jacobian matrix,which avoids tedious training process on real robotic systems.Simulation and experiments are conducted to validate the effectiveness of the proposed methods.展开更多
基金This project is supported by National Natural Science Foundation of China(No.50375034).
文摘An exoskeleton force feedback dataglove is developed, which uses the pneumatic artificial muscles as actuators. On the basis of the simplified hand model, the motion equation is deduced according to the theory of Denavit-Hartenberg. The model of the equivalent contact forces exerted by the object on the finger is proposed. By the principle of virtual work, the static equilibrium of finger is established. The force Jacobian matrix of finger is calculated, and then the joint torques of the finger when grasping objects are obtained. The theory and structure of the force feedback datagolve are introduced. Based on the theory of motion stabilization of four-bar linkage, the flexion angles of joints are measured. The torques on finger joints caused by the output forces of pneumatic artificial muscles are calculated. The output forces of pneumatic artificial muscle, whose values are controlled by its inner pressure, can be calculated by the joint torques of the finger when grasping objects. The arms of force, driving torques and the needed output forces of pneumatic muscle are calculated for each joint of the index finger. The criterion of output force of pneumatic muscle is given.
基金supported by National Key Research and Development Program of China(No.2018AAA0103005)National Natural Science Foundation of China(No.61873266)。
文摘In this paper,an efficient skill learning framework is proposed for robotic insertion,based on one-shot demonstration and reinforcement learning.First,the robot action is composed of two parts:expert action and refinement action.A force Jacobian matrix is calibrated with only one demonstration,based on which stable and safe expert action can be generated.The deep deterministic policy gradients(DDPG)method is employed to learn the refinement action,which aims to improve the assembly efficiency.Second,an episode-step exploration strategy is developed,which uses the expert action as a benchmark and adjusts the exploration intensity dynamically.A safety-efficiency reward function is designed for the compliant insertion.Third,to improve the adaptability with different components,a skill saving and selection mechanism is proposed.Several typical components are used to train the skill models.And the trained models and force Jacobian matrices are saved in a skill pool.Given a new component,the most appropriate model is selected from the skill pool according to the force Jacobian matrix and directly used to accomplish insertion tasks.Fourth,a simulation environment is established under the guidance of the force Jacobian matrix,which avoids tedious training process on real robotic systems.Simulation and experiments are conducted to validate the effectiveness of the proposed methods.