Visual servoing is widely used in the peg-in-hole assembly due to the uncertainty of pose. Humans can easily align the peg with the hole according to key visual points/edges. By imitating human behavior, we propose P2HNet, a learning-based neural network that can directly extract desired landmarks for visual servoing. To avoid collecting and annotating a large number of real images for training, we built a virtual assembly scene to generate many synthetic data for transfer learning. A multi-modal peg-in-hole strategy is then introduced to combine image-based search-and-force-based insertion. P2HNet-based visual servoing and spiral search are used to align the peg with the hole from coarse to fine. Force control is then used to complete the insertion. The strategy exploits the flexibility of neural networks and the stability of traditional methods. The effectiveness of the method was experimentally verified in the D-sub connector assembly with sub-millimeter clearance. The results show that the proposed method can achieve a higher success rate and efficiency than the baseline method in the high-precision peg-in-hole assembly.

Redundant manipulators are widely used in fields such as human-robot collaboration due to their good flexibility. To ensure efficiency and safety, the manipulator is required to avoid obstacles while tracking a desired trajectory in many tasks. Conventional methods for obstacle avoidance of redundant manipulators may encounter joint singularity or exceed joint position limits while tracking the desired trajectory. By integrating deep reinforcement learning into the gradient projection method, a reactive obstacle avoidance method for redundant manipulators is proposed. We establish a general DRL framework for obstacle avoidance, and then a reinforcement learning agent is applied to learn motion in the null space of the redundant manipulator Jacobian matrix. The reward function of reinforcement learning is redesigned to handle multiple constraints automatically. Specifically, the manipulability index is introduced into the reward function, and thus the manipulator can maintain high manipulability to avoid joint singularity while executing tasks. To show the effectiveness of the proposed method, the simulation of 4 degrees of planar manipulator freedom is given. Compared with the gradient projection method, the proposed method outperforms in a success rate of obstacles avoidance, average manipulability, and time efficiency.

Bounding box algorithm is generally used to detect whether a manipulator is in collision with environment or itself. In this paper, we propose a rapid collision detection algorithm for manipulator based on the vector relation of basic geometrical elements. Firstly, we analyze the precision and efficiency of three commonly used algorithm - sphere, AABB (Axis-Aligned Bounding Box) and OBB(Oriented Bounding Box). Secondly, we extract the concept of “center distance” and “geometric dimension” by simplifying a manipulator and its environment to the combination of some geometry for detecting collision rapidly. Then, we simplify the collision of manipulator to 4 kinds of collision - sphere-cylinder, sphere-cuboid, cylinder-cylinder and cuboid-cuboid. Finally, the validity of this collision detection algorithm is verified by developing a simulation system based on OSG(OpenSceneGraph) for a 8-DOF manipulator.

On-orbit operation tasks require the space robot to work in an unstructured dynamic environment, where the end-effector’s trajectory and obstacle avoidance need to be guaranteed simultaneously. To ensure the completability and safety of the tasks, this paper proposes a new obstacle-avoidance motion planning method for redundant space robots via reinforcement learning (RL). First, the motion planning framework, which combines RL with the null-space motion for redundant space robots, is proposed according to the decomposition of joint motion. Second, the RL model for null-space obstacle avoidance is constructed, where the RL agent’s state and reward function are defined independent of the specific information of obstacles so that it can adapt to dynamic environmental changes. Finally, a curriculum learning-based training strategy for RL agents is designed to improve sample efficiency, training stability, and obstacle-avoidance performance. The simulation shows that the proposed method realizes reactive obstacle avoidance while maintaining the end-effector’s predetermined trajectory, as well as the adaptability to unstructured dynamic environments and robustness to the space robot’s dynamic parameters.