No abstract

In order to plan the robot path in 3D space efficiently, a modified Rapidly-exploring Random Trees based on heuristic probability bias-goal (PBG-RRT) is proposed. The algorithm combines heuristic probabilistic and bias-goal factor, which can get convergence quickly and avoid falling into a local minimum. Firstly, PBG-RRT is used to plan a path. After obtaining path points, path points are rarefied by the Douglas-Peucker algorithm while maintaining the original path characteristics. Then, a smooth trajectory suitable for the manipulator end effector is generated by Non-uniform B-spline interpolation. Finally, the effector is moving along the trajectory by inverse kinematics solving angle of joint. The above is a set of motion planning for the manipulator. Generally, 3D space obstacle avoidance simulation experiments show that the search efficiency of PBG-RRT is increased by 217%, while search time is dropped by 168% compared with P-RRT (Heuristic Probability RRT). After rarefying, the situation where the path oscillated around the obstacle is corrected effectively. And a smooth trajectory is fitted by spline interpolation. Ultimately, PBG-RRT is verified on the ROS (Robot Operating System) with the Robot-Anno manipulator. The results reveal that the validity and reliability of PBG-RRT are proofed in obstacle avoidance planning.

No abstract

The survivability of autonomous underwater vehicles (AUV) in complex missions and dangerous situations is of great significance to ocean resource exploration, hydrological research, maritime rescue, and undersea military. Existing researches on motion control for the AUV mainly focus on its normal operating, but the active self-rescue method in emergency situations is hardly found. As classical control methods are not sufficient enough for complicated self-rescue missions of the AUV, this paper uses the deep reinforcement learning (DRL) algorithm to solve this problem because the DRL algorithm has the advantages in learning and decision making for complex robot control missions. In this paper, the normal motion control of the AUV based on the deep deterministic policy gradient algorithm is explored, including the yaw angle adjustment, yaw angle adjustment extension, trajectory tracking, and normal floating-up control of the AUV. Then, active self-rescue methods are successfully achieved to recover the AUV from emergencies, such as ocean water density decreasing sharply or one fin getting jammed at a random angle. What is more, real environment experiments are successfully conducted on a self-developed platform of the AUV to validate the feasibility of the proposed control methods. The results can effectively improve the survivability of the AUV and can be a reference to submarine survivability technologies.

No abstract