The study of the polymodel complex of the motion planning system of a heterogeneous group of autonomous robots in conditions of spatial-situational uncertainty

2019 ◽  
Vol 7 (4) ◽  
pp. 291-299
Author(s):  
Dmitrii Motorin
Keyword(s):  
Motion Planning ◽  
Autonomous Robots ◽  
Heterogeneous Group ◽  
Planning System ◽  
Situational Uncertainty

Motion Planning of a Nonholomonic Mobile Manipulator for Moving Object Grasping

2013 ◽  
Vol 380-384 ◽  
pp. 591-594
Author(s):  
Nai Jian Chen ◽  
Fang Zhen Song ◽  
Hong Hua Zhao ◽  
Ying Jun Li
Keyword(s):  
Motion Planning ◽  
Obstacle Avoidance ◽  
Moving Objects ◽  
Nonholonomic Constraints ◽  
Moving Object ◽  
Experimental Results ◽  
Mobile Platform ◽  
Planning System ◽  
Mobile Manipulator

This paper studies a nonholonomic mobile manipulator that consists of a wheeled mobile platform with a mounted serial manipulator. It is designed and developed to navigate autonomously in handling moving objects subjected to nonholonomic constraints. A camera is mounted on the front of the platform and employed to identify and collect information about distance, velocity and direction of the object. With that information collected, a motion planning system determines the preferred operation region and the obstacle-avoidance area, and thus generates the expected trajectory of the mobile manipulator. Experimental results are shown that the mobile manipulator can identify the target, generate trajectories and grasp the moving object autonomously.

scholarly journals End-to-End AUV Motion Planning Method Based on Soft Actor–Critic

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5893
Author(s):  
Xin Yu ◽  
Yushan Sun ◽  
Xiangbin Wang ◽  
Guocheng Zhang
Keyword(s):  
Reinforcement Learning ◽  
Motion Planning ◽  
Autonomous Underwater Vehicle ◽  
Planning System ◽  
Optimal Decision ◽  
Target Point ◽  
Planning Problem ◽  
Training Time ◽  
Reward Function ◽  
End To End

This study aims to solve the problems of poor exploration ability, single strategy, and high training cost in autonomous underwater vehicle (AUV) motion planning tasks and to overcome certain difficulties, such as multiple constraints and a sparse reward environment. In this research, an end-to-end motion planning system based on deep reinforcement learning is proposed to solve the motion planning problem of an underactuated AUV. The system directly maps the state information of the AUV and the environment into the control instructions of the AUV. The system is based on the soft actor–critic (SAC) algorithm, which enhances the exploration ability and robustness to the AUV environment. We also use the method of generative adversarial imitation learning (GAIL) to assist its training to overcome the problem that learning a policy for the first time is difficult and time-consuming in reinforcement learning. A comprehensive external reward function is then designed to help the AUV smoothly reach the target point, and the distance and time are optimized as much as possible. Finally, the end-to-end motion planning algorithm proposed in this research is tested and compared on the basis of the Unity simulation platform. Results show that the algorithm has an optimal decision-making ability during navigation, a shorter route, less time consumption, and a smoother trajectory. Moreover, GAIL can speed up the AUV training speed and minimize the training time without affecting the planning effect of the SAC algorithm.

Sign in / Sign up

Export Citation Format

Share Document