A5094272939- Robotic Path Planning Algorithms
- Robot Manipulation and Learning
- Reinforcement Learning in Robotics
- Robotics and Automated Systems
- Robotic Mechanisms and Dynamics
- Robotics and Sensor-Based Localization
- Autonomous Vehicle Technology and Safety
Donghua University
2022-2024
Though there are extensive works on deep reinforcement learning (DRL) for robotics, sequential trajectory generation multiprocess robotic tasks based DRL is yet to be explored. In this article, the task formulated as a Markov decision process, and nested dual-memory deterministic policy gradient algorithm with dynamic criteria proposed, generalize traditional planning predefined target point into exploration problem aiming at area without solving inverse kinematics. First, architecture...
Trajectory generation for redundant manipulators based on inverse kinematics (IK) still faces some restraints, as it lacks universal IK calculation or specific trajectory methods that are suitable robots with arbitrary degrees of freedom. In this article, the IK-free robot is formulated a Markov decision process and implemented by general method deep reinforcement learning. First, an extensively explored evaluated actor-critic (E3AC) algorithm can make diverse action explorations...
Investigations on obstacle-avoidable robotic trajectory generation is of great significance to the secure production ordinary machinery factories, which allows robots work in complex environments. However, conventional collision-free highly dependent manual analysis environment, making extremely dedicated. To solve this problem, a more intelligent method based deep reinforcement learning that can globally perceive obstacle's information and automatically generate trajectories without inverse...