Researcher from Harbin Institute of Technology Reports Details of New Studies an d Findings in the Area of Robotics (A Soft Actor-Critic Deep Reinforcement-Learn ing-Based Robot Navigation Method Using LiDAR)
Researcher from Harbin Institute of Technology Reports Details of New Studies an d Findings in the Area of Robotics (A Soft Actor-Critic Deep Reinforcement-Learn ing-Based Robot Navigation Method Using LiDAR)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on robotics is the subjec t of a new report. According to news reporting from Harbin, People's Republic of China, by NewsRx journalists, research stated, "When there are dynamic obstacle s in the environment, it is difficult for traditional path-generation algorithms to achieve desired obstacle-avoidance results." Financial supporters for this research include Key Special Projects of Heilongji ang Province's Key R &D Program. The news correspondents obtained a quote from the research from Harbin Institute of Technology: "To solve this problem, we propose a robot navigation control me thod based on SAC (Soft Actor-Critic) Deep Reinforcement Learning. Firstly, we u se a fast path-generation algorithm to control the robot to generate expert traj ectories when the robot encounters danger as well as when it approaches a target , and we combine SAC reinforcement learning with imitation learning based on exp ert trajectories to improve the safety of training. Then, for the hybrid data co nsisting of agent data and expert data, we use an improved prioritized experienc e replay method to improve the learning efficiency of the policies."
Key words
Harbin Institute of Technology/Harbin/People's Republic of China/Asia/Emerging Technologies/Machine Learning/Reinf orcement Learning/Robot/Robotics
NETL
NSTL