A master's thesis at University of Basrah examines the manufacture of an eight-legged mobile robot based on machine learning.
A master's thesis at College of Engineering at University of Basrah examines the manufacture of an eight-legged mobile robot based on machine learning.
The thesis, presented by the student Fatima Hamid Khayoun, aims to create an eight-legged robot system and simulate it using the Matlab toolkit Simscape Multi-Body. This toolkit is designed to create physical connections and communication within the system, allowing Simscape Multi-Body to define the system's equations.
The thesis concluded that the performance of the eight-legged robot has improved with the implementation of the optimization approach, compared to previous cases that used open-loop and closed-loop techniques. Deep Deterministic Policy Gradient (DDPG) reinforcement learning is used to implement and enhance the walking motion of the robot through machine learning. The simulation results indicate that the performance of the eight-legged robot has been improved compared to previous cases, including open-loop, PID, and genetic algorithm. Moreover, the results generated by deep deterministic policy gradient reinforcement learning show superior performance. Department of Media and Government Communication