Development of Reinforcement Control Algorithm of Lower Body of Autonomous Humanoid Robot
Deepak Bharadwaj1, Manish Prateek2, Rashmi Sharma3
1Deepak Bharadwaj, Assistant Professor, School of Engineering, Department of Mechanical Engineering, University of Petroleum & Energy Studies Dehradun, India.
2Dr. Manish Prateek, Professor, School of Computer Science, University of Petroleum & Energy Studies Dehradun, India.
3Rashmi Sharma, Research Scholar, School of Computer Science, University of Petroleum & Energy Studies Dehradun, India.
Manuscript received on 12 April 2019 | Revised Manuscript received on 16 May 2019 | Manuscript published on 30 May 2019 | PP: 915-919 | Volume-8 Issue-1, May 2019 | Retrieval Number: F2292037619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents the reinforcement control algorithm for an autonomous humanoid robot. The proposed humanoid robot is sensing the present state and switching to the goal state without knowing the kinematics and dynamics of the body. Simulation is carried out on the MATLAB platform and Multibody dynamics toolbox to verify the algorithm. Optimal policy is decided based on the result to feed this value in model predative controller.
Index Terms: Reinforcement Algorithm, State, Reward, Q-Learning.
Scope of the Article: Algorithm Engineering