Title :
Robust Quantum-Inspired Reinforcement Learning for Robot Navigation
Author :
Dong, Daoyi ; Chen, Chunlin ; Chu, Jian ; Tarn, Tzyh-Jong
Author_Institution :
State Key Lab. of Ind. Control Technol., Zhejiang Univ., Hangzhou, China
Abstract :
A novel quantum-inspired reinforcement learning (QiRL) algorithm is proposed for navigation control of autonomous mobile robots. The QiRL algorithm adopts a probabilistic action selection policy and a new reinforcement strategy, which are inspired, respectively, by the collapse phenomenon in quantum measurement and amplitude amplification in quantum computation. Several simulated experiments of Markovian state transition demonstrate that QiRL is more robust to learning rates and initial states than traditional reinforcement learning. The QiRL approach is then applied to navigation control of a real mobile robot, and the simulated and experimental results show the effectiveness of the proposed approach.
Keywords :
Markov processes; learning (artificial intelligence); mobile robots; path planning; Markovian state transition; QiRL; amplitude amplification; autonomous mobile robots; mobile robot; probabilistic action selection; quantum computation; quantum measurement; robot navigation; robust quantum inspired reinforcement learning; Learning; Mobile robots; Navigation; Quantum computing; Robot sensing systems; Robustness; Probabilistic action selection; quantum amplitude amplification; quantum-inspired reinforcement learning (QiRL); robot navigation;
Journal_Title :
Mechatronics, IEEE/ASME Transactions on
DOI :
10.1109/TMECH.2010.2090896