Walking Motion Generation, Synthesis, and Control for Biped Robot by Using PGRL, LPI, and Fuzzy Logic

Abstract

This paper proposes the implementation of fuzzy motion control based on reinforcement learning (RL) and Lagrange polynomial interpolation (LPI) for gait synthesis of biped robots. First, the procedure of a walking gait is redefined into three states, and the parameters of this designed walking gait are determined. Then, the machine learning approach applied to adjusting the walking parameters is policy gradient RL (PGRL), which can execute real-time performance and directly modify the policy without calculating the dynamic function. Given a parameterized walking motion designed for biped robots, the PGRL algorithm automatically searches the set of possible parameters and finds the fastest possible walking motion. The reward function mainly considered is first the walking speed, which can be estimated from the vision system. However, the experiment illustrates that there are some stability problems in this kind of learning process. To solve these problems, the desired zero moment point trajectory is added to the reward function. The results show that the robot not only has more stable walking but also increases its walking speed after learning. This is more effective and attractive than manual trial-and-error tuning. LPI, moreover, is employed to transform the existing motions to the motion which has a revised angle determined by the fuzzy motion controller. Then, the biped robot can continuously walk in any desired direction through this fuzzy motion control. Finally, the fuzzy-based gait synthesis control is demonstrated by tasks and point- and line-target tracking. The experiments show the feasibility and effectiveness of gait learning with PGRL and the practicability of the proposed fuzzy motion control scheme.

Optimized Motion Energy Estimation for Group of Pictures in Multi-Level Error Protection of H.264/AVC Video Bitstreams

“…Lagrange polynomial is introduced as an efficient approximation method [14], which uses statistical information of the reference points (previous GOPs) to predict the current point (current GOP). In…”

“…It is proven that the F IXED LP method provides a better motion energy estimation compared to the W AV G method [14]. However, two outstanding issues existed in the F IXED LP method, which could be introduced as (1) how to choose an optimum number of previous GOPs that provides a good estimation with low complexity, and (2) how to select previous GOPs highly correlated to the current one, which can be used as references in Lagrange polynomial.…”

Comparisons Between Two Visual Navigation Strategies for Kicking to Virtual Target Point of Humanoid Robots

“…Substituting (14) and x vtp , x b , x p ≥ 0 into (13) gives (10). Then the first visual navigation strategy by the realization of the VTP all the time is designed as follows:…”

“…Based on pixel number variation of charge-coupled device images, a 2-D localization of target objects in robot soccer competitions was demonstrated to show their effectiveness [13]. Recently, [14] proposed the implementation of fuzzy motion control based on reinforcement learning (RL) and Lagrange polynomial 0018-9456 c 2013 IEEE interpolation (LPI) for gait synthesis of biped robots to obtain the target tracking.…”

Humanoid robot gait imitation

“…One of the key issues about humanoid robots is the walking motion [1] [2], which emphasizes how the humanoid robots could keep balance during the walking cycles.…”