Hybrid Model for Passive Locomotion Control of a Biped Humanoid:The Artificial Neural Network Approach

Abstract

Developing a correct model for a biped robot locomotion is extremely challenging due to its inherently unstable structure because of the passive joint located at the unilateral foot-ground contact and varying configurations throughout the gait cycle, resulting variation of dynamic descriptions and control laws from phase to phase. The present research describes the development of a hybrid biped model using an Open Dynamics Engine (ODE) based analytical three link leg model as a base model and, on top of it, an Artificial Neural Network based learning model which ensures better adaptability, better limits cycle behaviors and better generalization while negotiating along a down slope. The base model has been configured according to the individual subjects and data have been collected using a novel technique through an android app from those subjects while walking down a slope. The pattern between the deviation of the actual trajectories and the base model generated trajectories has been found using a back propagation based artificial neural network architecture. It has been observed that this base model with learning based compensation enables the biped to better adapt in a real walking environment, showing better limit cycle behaviors. We also observed the bounded nature of deviation which led us to conclude that the strategy for biped locomotion control is generic in nature and largely dominated by learning.

Real‐time force doors detection system using distributed sensors and neural networks

“…The use of distributed sensors in buildings or outdoor environments is a very common approach. However, many research works are starting to embed sensors in some moving systems like robots . The combination of the data and neural networks is able to create autonomous location systems.…”

“…However, many research works are starting to embed sensors in some moving systems like robots. 22,23 The combination of the data and neural networks is able to create autonomous location systems. Thus, some research works propose to include sensors and neural networks in vehicles to evaluate safety at every moment.…”

Normalized Neural Network for Energy Efficient Bipedal Walking Using Nonlinear Inverted Pendulum Model

“…The neural network eliminates the need for solving non-linear equations on-line. Raj et al [17] employed a neural network and Open Dynamics Engine to build a hybrid model for the locomotion control of a bipedal robot. Li et al [18] adopted central pattern generators and neural networks to generate bipedal locomotion.…”

Machine Intelligence and Signal Analysis

“…In this case we have considered only states in terms of joints angle value we would not referred the terrain. Cellular automata are mathematical tool [10] for modeling a system that evolves with certain set of rule. It merges the specifications for discrete switching logic and continuous dynamics behaviors of any dynamical system.…”