GA-based Automatic Acquisition of Fuzzy Rules for Controlling Quadruped Walking Robots
نویسندگان
چکیده
This paper presents a method that can acquire fuzzy rules for Sony legged robot behaviours automatically. We use fuzzy logic controllers (FLCs) to design robot behaviours. The antecedents of the FLCs are pre-design, while their consequences are left for automatic acquisition. Once the consequences are optimally chosen, the robot behaviours are well designed. Genetic algorithms (GAs) are employed to search best FLC consequences. The Sony quadruped robots are used to evaluate proposed approaches in the robotic football domain. Two behaviours, ball-chasing and position-reaching, are studied and implemented in both simulation and real robots. The results show that the behaviours can be automatically acquired through the FLCs evolving.
منابع مشابه
Analysis of Balance of Quadrupedal Robotic Walk using Measure of Balance Margin
In this study, we analyze the balance of quadruped walking robots. For this purpose, a simplified polygonal model of a quadruped walking configuration is considered. A boundaryrange-based balance margin is used for determining the system stability of the polygonal walking configuration considered herein. The balance margin enables the estimation of the walking configuration’s balance for effect...
متن کاملDynamics modeling and stable gait planning of a quadruped robot in walking over uneven terrains
Quadruped robots have unique capabilities for motion over uneven natural environments. This article presents a stable gait for a quadruped robot in such motions and discusses the inverse-dynamics control scheme to follow the planned gait. First, an explicit dynamics model will be developed using a novel constraint elimination method for an 18-DOF quadruped robot. Thereafter, an inverse-dynamics...
متن کاملA Multi-Agent System for Cooperative Quadruped Walking Robots
We are interested in participating in RoboCup (Robot World Cup Initiative) challenge since it is an excellent forum to promote the research in many areas such as artificial intelligence, robotics, and agent technology. This paper introduces our current research efforts to build a multi-agent system for cooperation and learning of multiple legged robots in the RoboCup domain. A behaviour-based h...
متن کاملPareto design of fuzzy tracking control based on the particle swarm optimization algorithm for a walking robot in the lateral plane on slope
Many researchers have controlled and analyzed biped robots that walk in the sagittal plane. Nevertheless, walking robots require the capability to walk merely laterally, when they are faced with the obstacles such as a wall. In walking robot field, both nonlinearity of the dynamic equations and also having a tracking system cause an effective control has to be utilized to address these problems...
متن کاملHybrid learning architecture for fuzzy control of quadruped walking robots
This article presents a hybrid learning architecture for fuzzy control of quadruped walking robots in the RoboCup domain. It combines reactive behaviors with deliberative reasoning to achieve complex goals in uncertain and dynamic environments. To achieve real-time and robust control performance, fuzzy logic controllers (FLCs) are used to encode the behaviors and a two-stage learning scheme is ...
متن کامل