Evolving Fuzzy Logic Controllers for Sony Legged Robots
نویسندگان
چکیده
This paper presents an evolutionary approach to learning a fuzzy logic controller(FLC) employed for reactive behaviour control of Sony legged robots. The learning scheme is divided into two stages. The first stage is a structure learning in which the rule base of FLC is generated by a backup updating learning. The second stage is a parameter learning in which the parameters of membership functions of fuzzy sets are learned by a genetic algorithm (GA). Simulation results are provided to show the effectiveness of the proposed learning scheme.
منابع مشابه
GA-based Automatic Acquisition of Fuzzy Rules for Controlling Quadruped Walking Robots
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 employe...
متن کاملFuzzy behaviour learning for sony legged robots
This paper presents a learning reactive control scheme for the Sony legged robots to play soccer. We built a behavior-based architecture that consists of a set of reactive behaviors and a deliberative reasoning component to select or cc-ordinate the reactive behaviors. The major reactive behavior is for a Sony robot to move towards the ball, guided by on-board sensors. Fuzzy logic is used to en...
متن کاملReinforcement Learning of Fuzzy Logic Controllers for Quadruped Walking Robots
This paper presents a fuzzy logic controller (FLC) for the implementation of some behaviour of Sony legged robots. The adaptive heuristic Critic (AHC) reinforcement learning is employed to refine the FLC. The actor part of AHC is a conventional FLC in which the parameters of input membership functions are learned by an immediate internal reinforcement signal. This internal reinforcement signal ...
متن کاملReactive Behaviours and Agent Architecture for Sony Legged Robots to Play Football
Abstract. It has been an ultimate long-time dream in robotics and AI fields to build robotic systems with life-like appearance, behaviours and intelligence, reflected by many science fiction books and films. This is also an extremely challenging task. This paper introduces our current research efforts to build a multi-agent system for cooperation and learning of multiple life-like robots in the...
متن کاملTowards Learning and Evolving of a Team of Sony Legged Robots
This paper presents a hybrid approach to learning and evolving of a team of Sony legged robots (AIBO) in the robot football domain. These advanced walking robots aim to participate in the Sony Legged Robot League within the RoboCup competition. To achieve this goal, three important issues have been addressed in the paper:(i) multi-sensor based distributed perception, (ii) behaviour based approa...
متن کامل