On chains of oscillators forced at one end
SIAM Journal on Applied Mathematics
Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Evolving dynamical neural networks for adaptive behavior
Adaptive Behavior
Locomotion with unit-modular reconfigurable robot
Locomotion with unit-modular reconfigurable robot
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Fast Biped Walking with a Sensor-driven Neuronal Controller and Real-time Online Learning
International Journal of Robotics Research
Biological Cybernetics - Special Issue: Dynamic Principles
Evolving 3d morphology and behavior by competition
Artificial Life
IEEE Transactions on Robotics
An adaptive, self-organizing dynamical system for hierarchical control of bio-inspired locomotion
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Roombots: mechanical design of self-reconfiguring modular robots for adaptive furniture
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Experiments with a ZigBee wireless communication system for self-reconfiguring modular robots
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Information Sciences: an International Journal
Roombots: reconfigurable robots for adaptive furniture
IEEE Computational Intelligence Magazine
Distributed online learning of central pattern generators in modular robots
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Fractal gene regulatory networks for robust locomotion control of modular robots
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
A self-organizing map for controlling artificial locomotion
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
The mathematical model and control scheme of a four-legged robot based on GZ-I and note module
ICIRA'10 Proceedings of the Third international conference on Intelligent robotics and applications - Volume Part I
Online adaptation of locomotion with evolutionary algorithms: a transferability-based approach
Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Robotics and Autonomous Systems
Neural control of a modular multi-legged walking machine: Simulation and hardware
Robotics and Autonomous Systems
Chaotic exploration and learning of locomotion behaviors
Neural Computation
Modular and reconfigurable mobile robotics
Robotics and Autonomous Systems
Robotics and Autonomous Systems
Fast damage recovery in robotics with the T-resilience algorithm
International Journal of Robotics Research
Hi-index | 0.00 |
This article addresses the problem of how modular robotics systems, i.e. systems composed of multiple modules that can be configured into different robotic structures, can learn to locomote. In particular, we tackle the problems of online learning, that is, learning while moving, and the problem of dealing with unknown arbitrary robotic structures. We propose a framework for learning locomotion controllers based on two components: a central pattern generator (CPG) and a gradient-free optimization algorithm referred to as Powell's method. The CPG is implemented as a system of coupled nonlinear oscillators in our YaMoR modular robotic system, with one oscillator per module. The nonlinear oscillators are coupled together across modules using Bluetooth communication to obtain specific gaits, i.e. synchronized patterns of oscillations among modules. Online learning involves running the Powell optimization algorithm in parallel with the CPG model, with the speed of locomotion being the criterion to be optimized. Interesting aspects of the optimization include the fact that it is carried out online, the robots do not require stopping or resetting and it is fast. We present results showing the interesting properties of this framework for a modular robotic system. In particular, our CPG model can readily be implemented in a distributed system, it is computationally cheap, it exhibits limit cycle behavior (temporary perturbations are rapidly forgotten), it produces smooth trajectories even when control parameters are abruptly changed and it is robust against imperfect communication among modules. We also present results of learning to move with three different robot structures. Interesting locomotion modes are obtained after running the optimization for less than 60 minutes.