Locomotion with unit-modular reconfigurable robot
Locomotion with unit-modular reconfigurable robot
Reinforcement Learning in the Multi-Robot Domain
Autonomous Robots
Multimode locomotion via SuperBot reconfigurable robots
Autonomous Robots
Design of the ATRON lattice-based self-reconfigurable robot
Autonomous Robots
Automated Design of Adaptive Controllers for Modular Robots using Reinforcement Learning
International Journal of Robotics Research
Million Module March: Scalable Locomotion for Large Self-Reconfiguring Robots
International Journal of Robotics Research
Learning to Move in Modular Robots using Central Pattern Generators and Online Optimization
International Journal of Robotics Research
Distributed Self-Reconfiguration of M-TRAN III Modular Robotic System
International Journal of Robotics Research
Evolutionary robotics: the next-generation-platform for on-line and on-board artificial evolution
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Anatomy-based organization of morphology and control in self-reconfigurable modular robots
Neural Computing and Applications
Roombots: reconfigurable robots for adaptive furniture
IEEE Computational Intelligence Magazine
Learning to coordinate behaviors
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
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
HyperNEAT for locomotion control in modular robots
ICES'10 Proceedings of the 9th international conference on Evolvable systems: from biology to hardware
Towards an evolutionary design of modular robots for industry
IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation - Volume Part I
No free lunch theorems for optimization
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
In this paper, we present a distributed reinforcement learning strategy for morphology-independent life-long gait learning for modular robots. All modules run identical controllers that locally and independently optimize their action selection based on the robot's velocity as a global, shared reward signal. We evaluate the strategy experimentally mainly on simulated, but also on physical, modular robots. We find that the strategy: (i) for six of seven configurations (3-12 modules) converge in 96% of the trials to the best known action-based gaits within 15 min, on average, (ii) can be transferred to physical robots with a comparable performance, (iii) can be applied to learn simple gait control tables for both M-TRAN and ATRON robots, (iv) enables an 8-module robot to adapt to faults and changes in its morphology, and (v) can learn gaits for up to 60 module robots but a divergence effect becomes substantial from 20-30 modules. These experiments demonstrate the advantages of a distributed learning strategy for modular robots, such as simplicity in implementation, low resource requirements, morphology independence, reconfigurability, and fault tolerance.