On building systems that will fail
Communications of the ACM - Special issue on LISP
Efficient and Accurate Parallel Genetic Algorithms
Efficient and Accurate Parallel Genetic Algorithms
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Multi-Objective Optimization Using Evolutionary Algorithms
Multi-Objective Optimization Using Evolutionary Algorithms
Robot Learning
Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics
Proceedings of the Third European Conference on Advances in Artificial Life
Survey of Intelligent Control Techniques for Humanoid Robots
Journal of Intelligent and Robotic Systems
Genetic diversity as an objective in multi-objective evolutionary algorithms
Evolutionary Computation
Stochastic Local Search: Foundations & Applications
Stochastic Local Search: Foundations & Applications
A tutorial on support vector regression
Statistics and Computing
Hardware Evolution of Analog Circuits for In-situ Robotic Fault-Recovery
EH '05 Proceedings of the 2005 NASA/DoD Conference on Evolvable Hardware
Innately adaptive robotics through embodied evolution
Autonomous Robots
Fault-Tolerant Systems
Action-selection and crossover strategies for self-modeling machines
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Learning to Move in Modular Robots using Central Pattern Generators and Online Optimization
International Journal of Robotics Research
Efficient Walking Speed Optimization of a Humanoid Robot
International Journal of Robotics Research
Fitness functions in evolutionary robotics: A survey and analysis
Robotics and Autonomous Systems
A survey of robot learning from demonstration
Robotics and Autonomous Systems
Self-modeling in humanoid soccer robots
Robotics and Autonomous Systems
Neuroevolution strategies for episodic reinforcement learning
Journal of Algorithms
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Computer-automated evolution of an x-band antenna for nasa's space technology 5 mission
Evolutionary Computation
Encouraging behavioral diversity in evolutionary robotics: An empirical study
Evolutionary Computation
Body Schema in Robotics: A Review
IEEE Transactions on Autonomous Mental Development
Autonomous evolution of dynamic gaits with two quadruped robots
IEEE Transactions on Robotics
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
Nonlinear System Identification Using Coevolution of Models and Tests
IEEE Transactions on Evolutionary Computation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Brief Robust fault-tolerant self-recovering control of nonlinear uncertain systems
Automatica (Journal of IFAC)
On the Performance of Indirect Encoding Across the Continuum of Regularity
IEEE Transactions on Evolutionary Computation
A comparison of sampling strategies for parameter estimation of a robot simulator
SIMPAR'12 Proceedings of the Third international conference on Simulation, Modeling, and Programming for Autonomous Robots
Behavioral repertoire learning in robotics
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Hi-index | 0.00 |
Damage recovery is critical for autonomous robots that need to operate for a long time without assistance. Most current methods are complex and costly because they require anticipating potential damage in order to have a contingency plan ready. As an alternative, we introduce the T-resilience algorithm, a new algorithm that allows robots to quickly and autonomously discover compensatory behavior in unanticipated situations. This algorithm equips the robot with a self-model and discovers new behavior by learning to avoid those that perform differently in the self-model and in reality. Our algorithm thus does not identify the damaged parts but it implicitly searches for efficient behavior that does not use them. We evaluate the T-resilience algorithm on a hexapod robot that needs to adapt to leg removal, broken legs and motor failures; we compare it to stochastic local search, policy gradient and the self-modeling algorithm proposed by Bongard et al. The behavior of the robot is assessed on-board thanks to an RGB-D sensor and a SLAM algorithm. Using only 25 tests on the robot and an overall running time of 20 min, T-resilience consistently leads to substantially better results than the other approaches.