Evolutionary neurocontrollers for autonomous mobile robots
Neural Networks - Special issue on neural control and robotics: biology and technology
Multi-Objective Optimization Using Evolutionary Algorithms
Multi-Objective Optimization Using Evolutionary Algorithms
Evolution of Plastic Control Networks
Autonomous Robots
Running Across the Reality Gap: Octopod Locomotion Evolved in a Minimal Simulation
Proceedings of the First European Workshop on Evolutionary Robotics
Evolutionary Techniques in Physical Robotics
ICES '00 Proceedings of the Third International Conference on Evolvable Systems: From Biology to Hardware
Combining Simulation and Reality in Evolutionary Robotics
Journal of Intelligent and Robotic Systems
Evaluation of real-time physics simulation systems
Proceedings of the 5th international conference on Computer graphics and interactive techniques in Australia and Southeast Asia
Using behavioral exploration objectives to solve deceptive problems in neuro-evolution
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Evolving mobile robots in simulated and real environments
Artificial Life
Automatic system identification based on coevolution of models and tests
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Explorations in design space: unconventional electronics designthrough artificial evolution
IEEE Transactions on Evolutionary Computation
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
How to promote generalisation in evolutionary robotics: the ProGAb approach
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Online adaptation of locomotion with evolutionary algorithms: a transferability-based approach
Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Evolving locomotion for a simulated 12-DOF quadruped robot
IPCAT'12 Proceedings of the 9th international conference on Information Processing in Cells and Tissues
Evolving flexible joint morphologies
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Not all physics simulators can be wrong in the same way
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Evolution of station keeping as a response to flows in an aquatic robot
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Sensitivity analysis of a crawl gait multi-objective optimization system
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
Applying evolutionary computation to harness passive material properties in robots
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
Humanoid robots learning to walk faster: from the real world to simulation and back
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Architecture of a cyberphysical avatar
Proceedings of the ACM/IEEE 4th International Conference on Cyber-Physical Systems
Encouraging reactivity to create robust machines
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
| Hi-index | 0.00 |
The reality gap, that often makes controllers evolved in simulation inefficient once transferred onto the real system, remains a critical issue in Evolutionary Robotics (ER); it prevents ER application to real-world problems. We hypothesize that this gap mainly stems from a conflict between the efficiency of the solutions in simulation and their transferability from simulation to reality: best solutions in simulation often rely on bad simulated phenomena (e.g. the most dynamic ones). This hypothesis leads to a multi-objective formulation of ER in which two main objectives are optimized via a Pareto-based Multi-Objective Evolutionary Algorithm: (1) the fitness and (2) the transferability. To evaluate this second objective, a simulation-to-reality disparity value is approximated for each controller. The proposed method is applied to the evolution of walking controllers for a real 8-DOF quadrupedal robot. It successfully finds efficient and well-transferable controllers with only a few experiments in reality.