Evolving Mobile Robots in Simulated and Real Environments

Abstract

The problem of the validity of simulation is particularly relevant for methodologies that use machine learning techniques to develop control systems for autonomous robots, like, for instance, the Artificial Life approach named Evolutionary Robotics. In fact, despite that it has been demonstrated that training or evolving robots in the real environment is possible, the number of trials needed to test the system discourage the use of physical robots during the training period. By evolving neural controllers for a Khepera robot in computer simulations and then transferring the obtained agents in the real environment we will show that: (a) an accurate model of a particular robot-environment dynamics can be built by sampling the real world through the sensors and the actuators of the robot; (b) the performance gap between the obtained behaviors in simulated and real environment may be significantly reduced by introducing a "conservative" form of noise; (c) if a decrease in performance is observed when the system is transferred in the real environment, successful and robust results can be obtained by continuing the evolutionary process in the real environment for few generations.

Evolution of Implicit and Explicit Communication in Mobile Robots

“…the role of friction and inertia has been simulated in consideration of the light weight and the limited maximum speed of the e-puck robots). The state of the infrared sensors has been computed by using a sampling technique (Miglino et al, 1995). The shape of the robot body and the position of the sensors have been simulated with an accuracy of floating point precision.…”

Evolution of Embodied Intelligence

“…However, a possible strategy would be to evolve the learning rules (as described in a section above) and have the ÒnewbornÓ physical robot adapt online to its own physical characteristics. Also adding some noise to the sensors and actuator while simulating the robot may help bridge the gap to reality [23] by avoiding that the controller over-specialises to the simulation. Co-evolution of the body and controller has also been applied to biped robots [4].…”

Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs

“…The experiment is carried out in a realistic simulation of the Khepera robot ( fig. 1(a)) based on sensor sampling [6] and adding 5% uniform noise to the sampled values. Initially the robot is positioned as shown in figure 2, and the task is to find and stay on the black reward-zone which can be positioned in either the left or the right arm of the maze.…”

“…plastic Hebbian synapse networks [2]. However, several techniques for reducing this "reality gap"-problem, by adding noise at different levels of the simulation, have been proposed [5] [6]. With this in mind the simulator was changed in the following way: Sensor noise levels were increased from 5% to 10%.…”