Automatically Designing Robot Controllers and Sensor Morphology with Genetic Programming

Abstract

Abstract. Genetic programming provides an automated design strategy to evolve complex controllers based on evolution in nature. In this contribution we use genetic programming to automatically evolve efficient robot controllers for a corridor following task. Based on tests executed in a simulation environment we show that very robust and efficient controllers can be obtained. Also, we stress that it is important to provide sufficiently diverse fitness cases, offering a sound basis for learning more complex behaviour. The evolved controller is successfully applied to real environments as well. Finally, controller and sensor morphology are co-evolved, clearly resulting in an improved sensor configuration.

Learning fuzzy controllers in mobile robotics with embedded preprocessing

“…• ν-Support Vector Regression (ν-SVR) 4 : a ν-SVM [36] version for regression with a Gaussian RBF kernel. The parameter sigma is estimated based upon the 0.1 and 0.9 quantile of ||x − x || 2 .…”

“…The learning of controllers for autonomous robots has been dealt with by using different machine learning techniques. Among the most popular approaches can be found evolutionary algorithms [4,5], neural networks [6] and reinforcement learning [7,8]. Also hibridations of them, like evolutionary neural networks [9], reinforcement learning with evolutionary algorithms [10,11], the widely used genetic fuzzy systems [12,13,14,15,16,17,18], or even more uncommon combinations like ant colony optimization with reinforcement learning [19] or differential evolution [20] or evolutionary group based particle swarm optimization [21] have been successfully applied.…”

“…In [7], this issue has been managed from the reinforcement learning perspective, by using a probability density estimation of the joint space of states. Among all the approaches based on evolutionary algorithms, only in [4] no expert knowledge has been taken into account. In this work, the number of sensors and their position are learned from a reduced number of sensors.…”

“…The implementation in Keel[32], an open source (GPLv3) Java software tool to assess evolutionary algorithms for Data Mining problems, was used 3. The package nnet[34] of the statistical software R was used 4. The package kernlab[35] of the statistical software R was used.…”