This work addresses the real time control of the Khepera mobile robot [1] navigation in a maze with reflector walls. Boolean Neural Networks such as RAM [2] and GSN [3] models are applied to drive the vehicle, following a light source, while avoiding obstacles. Both neural networks are implemented with simple logic and arithmetic functions (NOT, AND, OR, Addition, and Comparison), aiming to imp...

We have used an automatic programming method called Genetic Programming (GP) for control of a miniature robot. Our earlier work on real-time learning su ered from the drawback of the learning time being limited by the response dynamics of the robot's environment. In order to overcome this problem we have devised a new technique which allows learning from past experiences that are stored in memo...

The performances of an EKF-based SLAM approach are experimentally discussed in the case of a mini-robot equipped with low-cost IR sensors only, showing that despite of the sparseness and noisiness of the sensors, SLAM experiments using classical SLAM methods can be performed even on a Khepera robot in a real arena, whose dimensions may be significantly larger than the robot size. The main chara...

Robot design complexity is increasing day by day especially in automated industries. In this paper we propose biologically inspired design framework for robots in dynamic world on the basis of Co-Evolution, Virtual Ecology, Life time learning which are derived from biological creatures. We have created a virtual khepera robot in Framsticks and tested its operational credibility in terms hardwar...

We have developed a neuro-robot-hybrid system using a living neuronal network and a miniature moving robot. The living network of rat hippocampal neurons can distinguish patterns of action potentials evoked by different inputs, suggesting that a cultured neuronal network can represent particular states as symbols. We used a Khepera II robot and a robot made using a LEGO mindstorm NXT kit to int...

This paper presents preliminary results of an experimental study that intends to find the best chemical volatiles to mark odourific trails with mobile robots. The characteristics of the chemicals chosen for this purpose is presented and the influence of the substrate permeability on the ability to detect those chemicals along the time is analysed. The detection of a chemical trail by a Khepera ...

The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. To overcome this problem, new basis functions called geo...

Behaviors such as exploration and homing, that seemingly demand a complex control system, only require a perceptron that connects a robot’s sensors to its motors. This is shown by evolving such neurocontrollers for the Khepera robot. An exploitation of the robot’s perception of the environment’s geometrical shape allows the robot to encode time, even though explicitly it is not presented with t...

Two computationally simple forms of dead reckoning were implemented in a physical robot (Khepera). The precision of homing was compared between both strategies for various environments in which obstacles were distributed in four different ways: regular, at random, clumped, and with walls. Counter intuitively, the computational more complex strategy did not perform better in general. Both strate...

The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on ...