We investigate whether a swarm of robots can evolve controllers that cause aggregation into ‘multi-cellular’ robot organisms without a specific reward to do so. To this end, we create a world where ...aggregated robots receive more energy than individual ones and enable robots to evolve their controllers on-the-fly, during their lifetime. We perform experiments in six different implementations of the basic idea distinguished by the system of energy distribution and the level of advantage aggregated robots have over individual ones. The results show that ‘multi-cellular’ robot organisms emerge in all of these cases.
We present a practical application of sensorimotor self- simulation for a mobile robot. Using its self-simulation, the robot can reason about its ability to perform tasks, despite having no model of ...many of its internal processes and thus no way to create an a priori configuration space in which to search. We suggest that this in-the-head rehearsal of tasks is particularly useful when the tasks carry a high risk of robot “death”, as it provides a source of negative feedback in perfect safety. This approach is a useful complement to existing work using forward models for anticipatory behaviour. A minimal system is shown to be effective in simulation and real-world experiments. The virtues and limitations of the approach are discussed and future work suggested.
This paper reports on a feasibility study into the evolution of robot controllers during the actual operation of robots (on-line), using only the computational resources within the robots themselves ...(on-board). We identify the main challenges that these restrictions imply and propose mechanisms to handle them. The resulting algorithm is evaluated in a hybrid system, using the actual robots’ processors interfaced with a simulator that represents the environment. The results show that the proposed algorithm is indeed feasible and the particular problems we encountered during this study give hints for further research.
Rat’s Life: A Cognitive Robotics Benchmark Michel, Olivier; Rohrer, Fabien; Bourquin, Yvan
European Robotics Symposium 2008,
01/2008, Letnik:
44
Book Chapter, Journal Article
Recenzirano
This paper describes Rat’s Life: a complete cognitive robotics benchmark that was carefully designed to be easily reproducible in a research lab with limited resources. It relies on two e-puck ...robots, some LEGO bricks and the Webots robot simulation software. This benchmark is a survival game where two robots compete against each other for resources in an unknown maze. Like the rats in cognitive animal experimentation, the e-puck robots look for feeders which allow them to live longer than their opponent. Once a feeder is reached by a robot, the robot draws energy from it and the feeder becomes unavailable for a while. Hence, the robot has to further explore the maze, searching for other feeders while remembering the way back to the first ones. This allows them to be able to refuel easily again and again and hopefully live longer than their opponent. ...
One of the grand challenges in self-configurable robotics is to enable robots to change their configuration, autonomously, and in parallel, depending on changes in the environment. In this paper we ...investigate, in simulation, if this is possible through evolutionary algorithms (EA). To this end, we implement an unconventional on-line, on-board EA that works inside the robots, adapting their controllers to a given environment on-line. This adaptive robot swarm is then exposed to changing circumstances that require that robots aggregate into “organisms” or dis-aggregate into swarm mode again to improve their fitness. The experimental results clearly demonstrate that this EA is capable of adapting the system in real time, without human intervention.
Traditional agriculture has been the global Abstract- This paper presents a SLAM (Simultaneous localisation and mapping) using an E-puck robot in Webots software. The area of autonomous mobile robots ...has recently piqued numerous researchers' interest. Due to the unique requirements of many applications of mobile robot systems, particularly in the area of localisation, robot mapping and line following have become the backbone of directing robots in an unfamiliar environment. A theoretical basis for SLAM and occupancy grids, which are employed in this work to build maps, is provided in this paper. The E-Puck robot is utilised in this project, and the simulation is done in the Webots program using Python. The E-Puck robot was successfully programmed and controlled in this experiment to locate and map an unknownarea. To cope with the uncertainty of robot posture in SLAM and self-localisation during navigation, we employ the ExtendedKalman filter (EKF). The mapping (occupancy grid) has been completed, and the robot may now travel through the surroundings using it. Using simulation results, we demonstratethat the robot system can find itself, construct an environment map, and navigate (teleoperation) in the environments.
A distributed simulation environment is introduced in this paper that allows to simulate robot swarms as well as modular robots. This simulator is in use within the European projects ’SYMBRION’ and ...’REPLICATOR’. The project’s main goal is to build robots that can aggregate to multi-robot organisms. These robots will be able to act individually, as a swarm or within an organism. The simulator needs to be able to simulate all of these behaviors. As the number of robots can be large, both in the swarm as well as in the organism, the simulator needs to be distributed on several computers. As the demand varies between the different behaviors –swarm and organism behavior– the behavior of the simulator needs to vary as well, e.g. for a swarm, a dynamic simulation is not necessary, whereas for an organism, a fast dynamic simulation is obligatory. We are therefore developing the Symbricator3D simulation environment, that will fulfill all the described requirements.
Previous work has shown that robot navigation systems that employ an architecture based upon the idiotypic network theory of the immune system have an advantage over control techniques that rely on ...reinforcement learning only. This is thought to be a result of intelligent behaviour selection on the part of the idiotypic robot. In this paper an attempt is made to imitate idiotypic dynamics by creating controllers that use reinforcement with a number of different probabilistic schemes to select robot behaviour. The aims are to show that the idiotypic system is not merely performing some kind of periodic random behaviour selection, and to try to gain further insight into the processes that govern the idiotypic mechanism. Trials are carried out using simulated Pioneer robots that undertake navigation exercises. Results show that a scheme that boosts the probability of selecting highly-ranked alternative behaviours to 50% during stall conditions comes closest to achieving the properties of the idiotypic system, but remains unable to match it in terms of all round performance.
Evolutionary robotics uses evolutionary computation to optimize physically embodied agents. We present here a framework for performing off-line evolution of a pluripotent robot controller that ...manages to form multicellular robotic organisms from a swarm of autonomously moving small robot modules. We describe our evolutionary framework, show first results and discuss the advantages and disadvantages of our off-line evolution approach. In detail, we explain the single parts of the framework and a novel homeostatic hormone-based controller, which is shaped by artificial evolution to control both, the non-aggregated single robotic modules and the joined high-level robotic organisms. As a first step we present results of this evolutionary shaped controller showing the potential for different motion behaviours.