Conception de structures neuronales pour le contrôle de robots mobiles autonomes

There is a large number of possible applications in the field of mobile robotics: Mail delivery robots, domestic or industrial vacuum cleaners, surveillance robots, demining robots and many others could be very interesting products. Despite this potential market and the actual technology, only few simple systems are commercially available. This proves that there are several important and problematic issues in this field, mainly at the intelligence level. As a reaction to the failure of the classical artificial intelligence applied to the field of mobile robotics, several new approaches have been proposed. Artificial neural networks are one of these, and genetic algorithms, supported by the Artificial Life trend, are also getting more and more consideration. These two techniques have already been applied to mobile robotics, but mainly in simulation, and without a final test on a real mobile robot. The use of physical robots for this research seems to be still problematic due to the lack of efficient tools. Several neural structures for the control of mobile robots have been analysed in this work. All experiences have been carried out on physical robots. To reach this goal, an important effort has been made in order to design new efficient robotic tools. Together with Edo Franzi, André Guignard and Yves Cheneval, we have developed and built hardware and software tools that make an efficient research work possible. Along with several analysis software tools, the mobile robot Khepera has been a result of this development. Using this equipment, six experiences have been carried out, covering a large spectrum of the possible ways neural networks can be used for the control of mobile robots. These experiments have nevertheless been restricted to simple behaviours and small neural networks. The first two experiments show, with a very simple and manually adjusted behaviour, the important role of the interaction of the robot with its environment. The first experiment is based on a collective behaviour, the second on a collaborative one. The adaptation of the robot to the environment is introduced in the third experiment, in which a learning technique is applied. The result is a robot able to learn how to use visual stimuli to avoid particular obstacles. Despite its interesting results, this approach has turned out to be very limited, due to the rigid structure needed. The last three experiments demonstrate the possibilities of the use of genetic algorithms, which proved to be a very flexible adaptation mechanism. The first of these three experiments tests the feasibility of this approach. The second one takes advantage of the characteristics of genetic algorithms to achieve more complex behaviours. Finally, genetic algorithms and learning techniques are associated in the last experiment, showing a high adaptive structure. An important effort has been made to show both advantages and disadvantages of each technique, in order to provide the necessary elements for the continuation of this research activity.

Evolutionary Robotics. The Biology, Intelligence, and Technology of Self-organizing Machines

Dario Floreano

Evolutionary robotics is a new technique for the automatic creation of autonomous robots. Inspired by the Darwinian principle of selective reproduction of the fittest, it views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention. Drawing heavily on biology and ethology, it uses the tools of neural networks, genetic algorithms, dynamic systems, and biomorphic engineering. The resulting robots share with simple biological systems the characteristics of robustness, simplicity, small size, flexibility, and modularity. In evolutionary robotics, an initial population of artificial chromosomes, each encoding the control system of a robot, is randomly created and put into the environment. Each robot is then free to act (move, look around, manipulate) according to its genetically specified controller while its performance on various tasks is automatically evaluated. The fittest robots then "reproduce" by swapping parts of their genetic material with small random mutations. The process is repeated until the "birth" of a robot that satisfies the performance criteria. This book describes the basic concepts and methodologies of evolutionary robotics and the results achieved so far. An important feature is the clear presentation of a set of empirical experiments of increasing complexity. Software with a graphic interface, freely available on a Web page, will allow the reader to replicate and vary (in simulation and on real robots) most of the experiments.

MIT Press2001

Synthesis, modeling, and experimental validation of distributed robotic search

James Pugh

The work of this thesis centers around the research subject of distributed robotic search. Within the field of distributed robotic systems, a task of particular interest is attempting to locate one or more targets in a possibly unknown environment. While numerous studies have proposed and analyzed methods to accomplish this, there is currently a lack of a strong foundation of tools and techniques that can be used to facilitate the development and evaluation of different approaches to distributed robotic search. In this work, we aim to provide such a foundation through tools, methods, models, and analysis of experimentation. An often overlooked aspect of the distributed robotic research process is the development and analysis of tools and modules to be used with robotic systems. These may include plug-ins for realistic robotic simulators, software/hardware systems to track multiple mobile robots in real-time, extension boards for robotic platforms, and the robots themselves. Along with other tools developed and used for this work, we focus particularly on the development, characterization, and validation of a fast, accurate on-board system for relative positioning and communication between robots, a capability which is critical for effective distributed robotic search. Designing individual robot controllers to generate a specific group behavior is a difficult and often counter-intuitive process. A possible alternative to hand-crafting distributed search controllers is automatic synthesis using machine-learning techniques. We explore the effectiveness of using a noise-resistant version of the Particle Swarm Optimization algorithm to optimize the weights of an embedded Artificial Neural Network, allowing the robot to learn obstacle avoidance behavior (a common benchmark for robotic learning techniques); we find that this technique appears to offer superior performance as compared to the canonical approach of using Genetic Algorithms for this type of learning. A method for faster learning using distributed evaluation in a robot team is tested and is found to offer comparable performance using only a fraction of the original learning time. This technique can be used for fast, effective learning and adaptation in a distributed robotic system performing search. The process of designing and analyzing algorithms for distributed robotic systems can be greatly facilitated if models are available to describe the dynamics of the algorithm at an abstract level. Inspired by previous examples in the distributed robotic field, we work to design a model of robotic search that captures the system at different levels of abstraction, ranging from accurately recreating the details of individual robots to describing the entire system as an indivisible whole. To capture the entire search process, we model both the exploration phase, where robots cover an environment in an effort to detect traces of targets, and the localization phase, where robots use target emission sensing to navigate towards the target. The utility of our models is demonstrated by using them to develop an effective technique for the declaration phase of search, where robots decide that a target has been accurately localized and announce its position. In distributed robotics research, it is important that techniques developed with abstracted simulations and models are ultimately validated using real robotic platforms in order to verify their correctness. In that spirit, we run systematic sound search experiments using teams of up to ten real robots. These experiments utilize the tools developed throughout the research process, demonstrate the utility of our learning technique for fast search adaptation, and serve to validate our models of distributed robotic localization. In addition, they allow us to analyze and better understand the subtle dynamics of the search process, providing information which should be useful for any future work on distributed robotic search.

EPFL2008

Shoaling with fish: using miniature robotic agents to close the interaction loop with groups of zebrafish Danio rerio

Frank Bonnet

Robotic animals are nowadays developed for various types of research, such as bio-inspired robotics, biomimetics and animal behavior studies. The miniaturization of technologies and the increase in performance of embedded systems allowed engineers to develop more powerful, sophisticated and miniature devices. The case of robotic fish is a typical example of such challenging design: the fish locomotion and body movements are difficult to reproduce and the device has to move autonomously underwater. More specifically, in the case of collective animal behavior research, the robotic device has to interact with animals by generating and exploiting signals relevant for social behavior. Once perceived by the animal society as conspecific, these robots can become powerful tools to study the animal behaviors, as they can at the same time monitor the changes in behavior and influence the collective choices of the animal society. In this work, we present novel robotized tools that can integrate shoals of fish in order to study their collective behaviors. This robotic platform is composed of two subsystems: a miniature wheeled mobile robot that can achieve dynamic movements and multi-robot long-duration experiments, and a robotic fish lure that is able to beat its tail to generate fish-like body movements. The two subsystems are coupled with magnets which allows the wheeled mobile robot to steer the robotic fish lure so that it reaches very high speeds and accelerations while achieving shoaling. An experimental setup to conduct studies on mixed societies of artificial and living fish was designed to facilitate the experiments for biologists. A software framework was also implemented to control the robots in a closed-loop using data extracted from visual tracking that retrieved the position of the robots and the fish. We selected the zebrafish Danio rerio as a model to perform experiments to qualify our system. We used the current state of the art on the zebrafish social behavior to define the specifications of the robots, and we performed stimuli analysis to improve their developments. Bio-inspired controllers were designed based on data extracted from experiments with zebrafish for the robots to mimic the zebrafish locomotion underwater. Experiments involving a robot with a shoal of fish in a constrained environment showed that the locomotion of the robot was one of the main factor to affect the collective behavior of zebrafish. We also shown that the body movements and the biomimetic appearance of the lure could increase its acceptance by fish. Finally, an experiment involving a mixed society of fish and robots qualified the robotic system to be integrated among a zebrafish shoal and to be able to influence the collective decisions of the fish. These results are very promising for the field of fish-robot interaction studies, as we showed the effect of the robots in long-duration experiments and repetitively, with the same order of response from the animals.