Biologically inspired learning system (original) (raw)

Learning for intelligent mobile robots

2003

Unlike intelligent industrial robots which often work in a structured factory setting, intelligent mobile robots must often operate in an unstructured environment cluttered with obstacles and with many possible action paths. However, such machines have many potential applications in medicine, defense, industry and even the home that make their study important. Sensors such as vision are needed. However, in many applications some form of learning is also required. The purpose of this paper is to present a discussion of recent technical advances in learning for intelligent mobile robots.

The use of Artificial Intelligence in autonomous mobile robots

As far as I can remember I have always been fascinated about space. When I saw a documentary about the Russian moon many years ago, I realized that robots are great tools for space exploration. They can be operated from the earth without any risk to humans, or travel through space autonomously. It was then that I became interested in robotics and my curiosity about the subject would grow with the years. The android Data from the television sci-fi Star Trek, an article about the robot Genghis that learnt itself to walk, a documentary about Luc Steels' robot experiments, and especially the deployment of the rover Sojourner on Mars, they all contributed to my interest in robotics. An obligatory part of the computer science Master's program of the Delft University of Technology (DUT) is the research project, usually done in the fourth or fifth year. The main goal of this project is to gain experience in research. Since there is no course on intelligent robotics at the DUT, this was the perfect opportunity for me to learn more about robotics and Artificial intelligence. To get acquainted with the subject, I decided to start by reading some books and articles that gave a general overview of the field. The results can be found in the first part of this report. The first books and articles I read mentioned Rodney Brooks and his subsumption robot architecture quite often. When I did further research on this topic I discovered the interesting subfield of behavior-based robotics, described in the second part in this report. The third part deals with a fairly new subject called evolutionary robotics that allowed me to combine robotics with another interest of mine, which is genetic algorithms. During my search for information on robots I found that many papers on robots can be found on the World Wide Web. The sites and pages I used in my research are included in the appendix at the end of the report. I would like to thank everyone who helped me with my research, especially Leon Rothkrantz for his supervision and guidance during this project.

Adaptive behavior-based control for robot navigation: A multi-robot case study

2013 XXIV International Conference on Information, Communication and Automation Technologies (ICAT), 2013

The main focus of the work presented in this paper is to investigate the application of certain biologically-inspired control strategies in the field of autonomous mobile robots, with particular emphasis on multi-robot navigation systems. The control architecture used in this work is based on the behavior-based approach. The main argument in favor of this approach is its impressive and rapid practical success. This powerful methodology has demonstrated simplicity, parallelism, perception-action mapping and real implementation. When a group of autonomous mobile robots needs to achieve a goal operating in complex dynamic environments, such a task involves high computational complexity and a large volume of data needed for continuous monitoring of internal states and the external environment. Most autonomous mobile robots have limited capabilities in computation power or energy sources with limited capability, such as batteries. Therefore, it becomes necessary to build additional mechanisms on top of the control architecture able to efficiently allocate resources for enhancing the performance of an autonomous mobile robot. For this purpose, it is necessary to build an adaptive behavior-based control system focused on sensory adaptation. This adaptive property will assure efficient use of robot's limited sensorial and cognitive resources. The proposed adaptive behavior-based control system is then validated through simulation in a multi-robot environment with a task of prey/predator scenario.

Fuzzy Rule Based Neuro-Dynamic Programming for Mobile Robot Skill

Biologically inspired architectures that mimic the organizational structure of living organisms and in general frameworks that will improve the design of intelligent robots attract significant attention from the research community. Selforganization problems, intrinsic behaviors as well as effective learning and skill transfer processes in the context of robotic systems have been significantly investigated by researchers. Our work presents a new framework of developmental skill learning process by introducing a hierarchical nested multiagent architecture. A neuro-dynamic learning mechanism employing function approximators in a fuzzified state-space is utilized, leading to a collaborative control scheme among the distributed agents engaged in a continuous space, which enables the multi-agent system to learn, over a period of time, how to perform sequences of continuous actions in a cooperative manner without any prior task model. The agents comprising the system manage to gain experience over the task that they collaboratively perform by continuously exploring and exploiting their state-to-action mapping space. For the specific problem setting, the proposed theoretical framework is employed in the case of two simulated e-Puck robots performing a collaborative box-pushing task. This task involves active cooperation between the robots in order to jointly push an object on a plane to a specified goal location. We should note that 1) there are no contact points specified for the two e-Pucks and 2) the shape of the object is indifferent. The actuated wheels of the mobile robots are considered as the independent agents that have to build up cooperative skills over time, in order for the robot to demonstrate intelligent behavior. Our goal in this experimental study is to evaluate both the proposed hierarchical multi-agent architecture, as well as the methodological control framework. Such a hierarchical multi-agent approach is envisioned to be highly scalable for the control of complex biologically inspired robot locomotion systems.

Reinforcement learning-based group navigation approach for multiple autonomous robotic systems

Advanced Robotics, 2006

In several complex applications, the use of multiple autonomous robotic systems (ARS) becomes necessary to achieve different tasks, such as foraging and transport of heavy and large objects, with less cost and more efficiency. They have to achieve a high level of flexibility, adaptability and efficiency in real environments. In this paper, a reinforcement learning (RL)-based group navigation approach for multiple ARS is suggested. Indeed, the robots must have the ability to form geometric figures and navigate without collisions while maintaining the formation. Thus, each robot must learn how to take its place in the formation, and avoid obstacles and other ARS from its interaction with the environment. This approach must provide ARS with the capability to acquire the group navigation approach among several ARS from elementary behaviors by learning with trialand-error search. Then, simulation results display the ability of the suggested approach to provide ARS with capability to navigate in a group formation in dynamic environments. With its cooperative behavior, this approach makes ARS able to work together to successfully fulfill the desired task.

Development of control algorithms for a self-learning mobile robot

2007

Autonomous learning robots have the advantage over manually programmed robots in that they are able to adapt to varying conditions, both internal to the robot (e.g., energy levels) as well as external environmental conditions (e.g. obstacles, light). In this project, there were analized the possibilities to implement a robot that learns how avoid obstacle using online self-adaptation. Initially it was sudied and implemented a robot that explores an unknown path, using touch sensors and an obstacol detector to find its way during the exploration. Finally it was implemented a genetic algorithm on the robot and experimented with using genetic algorithm as a form of robot learning. The robot was built using the Lego RCX.

Reinforcement learning based group navigation approach for multiple autonomous robotic system

Journal of Computer and System Sciences, 2005

In several complex applications, the use of multiple autonomous robotic systems (ARS) becomes necessary to achieve different tasks such as foraging and transport of heavy and large objects with less cost and more efficiency. They have to achieve a high level of flexibility, adaptability and efficiency in real environments. In this paper, a reinforcement learning (RL) based group navigation approach for multiple ARS is suggested. Indeed, the robots must have the ability to form geometric figures and navigate without collisions while maintaining the formation. Thus, each robot must learn how to take its place in the formation and avoid obstacles and other ARS from its interaction with the environment. This approach must provide ARS with capability to acquire the group navigation approach among several ARS from elementary behaviors by learning with trial and error search. Then, simulation results display the ability of the suggested approach to provide ARS with capability to navigate in a group formation in dynamic environments.