• Rural Digital Europe
• Part of book or chapter of book close

One of the ultimate dream in robotics is to create lifelike robotics systems, such as humanoid robot and animal-like legged robot. We choose to build pet-type legged robot because we believe that doglike and cat-like legged robot has major potential for future entertainment robotics markets for personal robots. However, numbers of challenges exists before any of such robot to be fielded in the real world. Robots have to be reasonably intelligent, maintains certain level of agility, and be able to engaged in some collaborative behaviours. RoboCup is an ideal challenge to foster robotics technologies for small personal and mobile robotics system. This paper, we present Sony's legged robots system which enter RoboCup-98 Paris as a special exhibition games.

Proposes a reinforcement learning architecture that allows an autonomous robot to acquire efficient navigation strategies in a few trials. Besides fast learning, the architecture has 3 further appealing features. (1) Since it learns from built-in reflexes, the robot is operational from the very beginning. (2) The robot improves its performance incrementally as it interacts with an initially unknown environment, and it ends up learning to avoid collisions even if its sensors cannot detect the obstacles. This is a definite advantage over non-learning reactive robots. (3) The robot exhibits high tolerance to noisy sensory data and good generalization abilities. All these features make this learning robot's architecture very well suited to real-world applications. The authors report experimental results obtained with a real mobile robot in an indoor environment that demonstrate the feasibility of this approach. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1994, Múnich (Alemania) Peer Reviewed

Social robots are receiving much interest in the robotics community. The most important goal for such robots lies in their interaction capabilities. An attention system is crucial, both as a filter to center the robot’s perceptual resources and as a mean of letting the observer know that the robot has intentionality. In this paper a simple but flexible and functional attentional model is described. The model, which has been implemented in an interactive robot currently under development, fuses both visual and auditive information extracted from the robot’s environment, and can incorporate knowledge-based influences on attention.

Robot games have been proposed as a way to motivate people to do physical exercises while playing. Although this area is very new, both commercial and scientific robot games have been developed mainly based on interaction with a single user and a robot. The goal of this paper is to describe a generic software framework which can be used to create games where multiple players can play against a mobile robot. The paper shows how an adaptive AI system (D2) developed for real-time strategy (RTS) computer games can be successfully applied in a robotics context using the robotics control framework Player/Stage. D2 is based on Case-Based Planning which learns from demonstration. Using the proposed framework, the paper shows how a robot learns a strategy for an implementation of a simple game.

The controlling mechanism of a typical mobile robot is usually a computer system either remotely positioned or in-body. Recent research is on-going in which biological neurons are grown and trained to act as the brain of an interactive real-world robot - thereby acting as instinctive computing elements. Studying such a system provides insights into the operation of biological neural structures; therefore, such research has immediate medical implications as well as enormous potential in computing and robotics. A system involving closed-loop control of a mobile robot by a culture of neurons has been created. This article provides an overview of the problem area, gives an idea of the breadth of present ongoing research, details our own system architecture and, in particular, reports on the results of experiments with real-life robots. The authors see this as a new form of artificial intelligence.

Designing robots that learn by themselves to perform complex real-world tasks is a still-open challenge for the field of robotics and artificial intelligence. In this paper the author presents the robot learning problem as a lifelong problem, in which a robot faces a collection of tasks over its entire lifetime. Such a scenario provides the opportunity to gather general-purpose knowledge that transfers across tasks. The author illustrates a particular leaning mechanism, explanation-based neural network learning, that transfers knowledge between related tasks via neural network action models. The learning approach is illustrated using a mobile robot, equipped with visual, ultrasonic and laser sensors. In less than 10 minutes operation time, the robot is able to learn to navigate to a marked target object in a natural office environment. >

A robotic agent experiences a world of continuous multivariate sensations and chooses its actions from continuous action spaces. Unless the agent is able to successfully partition these into functionally similar classes, its ability to interact with the world will be extremely limited. We present a method whereby an unsupervised robotic agent learns to discriminate discrete actions out of its continuous action parameters. These actions are discriminated because they lead to qualitatively distinct outcomes in the robot's sensor space. Once found, these actions can be used by the robot as primitives for further exploration of its world. We present results gathered using a Pioneer 1 mobile robot.