Behavior-oriented AI is a scientific discipline that studies how behavior of agents emerges and becomes intelligent and adaptive. Success of the field is defined in terms of success in building physical agents that are capable of maximising their own self-preservation in interaction with a dynamically changing environment. The paper addresses this artificial life route towards artificial intelligence and reviews some of the results obtained so far. 1 Official reference: Steels, L. (1994) The artificial life roots of artificial intelligence. Artificial Life Journal, Vol 1,1. MIT Press, Cambridge. 1 Introduction For several decades, the field of Artificial Intelligence has been pursuing the study of intelligent behavior using the methodology of the artificial [104]. But the focus of this field, and hence the successes, have mostly been on higher order cognitive activities such as expert problem solving. The inspiration for AI theories has mostly come from logic and the cognitive...

Active cameras provide a navigating vehicle with the ability to fixate and track features over extended periods of time, and wide fields of view. While it is relatively straightforward to apply fixating vision to tactical, short-term navigation tasks, using serial fixation on a succession of features to provide global information for strategic navigation is more involved. However, active vision is seemingly well-suited to this task: the ability to measure features over such a wide range means that the same ones can be used as a robot makes a wide range of movements. This has advantages for map-building and localisation. The core work of this thesis concerns simultaneous localisation and map-building for a robot with a stereo active head, operating in an unknown environment and using point features in the world as visual landmarks. Importance has been attached to producing maps which are useful for extended periods of navigation. Many map-building methods fail on extended runs because ...

A taxonomy is described that relates different navigational behaviours in a hierarchical and compositional way. Elementary navigation tactics are combined to tactical navigation in routes; landmarks in space are contrasted to routemarks in networks of passages. Survey knowledge comes in at the level of strategic navigation. The Bremen Autonomous Wheelchair is then presented as a vehicle for experimentation in robotics, both to model biologically plausible navigational behaviours and to develop efficient navigational mechanisms for a technical application. The implementation on the autonomous system is based on the use of basic behaviours and the identification of routemarks. The actual recognition of artificial routemarks is described and early results of the current work on the identification of natural 3D-marks are presented. 1

A self-organising controller for mobile robots is presented that allows robots to acquire sensor-motor competences autonomously, and thus adapt to changes in the environment, the task, or the robot itself, without external supervision and feedback. Using artificial neural networks, the robot acquires these fundamental sensor-motor competences rapidly, in a couple of learning steps, taking a few tens of seconds. Results of experiments with a number of mobile robots are presented, both by us and by other research groups, using the same controller architecture. 1 c flU. Nehmzow, 1994 1 1 Introduction As mobile robot technology advances and sophisticated mobile robots become widely available, at comparably low cost --- the Nomad 200 robot described in section 4.1 of this paper being one example --- the question of how to control such robots intelligently has become more interesting, both from a research and an industrial point of view. Intelligent control here means that the r...

The ability to acquire a representation of the spatial environment and the ability to localize within it are essential for successful navigation in a-priori unknown environments. The hippocampal formation is believed to play a key role in spatial learning and navigation in animals. This paper briefly reviews the relevant neurobiological and cognitive data and their relation to computational models of spatial learning and localization used in mobile robots. It also describes a hippocampal model of spatial learning and navigation and analyzes it using Kalman filter based tools for information fusion from multiple uncertain sources. The resulting model allows a robot to learn a place-based, metric representation of space in a-priori unknown environments and to localize itself in a stochastically optimal manner. The paper also describes an algorithmic implementation of the model and results of several experiments that demonstrate its capabilities.

This paper describes how an animat endowed with the MonaLysa control architecture can build a cognitive map that merges into a hierarchical framework not only topological links between landmarks, but also higher-level structures, control information, and metric distances and orientations. The paper also describes how the animat can use such a map to locate itself, even if it is endowed with noisy dead-reckoning capacities. MonaLysa's mapping and self-positioning capacities are illustrated by results obtained in three different environments and four noise-level conditions. These capacities appear to be gracefully degraded when the environment grows more challenging and when the noise level increases. In the discussion, the current approach is compared to others with similar objectives, and directions for future work are outlined. Keywords Hierarchical map. Topological information. Metric information. Landmarks. Self-positioning. Dead-reckoning. Robustness to noise. 1 Introduction In...

This paper describes how the MonaLysa control architecture implements a route-following navigation strategy. Two procedures that allow map building and self-positioning are described, and experimental results are provided that demonstrate that such procedures are robust with respect to noise. This approach is compared to others with similar objectives, and directions for future work are outlined. 1 Introduction In robotics or animat research, traditional navigation methods that use internal geometrical representations of the environment (Latombe, 1991) are confronted with various implementation difficulties, due to memory and time requirements, as well as sensory and motor errors (Nehmzow, 1995). To overcome these difficulties, several researchers (Chatila and Laumond, 1985; Kuipers and Byun, 1991; Mataric, 1992; Nehmzow, 1995) have advocated the use of various types of topological models to represent the connectivity of the environment, and several such models have been devised that...

This paper addresses the problem of localisation in autonomous mobile robot navigation, i.e., the task of identifying places after prior exploration and mapbuilding by the robot. In particular, the work is concerned with the more general problem of relocalisation without using past experience (i.e., knowing roughly where you are to start with), referred to here as the lost robot problem. In the experiments presented here, the robot had to relocalise after being moved to a randomly chosen location, its sensors being disabled during that move. The robot therefore had no a priori knowledge of its position, and had to use current sensory perceptions and map knowledge alone to relocalise. A perception-based localisation method is presented which is resilient to the problem of perceptual aliasing (i.e., perceptual identity of distinct locations), and is capable of relocalising even in environments where no single place has a unique perceptual signature. During an exploration phase, ...

We study and contrast particular issues arising in two social learning paradigms that are widely used in robotics research: (i) following or matched-dependent behaviour and (ii) static observational learning. Experiments are carried out with physical Khepera robots whose controllers include motor schemas and new neural network based methods for model agent-centred perception of angle and distance. The robots are trained to perceive the dynamic movement of a human or robot demonstrator carrying a light source. The robots learn the behaviour either through perception from a static location or while following. The differences and implications of the results of both the following and observation mechanisms are compared and contrasted.

There are different approaches to mobile robot navigation. Landmark-based localization has shown to be the alternative to simple dead-reckoning, but often landmarks are environmental specific, and recognition algorithms are computationally very expensive. This paper presents an approach to landmark-based navigation using emergency exit pannels and corridors as cues, without odometric information. Experiments are carried out to verify appart each landmark identification subsystem and both behaviors are combined together in a complete path through the environment.