|SAIS-SSLS 2003 Joint Workshop||April 10-11, 2003 - University or Örebro, Sweden|
Abstract: We investigate the interaction between
implicit and explicit processes in skill learning (e.g., embodies skills
versus declarative knowledge), and on that basis, develop computational
cognitive architectures (general models of cognition). We explore
various effects of the interaction between the two types of processes in
terms of improving (or hampering) learning. In particular, we focus on
a bottom-up approach (first learning implicit knowledge and then
explicit knowledge on its basis).
Thus far, we have been developing a computational architecture, CLARION, for capturing a wide range of quantitative human performance data related to the interaction. We are also carrying out human experiments to generate new data that further explicate the interaction between implicit and explicit cognitive processes.
Abstract: We will share positive and negative experiences from several commercialisation attempts of about a dozen AI ideas/companies in Sweden. Our talk includes hints on how to attract and handle venture capital. We will discuss experiences from science parks, incubators as well as "Soft (public) Money". Other topics will be how to act in different investor climates, bubbles and crashes as well as how commercialisation may affect your research.
Abstract: The goal of the artificial hand project is to develop new strategies for motor control of functional hand prostheses based on electrical signals generated from multiple muscle electrodes or microchips implanted in the peripheral or central nervous system. The project is multidisciplinary and involves several subprojects ranging from the study of nerve regeneration to the design of implanted silicon sieve electrodes. Artificial neural networks are used to categorize patterns of EMG signals and to produce sequences of motor commands that that can control a prosthesis. Today, the system has been tested on several patients that are able to control a virtual hand on a computer screen after a short training period. An artificial demonstrator hand has also been developed Another goal is to develop systems for artificial sensibility to be applied to such hand prostheses and to patients with loss of sensory nerve function. The overall goal is to create new possibilities for rehabilitation of amputees and paralysed patients.
Abstract: In this overview talk, I will propose a personal view on the development of the field of intelligent robotics from its initial conception to the present days, and point out some fundamental difficulties that made the creation of intelligent robots a much more challenging task than it was originally anticipated. The view proposed in this talk is that these challenges caused the field of (mobile) robotics and the field of artificial intelligence to split at an early stage, and to progress pretty much in isolation until the last decade. I will then outline the current approaches to integrate the results achieved in these two fields. I will conclude the talk by suggesting some "hot" research topics in the field of intelligent robots.
Abstract: A recent trend in evolutionary robotics and artificial life research is to maximize self-organization in the design of robotic systems, in particular using artificial evolutionary techniques, in order to reduce the human designer bias. This dissertation presents experiments in competitive co-evolutionary robotics that integrate and extend previous work on competitive co-evolution of neural robot controllers in a predator-prey scenario with work on the co-evolution of robot morphology and control systems. The focus here is on a systematic investigation of tradeoffs and interdependencies between morphological parameters and behavioral strategies through a series of predator-prey experiments in which increasingly many aspects are subject to self-organization through competitive co-evolution. The results show that there is a strong interdependency between morphological parameters and behavioral strategies evolved, and that the competitive co-evolutionary process was able to find a balance between and within these two aspects. It is therefore concluded that competitive co-evolution has great potential as a method for the automatic design of robotic systems.
Winner of the SAIS best Master's Thesis prize with the following motivation:
For a systematic investigation of tradeoffs and interdependencies between morphological parameters and behavioral strategies through a series of predator-prey experiments, in which increasingly many aspects are subject to self-organization, through competitive co-evolution. Resulting in integrating and extending previous work on competitive co-evolution of neural robot controllers in a predator-prey scenario with work on the 'co-evolution' of robot morphology and control systems.
Back to the program
[ Workshop Home ]