Conference paper
Multiresolutional Schemata for Unsupervised Learning of Autonomous Robots for 3D Space Operation
01 May 1994
Abstract
This paper describes a novel approach to the development of a learning control system for autonomous space robot (ASR) which presents the ASR as a "baby"-that is, a system with no a priori knowledge of the world in which it operates, but with behavior acquisition techniques that allows it to build this knowledge from th_ experiences of actions within a particular environment (we will call it an Astro-baby). The learning techniques are rooted in the recursive algorithm for inductive generation of nested schemata molded from processes of early cognitive development in humans. The algorithm extracts data from the environment and by means of correlation and abduction, it creates schemata that are used for control. This system is robust enough to deal with a constantly changing environment because such changes provoke the creation of new schemata by generalizing from experiences, while still maintaining minimal computational complexity, thanks to the system's multiresolutional nature. Experimenting with ASR is especially interesting because the rules of input control do not coincide with human intuitions. Actually, we want to see that the simulated device can learn the unexpected schemata from its own experience. Although the traditional approach to autonomous navigation involves off-line path planning with a known world map (such as the potential fields algorithm). in most of the real tasks the environment is not weU known because of ever-changing conditions of the assignment absence of gravity, and sophisticated, hard to predict obstacles like components of the space stations, etc. Astro-baby gathers data from its sensors and then by using a schema-discovery system it extracts concepts, forms schemata and creates a quantitative/conceptual semantic network. When the Astro-baby is first dropped into the space it does not have any experiences and its sensors and actuators are sets that do not have any distinction among its elements. Then. by trial and error, the ASR learns the function of its actuators and sensors; and how to activate them to achieve a the goal given by its creator, or the sub-goals that it finds. In our simulation the initial goal is to minimize the distance to a beacon. The learning techniques are rooted in a nested"hierarchical algorithm molded from processes of early cognitive development in humans. The algorithm extracts data from the environment and by means of correlation, it creates schemata (rules) that are used for control This system is robust enough to deal with a constantly changing environment because such changes provoke the creation of new schemata using generalization, while still maintaining minimal computational complexity, thanks to the system's multiresolutiortal nature. The results of simulation are positive. Astro-baby displays the ability to learn a number of maneuvers.
Metrics
1 Record Views
Details
- Title
- Multiresolutional Schemata for Unsupervised Learning of Autonomous Robots for 3D Space Operation
- Creators
- Alberto Lacaze - Drexel UniversityMichael Meystel - Drexel UniversityAlexander Meystel - Drexel University
- Conference
- The 1994 Goddard Conference on Space Applications of Artificial Intelligence (Goddard Space Flight Center)
- Publisher
- National Aeronautics and Space Administration
- Resource Type
- Conference paper
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Identifiers
- 991022032971204721