Published on Sun Oct 11 2009

Higher coordination with less control - A result of information maximization in the sensorimotor loop

Keyan Zahedi, Nihat Ay, Ralf Der

This work presents a novel learning method in the context of embodied artificial intelligence and self-organization. The learning rule is derived from the principle of maximizing the predictive information in the sensorimotor loop. It is evaluated on robot chains of varying length withividually controlled, non-communicating segments.

0
0
0
Abstract

This work presents a novel learning method in the context of embodied artificial intelligence and self-organization, which has as few assumptions and restrictions as possible about the world and the underlying model. The learning rule is derived from the principle of maximizing the predictive information in the sensorimotor loop. It is evaluated on robot chains of varying length with individually controlled, non-communicating segments. The comparison of the results shows that maximizing the predictive information per wheel leads to a higher coordinated behavior of the physically connected robots compared to a maximization per robot. Another focus of this paper is the analysis of the effect of the robot chain length on the overall behavior of the robots. It will be shown that longer chains with less capable controllers outperform those of shorter length and more complex controllers. The reason is found and discussed in the information-geometric interpretation of the learning process.

Wed Jan 30 2013
Machine Learning
Information driven self-organization of complex robotic behaviors
Information theory is a powerful tool to express principles to drive autonomous systems. The information principle, formulated at the level of behavior, is translated to the dynamics of the synapses.
0
0
0
Thu Jun 30 2011
Artificial Intelligence
Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments
Reinforcement learning can only be successfully applied to complex autonomous robots if strong assumptions are made on the characteristics of the environment in which the learning is performed. The introduction of such assumptions leads to strongly-biased learning systems that can eventually lose the generality of traditional reinforcement-learning algorithms.
0
0
0
Tue Feb 26 2019
Artificial Intelligence
Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives
Voluntary behavior of humans appears to be composed of small, elementary building blocks or behavioral primitives. Here, we introduce a computational learning architecture, termed surprise-based behavioral modularization into event-predictive structures.
0
0
0
Fri May 06 2011
Artificial Intelligence
Self-organized adaptation of a simple neural circuit enables complex robot behaviour
Chaos control is a new strategy to generate complex behaviour of an autonomous robot. 18 sensors drive 18 motors via a simple neural control circuit. The control quickly and reversibly adapts to new situations.
0
0
0
Thu Apr 30 2020
Machine Learning
How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
Taking inspiration from how the brain coordinates multiple learning systems is an appealing strategy to endow robots with more flexibility. One of the expected advantages would be for robots to autonomously switch to the least costly system when its performance is satisfying.
0
0
0
Wed Nov 25 2020
Artificial Intelligence
Sensorimotor representation learning for an "active self" in robots: A model survey
Safe human-robot interactions require robots to be able to learn how to behave appropriately in a dynamic and unstructured environment. In humans, these capabilities are thought to be related to our ability to perceive our body in space.
0
0
0