The road sign problem revisited: handling delayed response tasks with neural robot controllers

Authors:
Mikael Thieme;Tom Ziemke
Affiliations:
Department of Computer Science, University of Skövde, Box 408, 54128 Skövde, Sweden;Department of Computer Science, University of Skövde, Box 408, 54128 Skövde, Sweden
Venue:
ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Year:
2002

Citing 5
Cited 1

The Induction of Dynamical Recognizers

Machine Learning - Connectionist approaches to language learning
Evolutionary robotics and the radical envelope-of-noise hypothesis

Adaptive Behavior
Beyond physical grounding and naive time: investigations into short-term memory for autonomous agents

Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
Embedding Connectionist Autonomous Agents in Time: The ‘Road Sign Problem’

Neural Processing Letters
Mobile robot learning of delayed response tasks through event extraction: a solution to the road sign problem and beyond

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2

Evolving reinforcement learning-like abilities for robots

ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware

Quantified Score

Hi-index	0.00

Visualization

Abstract

The 'road sign problem' is a class of delayed response tasks in which an agent's correct turning direction at a T-junction is dependent on a stimulus it has encountered earlier. Neural robot controllers of four different architectures have been evaluated in experiments with six different variations of the problem. The highest reliability was achieved by Extended Sequential Cascaded Networks, a higher-order recurrent neural network architecture.