Artificial Intelligence
Real-time search for learning autonomous agents
Real-time search for learning autonomous agents
Xavier: a robot navigation architecture based on partially observable Markov decision process models
Artificial intelligence and mobile robots
Simulated and situated models of chemical trail following in ants
Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
Value-update rules for real-time search
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Whistling in the dark: cooperative trail following in uncertain localization space
AGENTS '00 Proceedings of the fourth international conference on Autonomous agents
Exploring unknown environments with real-time search or reinforcement learning
Proceedings of the 1998 conference on Advances in neural information processing systems II
Automatically tracking and analyzing the behavior of live insect colonies
Proceedings of the fifth international conference on Autonomous agents
An Behavior-based Robotics
Efficiently searching a graph by a smell-oriented vertex process
Annals of Mathematics and Artificial Intelligence
Efficient and inefficient ant coverage methods
Annals of Mathematics and Artificial Intelligence
Coverage for robotics – A survey of recent results
Annals of Mathematics and Artificial Intelligence
Real-time search in non-deterministic domains
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Easy and hard testbeds for real-time search algorithms
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
| Hi-index | 0.00 |
We study robots that leave trails in the terrain to cover closed terrain efficiently and robustly. Such ant robots have so far been studied only theoretically for gross ant robot simplifications in unrealistic settings. In this article, we design ant robots for a realistic robot simulation environment. We discuss how large the markers should be that form the trail, how frequently they should be dropped, how large the sensed floor area below the ant robots should be, how the ant robots should move depending on where the markers are in the sensed area, and how the markers should be deleted to avoid saturating the floor with markers. We then report experiments that we have performed to understand the behavior of the resulting ant robots better, including their efficiency and robustness in situations where they are failing, they are moved without realizing this, and markers are deleted. Finally, we report the results of a large-scale experiment where ten ant robots covered an area of 25 by 25 meters repeatedly over 85 hours.