Quantitative evaluation of the exploration strategies of a mobile robot
International Journal of Robotics Research
Learning metric-topological maps for indoor mobile robot navigation
Artificial Intelligence
Frontier-based exploration using multiple robots
AGENTS '98 Proceedings of the second international conference on Autonomous agents
Exploration in active learning
The handbook of brain theory and neural networks
Using EM to Learn 3D Models of Indoor Environments with Mobile Robots
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Cooperative Autonomous Low-Cost Robots for exploring Unknown Environments
The 4th International Symposium on Experimental Robotics IV
Coordination for Multi-Robot Exploration and Mapping
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Collaborative Exploration of Unknown Environments with Teams of Mobile Robots
Revised Papers from the International Seminar on Advances in Plan-Based Control of Robotic Agents,
Exploring artificial intelligence in the new millennium
Efficient Exploration In Reinforcement Learning
Efficient Exploration In Reinforcement Learning
Exploration of Unknown Environments with Motivational Agents
AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1
Case-Based Collective Inference for Maritime Object Classification
ICCBR '09 Proceedings of the 8th International Conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
Learning hierarchical object maps of non-stationary environments with mobile robots
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
| Hi-index | 0.00 |
We propose a multi-agent approach to the problem of exploring unknown environments that relies on providing the agents with a measure of interest for the viewpoints of the surrounding environment. Such measure of interest takes into account the expected decrease in uncertainty provided by acquiring the information of objects seen from a viewpoint and the novelty of the potential class label of those objects. This allows the agents to visit selectively the objects that populate the environment. This single agent exploration strategy is combined with a multi-agent exploration strategy relying on a brokering system that allows the coordination of the agent team according to the agents's personal interest and their distance to the viewpoints. The advantages of these forms of selective attention, together with those of the collaborative multi-agent exploration strategy, are tested in several scenarios, comparing our approach against classical ones.