A systematic agent framework for situated autonomous systems

Authors:
Frédéric Py;Kanna Rajan;Conor McGann
Affiliations:
Monterey Bay Aquarium Research Institute, Moss Landing, California;Monterey Bay Aquarium Research Institute, Moss Landing, California;Willow Garage, Menlo Park, California
Venue:
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 2 - Volume 2
Year:
2010

Citing 6
Cited 4

Towards a general theory of action and time

Artificial Intelligence
Remote Agent: to boldly go where no AI system has gone before

Artificial Intelligence - Special issue: artificial intelligence 40 years later
Three-layer architectures

Artificial intelligence and mobile robots
Interleaving Planning and Robot Execution for Asynchronous User Requests

Autonomous Robots - Special issue on autonomous agents
Constraint-Based Attribute and Interval Planning

Constraints
Adaptive control for autonomous underwater vehicles

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3

TGA-based controllers for flexible plan execution

KI'11 Proceedings of the 34th Annual German conference on Advances in artificial intelligence
Coordinated sampling of dynamic oceanographic features with underwater vehicles and drifters

International Journal of Robotics Research
Continuous time planning for multiagent teams with temporal constraints

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume One
Robotics and artificial intelligence: A perspective on deliberation functions

AI Communications - ECAI 2012 Turing and Anniversary Track

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a formal framework of an autonomous agent as a collection of coordinated control loops, with a recurring sense, plan, act cycle. Our framework manages the information flow within the partitioned structure to ensure consistency in order to direct the flow of goals and observations in a timely manner. The resulting control structure improves scalability since many details of each controller can be encapsulated within a single control loop. This partitioned agent design promises a domain-independent, scalable and robust approach for control of real-world autonomous robots operating in dynamic environments. We validate our framework with experimental results from deployments in two different real-world domains.