Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Kaa: policy-based explorations of a richer model for adjustable autonomy
Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
Exploiting belief bounds: practical POMDPs for personal assistant agents
Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
Using multiagent teams to improve the training of incident commanders
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Managing autonomy in robot teams: observations from four experiments
Proceedings of the ACM/IEEE international conference on Human-robot interaction
RIAACT: a robust approach to adjustable autonomy for human-multiagent teams
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 3
Improving adjustable autonomy strategies for time-critical domains
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Lazy approximation for solving continuous finite-horizon MDPs
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Towards adjustable autonomy for the real world
Journal of Artificial Intelligence Research
A fast analytical algorithm for solving Markov decision processes with real-valued resources
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
| Hi-index | 0.00 |
Commercial aviation transportation is on the rise and has become a necessity in our increasingly global world. There is a societal demand for more options, more traffic, more efficiency, while still maintaining safety in the airspace. To meet these demands the Next Generation Air Transportation System (NextGen) concept from NASA calls for technologies and systems offering increasing support from automated decision-aiding and optimization tools. Such systems must coordinate with the human operator to take advantage of the functions each can best perform: The automated tools must be designed to support the optimal allocation of tasks (functions) between the system and the human operators using these systems. Preliminary function allocation methods must be developed (and evaluated) that focus on the NextGen Airportal challenges, given a flexible, changing Concept of Operations (ConOps). We have begun making steps toward this by leveraging work in agents research (namely Adjustable Autonomy) in order to allow function allocation to become more dynamic and adjust to the goals, demands, and constraints of the current situation as it unfolds. In this paper we introduce Dynamic Function Allocation Strategies (DFAS) that are not static and singular, but rather are represented by allocation policies that vary over time and circumstances. The NextGen aviation domain is a natural fit for agent based systems because of its inherently distributed nature and the need for automated systems to coordinate on tasks maps well to the adjustable autonomy problem. While current adjustable autonomy methods are applicable in this context, crucial extensions are needed to push the existing models to larger numbers of human players, while maintaining critical timing. To this end, we have created an air traffic control system that includes: (1) A simulation environment, (2) a DFAS algorithm for providing adjustable autonomy strategies and (3) the agents for executing the strategies and measuring system efficiency. We believe that our system is the first step towards showing the efficacy of agent supported approach to driving the dynamic roles across human operators and automated systems in the NextGen environment. We present some initial results from a pilot study using this system.