Stochastic Models of a Cooperative Autonomous UAV Search Problem

Flint, Matthew; Fernandez, Emmanuel; Polycarpou, Marios M.

doi:10.5711/morj.8.4.13

Cited by 27 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two possible actions for the UAV -go left or go right -which is the same as choosing to go to cell 1 first or cell 2 first 6 . After the UAV has chosen which cell to observe first, the optimum policy is to keep moving back and forth between the cells, so that a single action defines the optimum policy in this very simple case.…”

Section: Figure 1 -Simplified Two-cell Problemmentioning

confidence: 99%

“…The use of aerial vehicles brings additional concerns pertaining to dynamics of the vehicles [4], but many of the same ideas apply. Flint et al [5] [6] have applied deterministic Dynamic Programming (DP) for path planning for each vehicle, with improvements suggested by Yang [7]. A Kshortest path algorithm has been used by Sujit et al [8] for maximizing explored area under endurance constraints, while [9] uses mixed integer linear programming for task assignment and trajectory planning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Persistent Surveillance Using Multiple Unmanned Air Vehicles

Nigam¹,

Kroo²

2008

2008 IEEE Aerospace Conference

View full text Add to dashboard Cite

Abstract-Search and exploration using multiple autonomous sensing platforms has been extensively studied in the fields of controls and artificial intelligence. The task of persistent surveillance is different from a coverage or exploration problem, in that the target area needs to be continuously searched, minimizing the time between visitations to the same region. This difference does not allow a straightforward application of most exploration techniques to the problem, although ideas from these methods can still be used. In this research we investigate techniques that are scalable, reliable, efficient, and robust to problem dynamics. These are tested in a multiple unmanned air vehicle (UAV) simulation environment, developed for this program.A semi-heuristic control policy for a single UAV is extended to the case of multiple UAVs using two methods. One is an extension of a reactive policy for a single UAV and the other involves allocation of sub-regions to individual UAVs for parallel exploration. An optimal assignment procedure (based on auction algorithms) has also been developed for this purpose. A comparison is made between the two approaches and a simplified optimal result. The reactive policy is found to exhibit an interesting emergent behavior as the number of UAVs becomes large. The control policy derived for a single UAV is modified to account for actual aircraft dynamics (a 3 degree-of-freedom nonlinear dynamics simulation is used for this purpose) and improvements in performance are observed. Finally, we draw conclusions about the utility and efficiency of these techniques.

show abstract

Section: Figure 1 -Simplified Two-cell Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Persistent Surveillance Using Multiple Unmanned Air Vehicles

Nigam¹,

Kroo²

2008

2008 IEEE Aerospace Conference

View full text Add to dashboard Cite

show abstract

“…Other work such as [53], [54] and [55] also use prior knowledge to coordinate agents in the systems. Examples of forms of knowledge communicated include sensory information ( [29], [8]) and resource availabilities [28]. The paper [31] describes a system where there is explicit communication of commands, parameter setup and assignment of tasks to agents involved in a search operation.…”

Section: A Knowledgementioning

confidence: 99%

“…The agents communicate with each other regarding formation of teams to undertake the task collectively. Other search and surveillance procedures involve communication of search routes ( [32]), locations of observed targets ( [30], [29]) and results of sensor actions in addition to UAV locations [56].…”

Section: A Knowledgementioning

confidence: 99%

“…Another approach allows the agents to learn the policies of other "neighboring" agents in addition to their own to bring about a non-direct interaction and optimal behavior of the system as a whole ( [27], [15] and [13]). Several systems such as in [28], [29], [30], [31], [32] and [8] involve explicit communication between the different agents in the system to bring about coordination.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An adaptive-learning framework for semi-cooperative multi-agent coordination

Boukhtouta

Berger

Powell

et al. 2011

2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)

View full text Add to dashboard Cite

Abstract-Complex problems involving multiple agents exhibit varying degrees of cooperation. The levels of cooperation might reflect both differences in information as well as differences in goals. In this research, we develop a general mathematical model for distributed, semi-cooperative planning and suggest a solution strategy which involves decomposing the system into subproblems, each of which is specified at a certain period in time and controlled by an agent. The agents communicate marginal values of resources to each other, possibly with distortion. We design experiments to demonstrate the benefits of communication between the agents and show that, with communication, the solution quality approaches that of the ideal situation where the entire problem is controlled by a single agent.

show abstract

Applications of Location Analysis

Eiselt¹,

Marianov²

2015

International Series in Operations Research &Amp; Management Science

View full text Add to dashboard Cite

Stochastic Models of a Cooperative Autonomous UAV Search Problem

Cited by 27 publications

References 0 publications

Persistent Surveillance Using Multiple Unmanned Air Vehicles

Persistent Surveillance Using Multiple Unmanned Air Vehicles

An adaptive-learning framework for semi-cooperative multi-agent coordination

Applications of Location Analysis

Contact Info

Product

Resources

About