Recursive Bayesian search-and-tracking using coordinated uavs for lost targets

Furukawa, Tomonari; Bourgault, F.; Lavis, Benjamin; Durrant‐Whyte, Hugh

doi:10.1109/robot.2006.1642081

Cited by 162 publications

(116 citation statements)

References 7 publications

Supporting

Mentioning

110

Contrasting

Unclassified

Order By: Relevance

“…About the movement, a large number researches have a pre-defined assumption that the UAV can not re-planned its movement no matter how the UAVs are distributed [13], [14], [15]. And most of them is associated with the first kind of search such as lane base search, random search, grid based search [16].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Framework for Probabilistic Search with Multi-UAVs

Qin¹,

Li²

2017

The 5th International Conference on Advanced Computer Science Applications and Technologies (ACSAT 2017)

View full text Add to dashboard Cite

Abstract. This paper focuses on the task of searching a stationary target using a team of multiple unmanned aerial vehicles (UAV) with limited communication ranges and sensing capabilities. It is based on a probabilistic representation model of the search environment, in which each UAV keeps a probability map on the presence of the target for each cell. The UAVs make observations and update the map for multiple rounds according to the Bayesian rule. In this process, each UAV can exchange data with its neighbors who are in its communication range. The decision of finding the target can be made once its probability of presence in any cell reaches a threshold. In this work, we design an efficient framework to decide the movement of each UAV at each time step, and propose a novel data fusion strategy among UAVs. The simulation result shows that our framework achieves improvements on both the success rate and the time taken to complete the searching task. We also explore the impact of different parameters, like the sensor model, moving mobility model of each UAV, and the data fusion strategies associated with the moving patterns. The simulation results show that the correct rate on target identification can vary greatly under different parameter settings, indicating the importance of the selection of UAV searching components such as the sensor model and the mobility model.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The target's occupancy probability is modelled as a Bernoulli Distribution [18], that is X c = 1 (target is in cell c) as probability P c and target is not in cell in c (X c = 0) is probability 1-P c . If cell c have not been searched, Pc = 0.5.…”

Section: Problem Statementmentioning

confidence: 99%

An Efficient Framework for Probabilistic Search with Multi-UAVs

Qin¹,

Li²

2017

The 5th International Conference on Advanced Computer Science Applications and Technologies (ACSAT 2017)

View full text Add to dashboard Cite

show abstract

“…Much research has been done based on the early work by Koopman; people have investigated different types of detection functions, different search patterns, more general target prior distributions, moving targets and moving searchers (see e.g., [22][23][24]). There are several recent papers considering a (multi) UAV search for targets using some Bayesian approach, see for instance Bourgault et al [25] and Furukawa et al [26]. A common search approach is to represent the target density by a discrete fixed probability grid, and the goal is to maximize the number of detected targets and the search performance is represented by a cumulative probability of detection.…”

Section: Background and Literature Surveymentioning

confidence: 99%

Road Target Search and Tracking with Gimballed Vision Sensor on an Unmanned Aerial Vehicle

et al. 2012

View full text Add to dashboard Cite

This article considers a sensor management problem where a number of road bounded vehicles are monitored by an unmanned aerial vehicle (UAV) with a gimballed vision sensor. The problem is to keep track of all discovered targets and simultaneously search for new targets by controlling the pointing direction of the vision sensor and the motion of the UAV. A planner based on a state-machine is proposed with three different modes; target tracking, known target search, and new target search. A high-level decision maker chooses among these sub-tasks to obtain an overall situational awareness. A utility measure for evaluating the combined search and target tracking performance is also proposed. By using this measure it is possible to evaluate and compare the rewards of updating known targets versus searching for new targets in the same framework. The targets are assumed to be road bounded and the road network information is used both to improve the tracking and sensor management performance. The tracking and search are based on flexible target density representations provided by particle mixtures and deterministic grids.

show abstract

“…The use of automated task planning for SaT missions has received little attention so far, while probabilistic approaches based on Recursive Bayesian Estimation (RBE) have been explored in more depth. Efficient solutions to SaT have been proposed under restrictive simplifying assumptions such as the search area being small (one/two square km), the temporal horizon being short (a few minutes) and the target's motion model being simple (e.g., targets being stationary or in Markovian motion) (Stone 1975;Bourgault et al 2006;Furukawa et al 2006;Lavis and Furukawa 2008;Lin and Goodrich 2014). Although this purely probabilistic approach is successful for small-scale and simple SaT problems, it fails in the face of all the constraints that characterise realworld SaT operations because it becomes computationally too expensive.…”

Section: Introductionmentioning

confidence: 99%

Combining temporal planning with probabilistic reasoning for autonomous surveillance missions

2015

View full text Add to dashboard Cite

It is particularly challenging to devise techniques for underpinning the behaviour of autonomous vehicles in surveillance missions as these vehicles operate in uncertain and unpredictable environments where they must cope with little stability and tight deadlines in spite of their restricted resources. State-of-the-art techniques typically use probabilistic algorithms that suffer a high computational cost in complex real-world scenarios. To overcome these limitations, we propose a hybrid approach that combines the probabilistic reasoning based on the target motion model offered by Monte Carlo simulation with long-term strategic capabilities provided by automated task planning. We demonstrate our approach by focusing on one particular surveillance mission, search-and-tracking, and by using two different vehicles, a fixed-wing UAV deployed in simulation and the "Parrot AR.Drone2.0" quadcopter deployed in a physical environment. Our experimental results show that our unique way of integrating probabilistic and deterministic reasoning pays off when we tackle realistic missions. Electronic supplementary materialThe online version of this article

show abstract

Recursive Bayesian search-and-tracking using coordinated uavs for lost targets

Cited by 162 publications

References 7 publications

An Efficient Framework for Probabilistic Search with Multi-UAVs

An Efficient Framework for Probabilistic Search with Multi-UAVs

Road Target Search and Tracking with Gimballed Vision Sensor on an Unmanned Aerial Vehicle

Combining temporal planning with probabilistic reasoning for autonomous surveillance missions

Contact Info

Product

Resources

About