Multi-UAV Cooperative Search Using an Opportunistic Learning Method

Abstract

The control of networked multivehicle systems designed to perform complex coordinated tasks is currently an important and challenging field of research. This paper addresses a cooperative search problem where a team of uninhabited aerial vehicles (UAVs) seeks to find targets of interest in an uncertain environment. We present a practical framework for online planning and control of a group of UAVs for cooperative search based on two interdependent tasks: (i) incrementally updating “cognitive maps” used as the representation of the environment through new sensor readings; (ii) continuously planning the path for each vehicle based on the information obtained through the search. We formulate the cooperative search problem and develop a decentralized strategy based on an opportunistic cooperative learning method, where the emergent coordination among vehicles is enabled by letting each vehicle consider other vehicles’ actions in its path planning procedure. By using the developed strategy, physically feasible paths for the vehicles to follow are generated, where constraints on aerial vehicles, including physical maneuverabilities, are considered and the dynamic nature of the environment is taken into account. We also present some mathematical analysis of the developed search strategy. Our analysis shows that this strategy guarantees a complete search of the environment and is robust to a partial loss of UAVs. A lower bound on the search time for any strategy and a relaxed upper bound for the proposed strategy are given. Simulation results are used to illustrate the effectiveness of the proposed strategy.

Survey of Important Issues in UAV Communication Networks

“…In their work on PRoPHET-based routing protocol [10] the authors explain how in opportunistic networks multi-UAVs find a path even if two end points are not directly connected leading to completion of missions. In their work on Multi-UAV cooperative search in [11] the authors describe how multi-UAV systems complete searches faster and are robust to loss of some UAVs. Advantages of multi-UAV networks are leading to their increasing use in civilian applications [1].…”

“…The task-planning problem for UAV networks with connectivity constraint involves a number of parameters and interaction of dynamic variables. An algorithm has been proposed for such a situation [11]. There is also an algorithm for distributed intelligent agent systems in which agents autonomously coordinate, cooperate, negotiate, make decisions and take actions to meet the objectives of a particular task.…”

An Organic Computing Approach to Self-Organizing Robot Ensembles

“…There have been efforts in this direction that yield the minimal number of units needed to find (mobile) targets within a given time and with a certain probability (Vincent and Rubin, 2004) or adapt concise trajectory plans for sets of units based on their individual properties (Yang et al, 2007). A general taxonomy for cooperative search is provided by El-Abd and Kamel (2005).…”

“…Their advantage over alternative topologies lies in sweeping large, connected areas, thus minimizing the odds of the target slipping through the search grid. Similar to Vincent and Rubin (2004), we can optimize the couplings to minimize the number of deployed units and to conduct a comprehensive search within a given time [as in Yang et al (2007)]. Considering inconsistencies in the ARUs' flight behaviors, the impact of the environment, and possible heterogeneities of the deployed units, the tandem of level 1 learnings and level 2 offline adjustments become all the more relevant.…”

Kripke modelling and verification of temporal specifications of a multiple UAV system

“…UAVs are suitable for these operations because they are too dangerous for human pilots. Some of the tasks such as monitoring forest fire propagation and mapping chemical cloud propagation can only be carried out by a group of UAVs and cannot be carried out by a single UAV [1][2][3][4]. Cooperative UAV control problems that have received recent attention include cooperative formation [5], cooperative task allocation, cooperative path-planning and cooperative search.…”