L. Parker, Cooperative robotics for multi-target observation, Intelligent Automation and Soft Computing 5(1) (1999), 5--19.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....plans warrants further investigation as a method for imbuing reactive agents with a priori knowledge. 1. Introduction Reconnaissance, like surveillance, is a dynamic, distributed sensory problem in an adversarial environment demanding a strongly cooperative solution to achieve a goal [13]. These problems require agents capable of coordinated sensing, processing, and communication [7] Purely reactive robotic architectures, such as those advocated by Brooks [3] allow a robot to operate in dynamic environments but abandon traditional planning and knowledge representation. Yet a ....

Lynne E. Parker, "Cooperative Robotics for MultiTarget Observation", Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5 (1), 5-19, 1999.

....the tracking network, and they can also adapt to the movement of targets or the dynamic changes in an environment by re positioning themselves in response. We introduce a scalable, cooperative tracking system that consists of multiple mobile robots and multiple stationary sensors. Prior research [7, 8] on cooperative tracking problem has focused on allocating multiple robots to multiple targets in a bounded environment with no obstacles. This work is supported in part by DARPA grant DABT63 99 10015 and NSF grants ANI 9979457 and ANI 0082498 These systems were not applied or scaled for ....

....1: The simulation environments (the black regions are occupied and the rest is free space) The associated topological maps are shown as graphs tional stereo system to track multiple moving targets. There is relatively little research on cooperative multitarget tracking using multiple robots. [7] utilized the ALLIANCE architecture to achieve target assignment; it used implicit communication (acquiescence and impatience levels) for cooperation. In contrast [8] used explicit communication (inhibition signal over the network) for target al..location. 10] described a Variable Structure ....

[Article contains additional citation context not shown here]

Lynne E. Parker, "Cooperative robotics for multi-target observation," Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, vol. 5, no. 1, pp. 5--19, 1999.

....multiple robots have been proposed. For example, the coordination of multiple robots manipulating objects using ropes [5] and the cooperation among a human and a group of robots [6] Also, other tasks that require tightly coupled cooperation have been addressed such as the Multi Target Observation [13]. This work builds on previous work [16, 18, 19] in which a decentralized control system was developed for coordinated control of mobile manipulators. In [18] the use of passive compliance (realized by an actively controlled parallel manipulator) was shown to result in a robust grasp, a grasp ....

L. E. Parker, "Cooperative robotics for multi-target observation," Intelligent Automation and Soft Computing, vol. 5, no. 1, pp. 5--19, 1999.

....including [2, 11, 4] The ALLIANCE architecture [17] presents a robust, multirobot, task allocation system. An opportunistic approach based on mutual inhibition and broadcast of local eligibility is presented in [22] The approach is applied to a target tracking problem studied previously in [18, 19]. An auction based approach based on commitment is presented in [8] where a task allocation strategy using a market based auction system commits the robots to their tasks until success or failure. The latter two approaches are summarized in this paper. 3 Unifying Framework The three approaches ....

....connect BLE enabled behaviors allows systems to scale in capability as well as in number of robots. 4. 2 The Problem Domain: MultipleTarget Tracking We have validated our BLE approach through experiments in the domain of cooperative multi robot observation of multiple moving targets, or CMOMMT [19]. CMOMMT involves a team of robots which must attempt to keep a number of prioritized moving targets under constant observation. We also implemented a weighted version of the problem, called W CMOMMT, in which the different targets are priorities. To apply BLE to this problem domain, each robot ....

Lynne E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5--19, 1999.

....partially known environments. GRAMMPS also has a low level planner on each robot and uses a similar approach to distribute targets, however GRAMMPS does not look at multiple resources or exogenous events. Most other cooperative robotic systems utilize reactive planning techniques (Mataric 1995; Parker 1999). These systems focus on behavioral approaches and do not explicitly reason about assigning goals and planning courses of actions. Furthermore, none of these systems utilize a learning component to drive the system goals. Future Work A number of extensions are planned for each component of ....

Parker, L. E. 1999. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing 5(1):5-19.

....planner on each robot and uses a similar approach to distribute targets. However GRAMMPS uses simulated annealing where we use a greedy approach, and GRAMMPS does not look at multiple resources or exogenous events. Many cooperative robotic systems utilize reactive techniques (Mataric 1995; Parker 1999). These systems have been shown to exhibit low level cooperative behavior in both known and noisy environments. However, they have not been shown useful for mission planning where a set of high level science and engineering goals must be achieved in an ecient manner. There are a number of ....

Parker, L. E. 1999. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing 5(1):5-19.

....a low level planner on each robot and uses a similar approach to distribute targets. However GRAMMPS uses simulated annealing where we use a greedy approach, and GRAMMPS does not look at multiple resources or exogenous events. Many cooperative robotic systems utilize reactive planning techniques [10, 13]. These systems have been shown to exhibit low level cooperative behavior in both known and noisy environments. However, these systems have not been shown useful for mission planning where a set of high level science and engineering goals must be achieved in an ecient manner. There are a number ....

Lynne E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, 5(1):5-19, 1999. 11

....themselves in order to efficiently allocate resources in response to task constraints, environmental conditions, and system resources. We introduce the Broadcast of Local Eligibility (BLE) as a general tool for coordination between robots, and then demonstrate its application to the CMOMMT [8] multi target observation task. PAB: Port Arbitrated Behavior Based Control In PAB systems, controllers are written in terms of behaviors, which are groups of concurrent processes that share a public interface. This interface is composed of ports, which are registers that each hold a single data ....

....its output is crossinhibited. Thus, each robot will claim the highest priority task that it is most suitable for. 3 The CMOMMT Task We have tested our BLE approach on a multi target observation task known as CMOMMT (Cooperative Multi robot Observation of Multiple Moving Targets) introduced by [8], and a prioritized variation that we call W CMOMMT. Broadcast of Local Eligibility for CMOMMT 5 CMOMMT is an NP hard problem that requires strong cooperation [7] for good performance. It has the benefit of simple formulation and analysis, and implemented systems for comparison. 3.1 Definition ....

[Article contains additional citation context not shown here]

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, 5:5--19, 1999.

....of Multiple Moving Targets) introduced by [Par97] and a prioritized variation that we call W CMOMMT. CMOMMT is an NP hard problem that requires strong cooperation [Par98] for good performance. It has the benefit of simple formulation and analysis, and implemented systems for comparison. Par99] gives a thorough overview of related work; KDPT97] investigates efficient algorithms for the related multi robot observation of entire areas, including trade offs between communicative, non communicative, and centralized methods. 12 a) Output Inhibit Best = 3 Local Robot 1 Behavior n ....

....is, to maximize the time during which each target in S is being observed by at least one robot. We assume that the area covered by the sensors of the robots is much smaller than the total area to be monitored and that targets move slower than the robots. The original formulation of the problem [Par99] assumes that robots share a known global coordinate system; we replace 13 this with the assumption that the robots can visually distinguish each target from the others 2 . Thus our formulation focuses on task space where Parker s formulation and implementation using predictive tracking and ....

[Article contains additional citation context not shown here]

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, 5:5--19, 1999.

....knowledge of the environment etc. Distributed approaches on the other hand are more appealing due to better properties of scaling and reliability. For an overview of approaches and issues in cooperative mobile robotics see [1] 3] 6] Related work on multi robot target observation has been done by [7] using the ALLIANCE architecture, where action selection consists of inhibition (through motivational behaviors) Other approaches to similar tasks include [2] which employs a formation control using a referenced based (e.g. leader, center, or neighbor) type of cooperation with no explicit task ....

....approach can easily be extended to any alternative command fusion mechanism (e.g. voting, fuzzy etc. We can thus conclude that the work described here extends command fusion action selection mechanisms to multi robot coordination. In contrast to behavior arbitration mechanisms (e.g. ALLIANCE [7]) that essentially allow for coordination in turn taking activities, multi robot command fusion allows for pursuit of multiple goals by multiple robots in parallel. We have demonstrated how multi robot command fusion can be used to produce dynamic task division in the context of cooperative ....

Lynne P. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5--19, 1999.

No context found.

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5{ 19, 1999.

....a problem of planning from a known world model. Instead, we investigate the power of a weighted force vector approach distributed across robot team members in simple, uncluttered environments that are either obstacle free or have a random distribution of simple convex obstacles. In other work [32], we describe the implementation of this weighted force vector approach in our ALLIANCE formalism ( 26] 30] for fault tolerant multi robot cooperation. In this article, we focus on the analysis of this approach as it compares to three other approaches: a) fixed robot positions (Fixed) b) ....

....ALLIANCE architecture to a variety of cooperative robot problems, including mock hazardous waste cleanup ( 27] 30] bounding overwatch ( 29] 28] janitorial service [29] box pushing [26] and simple cooperative baton passing [31] implemented on both physical and simulated robot teams. In [32], we provide the details of the behavior organization that implements our A CMOMMTapproach in the ALLIANCE architecture. In the current article, we focus on an analysis of the approach and compare it to three other control mechanisms to determine its usefulness in solving the CMOMMT problem. In ....

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5-19, 1999.

....implemented in a variety of proof of concept applications on both physical and simulated mobile robots. The applications implemented on physical robots include a mock hazardous waste cleanup task [28] 31] cooperative manipulation [32] cooperative observation of multiple moving targets [35], and a cooperative box pushing task, which is described in this section. Over 50 logged physical robot runs of the hazardous waste cleanup and the cooperative manipulation tasks were completed, as well as hundreds of runs of the cooperative observation of multiple moving targets. In addition, ....

....multi robot applications that are composed of independent subtasks. While the domain of multi robot applications that t this description is quite large, there are other types of cooperation that require a tighter coupling of robot tasks. One application of this type that we have been studying [35], 34] is the cooperative observation of multiple moving targets. This application requires a team of robots to continually adjust their movements based upon the locations of targets moving through an area of interest, as well as the movements of other robots on the team. We are exploring other ....

[Article contains additional citation context not shown here]

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5-19, 1999.

....so forth. Many other subproblems can also be addressed, including the physical tracking of targets (e.g. using vision, sonar, IR, or laser range) prediction of target movements, multi sensor fusion, and so forth. A HAND GENERATED SOLUTION TO CMOMMT We have developed a hand generated solution [17, 18] to the CMOMMT problem that performs well when compared to various control approaches. This solution has been implemented on both physical and simulated robots to demonstrate its e ectiveness. The hand generated solution, which we call A CMOMMT, is described brie y as follows. Robots use weighted ....

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5-19, 1999.

No context found.

L. E. Parker, "Cooperative robotics for multi-target observation," Intelligent Automation and Soft Computing 5(1), pp. 5--19, 1999.

No context found.

L. Parker, Cooperative robotics for multi-target observation, Intelligent Automation and Soft Computing 5(1) (1999), 5--19.

No context found.

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, 5(1):5-19, 1999.

No context found.

L. Parker, "Cooperative robotics for multi-target observation, " Intelligent Automation and Soft Computing, 1999.

No context found.

L. Parker, "Cooperative robotics for multi-target observation, " Intelligent Automation and Soft Computing, 1999.

No context found.

Lynne E. Parker, "Cooperative robotics for multitarget observation," Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, vol. 5, no. 1, pp. 5--19, 1999.

No context found.

Lynne E. Parker, "Cooperative robotics for multitarget observation," Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, vol. 5, no. 1, pp. 5--19, 1999.

No context found.

L. E. Parker, "Cooperative robotics for multi-target observation," Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, vol. 5, no. 1, pp. 5--19, 1999.

No context found.

Parker, L.: Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing 5 (1999) 5--19

No context found.

L. E. Parker, "Cooperative robotics for multi-target observation," Intelligent Automation and Soft Computing, special issue on Robotics Research at Oak Ridge National Laboratory, vol. 5, no. 1, pp. 5--19, 1999.

No context found.

Lynne E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, 5(19), 1999.

No context found.

L. E. Parker. Cooperative robotics for multi-target observation. Intelligent Automation and Soft Computing, 5:5#19, 1999.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC