A distributed architecture for heterogeneous multi sensor-task allocation

Abstract

Heterogeneous sensor networks are increasingly deployed to support users in the field requiring many different kinds of sensing tasks. There may be multiple alternative kinds of sensors suitable for a given task. Sensing tasks might compete for the exclusive usage of available sensors. Such an environment is highly dynamic with users moving and generating tasks at different rates. Users typically lack the time and expertise to manually decide which are the best sensors for their tasks. We need therefore to design a distributed system to automatically allocate sensors to tasks. We formalize this problem as MultiSensor Task Allocation (MSTA) and show that the heterogeneity of sensors and tasks requires knowledge-based sensor-task matching. We extend a pre-existent well known coalition formation protocol to propose a novel layered distributed system which by using qualitative and quantitative measures provides allocation flexibility. We demonstrate that it is feasible to perform the knowledge-based sensor-task matching on a user's device by presenting a proof-of-concept mobile app which allows a user in the field to interact with the system. We run simulations to demonstrate that our architecture is scalable and that the allocation quality improves by allowing preemption of sensing resources from ongoing tasks and a reallocation mechanism.

Human Factors in Intelligence, Surveillance, and Reconnaissance: Gaps for Soldiers and Technology Recommendations

“…There is also a broad research program on techniques for soft and hard information fusion [18]. The U.S. and U.K. International Technology Alliance in Network & Information Sciences is developing technology for coalition ISR allocation using controlled natural language [19], such as the Sensor Assignments to Mission (SAM) system [20], [21]. Last, comprehensive evaluations of tactical and operational gaps in ISR provide a military command and doctrinal perspective [22], [23].…”

“…The technological approach we are pursuing for decisionaiding is the SAM system [20], [21]-an artificial intelligence (AI) system for ISR resource allocation. SAM uses a controlled natural language as a common human and machinereadable representation of knowledge, thus it is likely to have greater transparency to humans than black box AI.…”

Tasking and sharing sensing assets using controlled natural language

“…Doing so allows us to deploy the knowledge base on a mobile device as described in, 10 where we compute the size of a realistic complete table to be in the order of 20,000 entries, which can comfortably be stored in 12MB on a smartphone or tablet. Note that the size of the deployed table can easily be reduced by including only task types and asset types relevant to a particular mission context.…”

“…Usage of the lookup table in asset assignment is covered in detail in. 10 In outline, the assignment procedure is as follows:…”

“…Because there was competition between tasks, we studied models for the pre-emption of existing tasks by new tasks. 10 A typical case would involve a new higher-priority task effectively "stealing" resources from an existing lower-priority task.…”