You are here

COSMIC-T: Collaborative intelligence for Olfactory Search Missions Integrating Canines and Technology

Award Information
Agency: Department of Defense
Branch: Defense Advanced Research Projects Agency
Contract: W31P4Q-22-C-0057
Agency Tracking Number: D2-2650
Amount: $1,799,440.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: AF19A-T001
Solicitation Number: 19.A
Solicitation Year: 2019
Award Year: 2022
Award Start Date (Proposal Award Date): 2022-07-26
Award End Date (Contract End Date): 2024-09-26
Small Business Information
500 West Cummings Park Suite 3000
Woburn, MA 01801-1111
United States
DUNS: 859244204
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: Yes
Principal Investigator
 Adam Kaplan
 (781) 933-5355
Business Contact
 Lora Loyall
Phone: (781) 933-5355
Research Institution

A critical class of difficult and important operations is “mixed team” environments (teams composed of heterogeneous agents, e.g., human/UxV/canine team) which require heterogeneous sub-teams to form and reform in accordance with an evolving situation.  Search and Rescue (SAR) missions are one example of this class of operations, typically including a distributed set of canine/human sub-teams which search for victims by leveraging the superior olfactory sensor of the canine and supplementary agents who supervise the canine and support related mission tasks such as medical treatment and victim evacuation, depending on the state of the victim.  Often, these missions are fully centralized with one or a few tightly-coupled teams inefficiently accomplishing the search.  Distributed teams are more efficient and cost-effective, leveraging the concept of mosaic operations enabling less expensive components; however, this approach comes with difficult coordination challenges.  Our proposed ToM-centric program is called Collaborative-intelligence for Olfactory Search Missions Integrating Canines and Technology (COSMIC-T). COSMIC-T will integrate Canines, UAVs and humans into loosely coupled teams that can dynamically form sub-teams to apply to specific situations. Example event drivers might include the finding of a strong scent likely to be associated with a victim but with no visible contact, or a decrease in team efficacy resulting from exhaustion (either canine or human or both) requiring perhaps replacements or plan revision. COSMIC-T It comprises two parallel component tasks, 1) we will research the theoretical extensions to ToM needed to make such a system operational in the real world and extensible to various missions, and 2) design and conduct experiments to validate this approach for an operational context, in this case a SAR mission, and move towards transition. 

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government