You are here

MIXTAPE: Middleware for Interactive XAI with Tree-based AI Performance Evaluation

Award Information
Agency: Department of Defense
Branch: Army
Contract: W911NF-22-P-0084
Agency Tracking Number: A22B-T016-0083
Amount: $172,999.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: A22B-T016
Solicitation Number: 22.B
Timeline
Solicitation Year: 2022
Award Year: 2022
Award Start Date (Proposal Award Date): 2022-09-26
Award End Date (Contract End Date): 2023-03-31
Small Business Information
1712 Route 9 Suite 300
Clifton Park, NY 12065-3104
United States
DUNS: 010926207
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Brian Hu
 (703) 638-0245
 brian.hu@kitware.com
Business Contact
 Denise Hale
Phone: (518) 836-2178
Email: denise.hale@kitware.com
Research Institution
 The Pennsylvania State University
 Tracy Ray
 
E397 Westgate building
University Park, PA 16802-6823
United States

 (814) 865-1372
 Nonprofit College or University
Abstract

Kitware, in partnership with Penn State University, is proud to propose this Phase I STTR effort to create XAI middleware that can support the interactive explanation and visualization of AI decision-making systems. Current (X)AI algorithms are often application-specific, limiting their portability to cross-cutting domains. Our approach, MIXTAPE, will create modular and extensible software interfaces and implementations of different XAI tools for humans to evaluate the performance of their AI agents in specific environments (e.g., in Multi-Domain Operations). This work builds upon our previous experience on the DARPA XAI and XAI Toolkit efforts, where we developed novel techniques for explaining the complex reasoning of AI agents in different environments. For explanations, we will extend the tree-based visualizations we used previously, which can show current and predicted future action and state information at critical decision points. To provide a process for humans to scaffold their explanation consumption, we will extend our work on After-Action Review for AI. Given the flexible nature of our framework, additional forms of explanation can also be incorporated, such as saliency maps, tracking win/loss probabilities over time, and including geospatial visualization when appropriate. We will first test our approach on the ARL Battlespace environment, but it can apply to different AI agents, wargaming scenarios, and AI testbeds.

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

US Flag An Official Website of the United States Government