SBIR/STTR Research Award
Winning in Capability-Disadvantaged Scenarios, with Reinforcement Learning
Award amount
$74,802Program and phase
STTR · Phase IAward year
2023Award details
- Awarding agency
- Department of Defense
- Branch
- Air Force
- Recipient company
- MICROSURGEONBOT INC
- Proposal award date
- 2022-11-03
- Contract end date
- 2023-02-04
- UEI
- MJ5VN8RGU389
- Solicitation number
- X22.D
- Topic code
- X22D-OTCSO1
Research abstract
Building on our ‘Universal Interface for Simulation’ called GURU’s remarkable ability to set up and run thousands of hypersonic trajectory simulations in minutes, we propose to add a Reinforcement Learning-driven self-play function to discover unconventional solutions to successfully intercept the threats in capability-disadvantaged scenarios. Think of how Google DeepMind wins complex videogames with MuZero – we’re bringing the latest artificial intelligence and the latest in simulation to discover new ways to defend against adversary hypersonic weapons.
Technology keywords
Not reported
Other awards by this recipient
Verified by the same UEI. These are other public SBIR/STTR award pages, not a merged company record.
- OrbitGuard: From Data Deluge to Decision Dominance
- Hierarchical AI System for Advanced Air Mobility Regulatory Gap Analysis
- GURU, Creating Winning Change with DET 23
- Autonomously Generating White Cell Training Scenarios
- On-Orbit Operations and Mission Planning in Minutes, not Hours
Awards with the same topic code
Verified by an exact topic code match. This is not a text-similarity match.
- Detecting, Forecasting, and Countering Great Power Information Operations in Developing Nations
- Performance and Acoustic Design Optimization Tools for Cyclonic Vortex Engines
- Lattitude (Lattus) Human System Mentoring Solution
- AI-enabled Multi-media Musculoskeletal Triage and Assessment Kit (AMTAK)
- Team-Based Decision-Making Simulation in Virtual Reality for Forward Deployed Damage Control Resuscitation and Surgery