Skip to main navigation Skip to search Skip to main content

SBIR Phase II: A Physics-Based Competitive Machine Learning Framework for AI-Driven Robotics Instruction

Project: Research

Abstract & Details

Description

Award ID: 2506458

The broader and commercial impact of this Small Business Innovation Research (SBIR) Phase II project is to provide mission-critical drone simulations with embedded robotics and artificial intelligence (AI) to accelerate learning in high school physics courses. These simulations visually demonstrate real-world applications of physics while teaching students to develop AI and machine learning (ML) models skills essential for robotics automation, critical skills for advancing the next-generation STEM workforce. This platform addresses the urgent need to improve AP Physics Exam outcomes and provide novel, high-quality resources to physics educators nationwide. By blending core physics education with hands-on applications, the technology bridges science, technology, engineering, and mathematics (STEM) education gaps and offers scalable resources aligned with NGSS and AP Physics standards. Pilot studies demonstrated a 98% improvement in student understanding of kinematics. By year three, the platform aims to increase AP Physics pass rates by 20% in participating schools and expand into five states, helping address the projected shortage of 186,000 engineers by 2031. This mission-critical drone simulation with embedded robotics framework helps prepare students to succeed in STEM education. This Small Business Innovation Research (SBIR) Phase II project addresses the foundational physics and engineering skills necessary to prepare students for STEM careers in advanced manufacturing and automation. The project leverages advancements in artificial intelligence (AI) and robotics to create an innovative bidirectional reinforcement learning curriculum to provide students with a dynamic, hands-on platform to master applied physics concepts such as force, motion, energy systems, and electromagnetic principles, while simultaneously advancing the autonomous capabilities of robotic systems. The research objectives include completion of the adaptive, AI-assisted platform that enables students to translate physics concepts into Python programming through the integration of machine learning algorithms with drones and robotic systems employed as interactive tools for both teaching and learning. This approach reinforces basic physics principles in real-world mission-critical scenarios. The research employs a dual-learning methodology as students refine their understanding of physics and programming while collaboratively improve robotic performance in simulated and physical environments. The anticipated technical results include a measurable improvement in student proficiency in physics and programming to provide scalable solutions and bridge gaps in STEM education and workforce readiness. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Lindsay Portnoy
StatusActive
Effective start/end date07/15/25 → 06/30/27

Funding

  • SBIR Phase II: $1,025,369.00

Active Fiscal Year

  • FY2027
  • FY2026
  • FY2025

Start Fiscal Year

  • FY2025

TIP Programs

  • SBIR Phase II

Small Business

  • Yes

Key Technology Areas

  • Super Intelligence
  • (confidence score: 100%)
  • Robotics and Advanced Manufacturing
  • (confidence score: 100%)

Technology Foci

  • Robotics
  • (confidence score: 100%)
  • Autonomy
  • (confidence score: 99%)

Congressional District at Award

  • District n. 14 of Florida

Current Congressional District

  • District n. 14 of Florida

United States

  • Florida

Core Based Statistical Area (CBSA)

  • Tampa-St. Petersburg-Clearwater, FL

County

  • County: Pinellas, FL

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint. Learn more about Elsevier's Fingerprint Engine here: https://beta.elsevier.com/products/elsevier-fingerprint-engine