Joseph Camp
Southern Methodist University, TX·Computer Science
Many students lack access to advanced training in artificial intelligence (AI) and autonomous systems, especially in regions where such tools are hard to reach. This project develops a hands-on AI curriculum built around teams of drones, using shared computing through the National AI Research Resource (NAIRR) Pilot, and draws its problems from the research needs of national laboratories and universities.
- Fields
Computer Science
Engineering
Education Research
- Topics
artificial intelligence
AI education
federated learning
- Grants
- 1 known grant, through May 2027
What they work on
- Develop an AI curriculum covering federated learning, explainable AI, homomorphic encryption and neural networks, taught through lectures, exercises and simulations and shared via the NAIRR Pilot.
- Train students to apply federated learning, where drones jointly improve an AI model without sharing raw data, to drone swarms using NAIRR Pilot computing platforms.
- Teach privacy-preserving data sharing with homomorphic encryption and blockchain-based smart contracts, and run field exercises where students use AI to plan missions and control autonomous drones.
More about the research
The curriculum covers four areas. First, lectures, exercises and simulations teach advanced AI topics, including neural networks, explainable AI (methods that show why a model made a decision) and federated learning. Second, students apply federated learning, in which several devices improve a shared AI model without sending their raw data to one place, to drone swarms using cloud-based or specialized computing platforms in the NAIRR Pilot. Third, the course teaches privacy-preserving data sharing, such as homomorphic encryption, which allows calculations on encrypted data, and blockchain-based smart contracts, to secure data and model training across distributed systems. Fourth, field-based training has students use AI models to control autonomous drones in changing environments, including mission planning, real-time decision-making and secure communication. The curriculum materials will be shared broadly through the NAIRR Pilot.
Why it matters
Students in regions with little access to advanced computing could gain practical skills in AI and autonomous drones through shared curriculum and NAIRR Pilot resources. This may help prepare a workforce able to build secure, privacy-preserving AI for distributed systems such as drone teams used in real-world missions.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Jane Huang
University of Notre Dame, IN·Computer Science
Design human-centered interfaces that help teams supervise autonomous drone swarms in time-critical tasks such as disaster response, using cognitive work analysis and iterative user-centered design.
Qi Lu
University of Texas Rio Grande Valley, TX·Computer Science
Develop a decentralized algorithm that plans multiple shortest routes at once, so that UAVs (aerial drones) can explore promising locations on demand, collecting data quickly while saving energy for the ground robots in the swarm.
Miao Pan
University of Houston, TX·Computer Science
Design software-hardware co-designed model pruning and adaptive quantization schemes that exploit the sparsity of model updates to reduce computation and memory access during federated learning on a single 5G mobile device.
The school
Southern Methodist University: 7 labs on PI Pages, $63M a year on research, 136 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.