Minghui (Scott) Zhao, a third-year Ph.D. student in Columbia Engineering’s Intelligent and the lab Connected Systems Laboratory (ICSL), won second place in the Student Research Competition at the 30th ACM International Conference on Mobile Computing and Networking (MobiCom ’24) in Washington, D.C. The award recognizes his team’s work on connecting foundation models with the physical world using reconfigurable drone systems.
Zhao’s winning project, EmbodiedRDA (Embodied Reconfigurable Drone Agent), addresses a key challenge in AI: enabling foundation models to interact with real-world environments. While AI systems excel at processing text and digital content, they often struggle with physical-world applications due to limited sensor configurations and static deployment locations.
EmbodiedRDA offers a novel solution through a custom-designed drone platform capable of autonomously swapping sensors and actuators based on task requirements. The system includes:
- A modular drone design that autonomously reconfigures its sensors and actuators
- A ground station built from a modified 3D printer for precise payload management
- A foundation-model-powered agent that processes user commands and controls the drone’s actions
The system demonstrated practical applications such as optimizing room temperatures, detecting chemical spills, locating objects, and delivering items. By combining foundation models with reconfigurable hardware, EmbodiedRDA represents a step toward more adaptable and capable AI systems that can actively engage with the physical world.
This recognition follows the project’s success in the conference’s demo track, where it received the Best Demo Runner-Up Award.
