Research activities in the Distributed Control and Dynamical Systems (DCDS) laboratory are focused on the science of autonomy, which is about closing the gap between sensing and action in robots. The goal is to create a robot that can sense its environment, collect data, choose the most relevant details, infer some form of meaning, come to conclusions, make decisions, form plans, and execute tasks.
For example, at the front end of the sensing-to-action progression, robots need to perceive their environment. Streaming images from high-frame-rate cameras might provide up to 1,000 frames per second from a single robot, resulting in gigabytes of imaging data per second. Networks of robots such as drone swarms need to make decisions based on massive amounts of data collected and passed between individual agents. Processing the raw data is costly, so efficient networks of agents need pre-processing algorithms that can identify only relevant information to guide motion and action planning.
Below: Prof. Motee (seated) works with students in the AIR lab on Mountaintop Campus.
This research is led by Prof. Nader Motee and has been supported by the Office of Naval Research, Air Force Office of Research, and National Science Foundation.
Read more about Prof. Motee’s work on robot autonomy including fast feature selection for visual navigation, multi-agent image classification, and predicting the risk of collision and detachment in vehicle platooning.