Robotics is the science of the cyber-physical interface – the connection between the cyber-world of information and computation and the real-world of things, masses, and forces.
Our research is focused on developing new motion planning and control algorithms that enable robots to interact with the real world in challenging circumstances.
We’re investigating new technologies to ensure safe and efficient movement through the environment, from wheeled and legged ground robots, to fixed and rotary-wing aerial robots, and surface and submersible marine robots,
We’re also developing novel mechanisms and manipulation technologies to enable robot arms and hands to perform productive tasks.
Our system identification and machine learning techniques allow robots to learn to predict the future based on past experience and use these predictions for robust and reliable planning and control.
This project aims to make machine-learning of dynamic system models reliable, accurate, and secure. Robots and other autonomous machines use models of the real world to predict the result of their actions and make decisions, but existing methods to learn such models from data are unreliable in many cases and can be easily fooled.
The outcomes of this project will be new models and algorithms that ensure safety and increase accuracy of models learned from data. This will benefit robotics, control engineering, infrastructure automation, and other fields that demand the capability to model physical systems from limited data. It will also improve cybersecurity by making learning algorithms resilient to deliberate attacks with false data
