In this research project, we aim to investigate model-free reinforcement learning algorithms under the high-level system specifications.
See this page for more details about our work.
In this research project, we aim to investigate the underlying compositional structure of the reactive games to develop efficient algorithms and a toolbox suitable for online reactive planning on robots such as driverless cars.
See this page for more details on reactive synthesis, compositional synthesis and our work.
The goal of this project is the creation of soft, snake-like robots that can navigate through real environments with confined spaces, fragile objects, clutter, rough and/or granular surfaces. This project is lead by Prof. Cagdas Onal (PI) from WPI Soft Robotics Lab and Prof. Jie Fu (Co-PI) from Control and Intelligent Robotics Lab (CIRL). Specifically, we plan to develop adaptive and robust control for the soft snake robotics given the difficulty-to-model dynamics. We will investigate learning-based control and stochastic planning to enable the snake robot effectively interacting with obstacles, and autonomously navigating under uneven and open environments under high-level, complex task specifications. When successful, we expect to deploy such a system for geo-exploration and search-and-rescue.
Provably safe autonomous navigation
In collaboration with WPI Embedded Computing Laboratory, our team will develop provably safe autonomous navigation by integrating temporal logic planning, nonlinear control, and formal verification.