I’m an engineer interested in systems that can intelligently interact with the real world. That started with VEX robotics in high school and continued at UMass Lowell, where I spent four years in the Persistent Autonomy and Robot Learning (PeARL) Lab — from my sophomore year through my Master’s. I then worked on embedded systems and electronics hardware at Draper Labs in Cambridge, MA, and I’m now starting as a Perception Engineer at Magna Electronics on the on-board vehicle tracking team.
Most of my personal projects are currently reinforcement learning based, training agents with my own library and doing sim2real transfer to an SO-ARM101 robot I have. You can find these under the Projects tab.
Robot skill learning and execution in uncertain and dynamic environments is a challenging task. This paper proposes an adaptive framework that combines Learning from Demonstration (LfD), environment state prediction, and high-level decision making. Proactive adaptation prevents the need for reactive adaptation, which lags behind changes in the environment rather than anticipating them. We propose a novel LfD representation, Elastic-Laplacian Trajectory Editing (ELTE), which continuously adapts the trajectory shape to predictions of future states. Then, a high-level reactive system using an Unscented Kalman Filter (UKF) and Hidden Markov Model (HMM) prevents unsafe execution in the current state of the dynamic environment based on a discrete set of decisions. We first validate our LfD representation in simulation, then experimentally assess the entire framework using a legged mobile manipulator in 36 real-world scenarios. We show the effectiveness of the proposed framework under different dynamic changes in the environment. Our results show that the proposed framework produces robust and stable adaptive behaviors.
@inproceedings{donald2024adaptive,title={An Adaptive Framework for Manipulator Skill Reproduction in Dynamic Environments},author={Donald, Ryan and Hertel, Brendan and Misenti, Stephen and Yan, Gao and Azadeh, Reza},booktitle={2024 21st International Conference on Ubiquitous Robots (UR)},year={2024},month=jun,}
