Welcome to PeARL lab website! Our research focuses on developing machine learning algorithms and their application to robot autonomy and physical Human-Robot Interaction. Our group's research interests include Learning from Demonstration, Learning Reactive Behaviors, and Reinforcement Learning.

• May 22, 2019 - Our team, RoboHawks, got second place in FetchIt! Robotics Challenge
• Jan 26, 2019 - Our paper was accepted at ICRA 2019
• Dec 31, 2018 - Funded PhD positions in Robotics [Closed]
• Dec 30, 2018 - Multiple funded Research Assistantships [Apply][Apply]
• Nov 27, 2018 - Our journal paper on TLGC was accepted

• Archives

Most recent publications

• Skill Acquisition via Automated Multi-Coordinate Cost Balancing [more]
• Trajectory-based Skill Learning using Generalized Cylinders [more]
• A Large-Scale Benchmark Study Investigating the Impact of User Experience, Task Complexity, and Start Configuration on Robot Skill Learning [more]

• All Publications

Welcome to PeARL lab website! Our research focuses on developing machine learning algorithms and their application to robot autonomy and physical Human-Robot Interaction. Our group's research interests include Learning from Demonstration, Learning Reactive Behavior, and Reinforcement Learning.

• 

  Trajectory Learning using Generalized Cylinders (TLGC)

  A Learning from Demonstration approach for trajectory-based skill learning.

• 

  Visuospatial Skill Learning

  A Learning from Demonstration approach for goal-based skill learning.

• 

  Failure Recovery for Autonomous Robots

  A direct policy search for discovering new policies to overcome thruster failures in Autonomous Underwater Vehicles (AUVs)