About

I’m a research scientist at Microsoft Research (MSR) in the Physically Embodied AI and Robotics group. My research interests span robotics, computer vision, machine learning, and human-robot interaction. I’m particularly interested in studying foundation models for robotics, human-in-the-loop robot learning, and reinforcement learning.

I received my Ph.D. from the University of Washington where I worked in the Human Centered Robotics Lab. I was advised by Maya Cakmak and I also work closely with Abhishek Gupta. During grad school, I received an Amazon Science fellowship, and I have worked closely with Amazon Robotics through the UW-Amazon Science Hub. I also spent a summer at the NVIDIA Seattle Robotics Lab led by Dieter Fox.

Before grad school, I was a software engineer at Amazon where I worked on computer vision for autonomous drone delivery. I also co-founded a YCombinator backed startup.

Publications

• Teaching Robots with Show and Tell: Using Foundation Models to Synthesize Robot Policies from Language and Visual Demonstrations

  Michael Murray, Abhishek Gupta, Maya Cakmak.
  Conference on Robot Learning (CoRL), 2024.
  paper poster

• Diffusion-PbD: Generalizable Robot Programming by Demonstration with Diffusion Features

  Michael Murray, Entong Su, Maya Cakmak.
  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
  paper website

• Learning to Grasp in Clutter with Interactive Visual Failure Prediction

  Michael Murray, Abhishek Gupta, Maya Cakmak.
  IEEE International Conference on Robotics and Automation (ICRA), 2024.
  paper website code

• Towards Robustly Picking Unseen Objects From Densely Packed Shelves

  Markus Grotz, Soofiyan Atar, Yi Li, Paolo Torrado, Boling Yang, Nick Walker, Michael Murray, Maya Cakmak, Joshua R Smith.
  RSS Workshop on Perception and Manipulation Challenges for Warehouse Automation, 2023.
  paper website code

• Following Natural Language Instructions for Household Tasks with Landmark Guided Search and Reinforced Pose Adjustment

  Michael Murray, Maya Cakmak.
  IEEE Robotics and Automation Letters (RA-L), 2022.
  paper

• Learning Backchanneling Behaviors for a Social Robot via Data Augmentation from Human-Human Conversations

  Michael Murray, Nick Walker, Amal Nanavati, Patricia Alves-Oliveira, Nikita Filippov, Allison Sauppe, Bilge Mutlu, Maya Cakmak.
  Conference on Robot Learning (CoRL), 2021.
  paper code poster

• Vision-and-Dialog Navigation

  Jesse Thomason, Michael Murray, Maya Cakmak, Luke Zettlemoyer.
  Conference on Robot Learning (CoRL), 2019.
  paper code demo poster