Max Robotics — Global Service Robot Directory + US Certification

About

Deirdre Quillen is a robotics and machine learning researcher whose work sits at the intersection of deep reinforcement learning, computer vision, and robotic manipulation. She has made significant contributions to teaching robots to interact with the physical world through data-driven approaches, with a particular focus on grasping and hand-eye coordination. Quillen's most influential work includes her contribution to QT-Opt (2018), a scalable deep reinforcement learning framework for vision-based robotic grasping that has garnered over 575 citations, demonstrating how large-scale RL can be applied to real-world manipulation challenges. Her earlier work on learning hand-eye coordination through large-scale data collection (2017, 276 citations) helped establish the viability of training robotic systems using monocular image inputs and convolutional neural networks. She also contributed to Meta-World (2019, 282 citations), a now-widely adopted benchmark for evaluating multi-task and meta reinforcement learning algorithms, which has become a standard tool in the research community. Her comparative evaluation of off-policy deep RL methods for robotic grasping further reflects her commitment to rigorous empirical methodology. Across her body of work, Quillen has helped shape how the field approaches scalable, generalizable robot learning.