Co-founder of Seattle Laboratory for Robotics. I completed a post-doc with Sham Kakade at the end of 2021. I attained my PhD in 2019 at UW with Emo Todorov. My primary area of focus is enabling intelligent systems through the automated discovery of solutions and mastery through experience. Another area of focus is deploying these intelligent entities to embody robotic systems. My undergraduate degree was in electrical & computer engineering and biomedical engineering at Carnegie Mellon.
Publications and Preprints
BAM: Bayes with Adaptive Memory
Josue Nassar, Jennifer Brennan, Ben Evans, Kendall Lowrey
International Conference on Learning Representations (ICLR) 2022; arXiv:2202.02405
Faster Policy Learning with Continuous-Time Gradients
Samuel Ainsworth, Kendall Lowrey, John Thickstun, Zaid Harchaoui, Siddhartha Srinivasa
Learning for Dynamics and Control (L4DC) 2021; pdf
Lyceum: An efficient and scalable ecosystem for robot learning
Colin Summers, Kendall Lowrey, Aravind Rajeswaran, Siddhartha Srinivasa, Emanuel Todorov
Learning for Dynamics and Control (L4DC) 2020; pdf
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch
International Conference on Learning Representations (ICLR) 2019; arXiv:1811.01848
Reinforcement learning for non-prehensile manipulation: Transfer
from simulation to physical system
Kendall Lowrey, Svetoslav Kolev, Jeremy Dao, Aravind Rajeswaran, Emanuel Todorov
IEEE SIMPAR 2018, (Best paper award); arXiv:1803.10371
Towards Generalization and Simplicity in Continuous Control
Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham Kakade
Neural Information Processing Systems (NIPS) 2017; arXiv:1703.02660
Real-time state estimation with whole-body multi-contact dynamics:
a modified UKF approach
Kendall Lowrey, Jeremy Dao, Emanuel Todorov
Humanoid Robots (Humanoids), 2016; pdf
Ensemble-CIO: Full-body dynamic motion planning that transfers to physical humanoids
Igor Mordatch, Kendall Lowrey, Emanuel Todorov
Intelligent Robots and Systems (IROS), 2015; pdf
Interactive control of diverse complex characters with neural networks
Igor Mordatch, Kendall Lowrey, Galen Andrew, Zoran Popovic, Emanuel Todorov
Neural Information Processing Systems (NIPS) 2015; pdf
Physically-consistent sensor fusion in contact-rich behaviors
Kendall Lowrey, Svetoslav Kolev, Yuval Tassa, Tom Erez, Emanuel Todorov
Intelligent Robots and Systems (IROS), 2014; pdf
An integrated system for real-time model predictive control of humanoid robots
Tom Erez, Kendall Lowrey, Yuval Tassa, Vikash Kumar, Svetoslav Kolev, Emanuel Todorov
Humanoid Robots (Humanoids), 2013; pdf
Teaching
CSE599G: Deep Reinforcement Learning (Instructor)
I co-taught a course on deep reinforcement learning at UW in Spring 2018 Aravind Rajeshwaran. The course took a broad perspective on reinforcement learning and covers techniques ranging from tabular dynamic programming methods to policy gradient methods, including emphasis on trajectory optimization. I co-designed the course structure and all the teaching material. This course is inspired by the course offerings of Emo Todorov, Balaraman Ravindran, and Sergey Levine.
CSE490R: Robotics (Teaching Assistant)
This undergraduate course involved full stack robotics, including topics such as state estimation, model learning, and perception and control, all implemented on a 1/10th sized autonomous car. The final project involved teams designing algorithms to navigate an unknown course without human input.