Caelan Garrett

Robotics, planning, and learning

Caelan Garrett

Senior Research Scientist at NVIDIA Research's Seattle Robotics Lab, working on robot planning and learning.

Google Scholar NVIDIA Profile MIT Homepage GitHub
Email
[first-initial][last-name]@nvidia.com
Focus
Task and motion planning, manipulation, robot learning
Previously
PhD, MEng, and BS degrees from MIT EECS

Research

Robot planning and learning

I primarily research Task and Motion Planning (TAMP): the intersection of classical planning from artificial intelligence and motion planning from robotics.

Before joining NVIDIA Research, I was a PhD student in the Learning and Intelligent Systems Group within MIT CSAIL, advised by Tomás Lozano-Pérez and Leslie Pack Kaelbling.

Open-world task and motion planning examples

Recent work

Recent papers

  1. ScheduleStream: Temporal Planning with Samplers for GPU-Accelerated Multi-Arm Task and Motion Planning & Scheduling. Caelan Garrett and Fabio Ramos. ICRA, 2026.
  2. Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training. Shuo Cheng, Liqian Ma, Zhenyang Chen, Ajay Mandlekar, Caelan Garrett, and Danfei Xu. NeurIPS, 2025.
  3. The Reality Gap in Robotics: Challenges, Solutions, and Best Practices. Elie Aljalbout et al. Annual Review of Control, Robotics, and Autonomous Systems, 2026.
  4. SkillGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment. Caelan Garrett, Ajay Mandlekar, Bowen Wen, and Dieter Fox. CoRL, 2024.
  5. NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors. Shuo Cheng, Caelan Garrett, Ajay Mandlekar, and Danfei Xu. CoRL, 2024.

See Google Scholar or the NVIDIA Profile for the current publication list.

Publications

Foundational papers

  1. Integrated Task and Motion Planning. Caelan Reed Garrett, Rohan Chitnis, Rachel Holladay, Beomjoon Kim, Tom Silver, Leslie Pack Kaelbling, and Tomás Lozano-Pérez. Annual Review of Control, Robotics, and Autonomous Systems, 2021.
  2. PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning. Caelan Reed Garrett, Tomás Lozano-Pérez, and Leslie Pack Kaelbling. ICAPS, 2020.
  3. Online Replanning in Belief Space for Partially Observable Task and Motion Problems. Caelan Reed Garrett, Chris Paxton, Tomás Lozano-Pérez, Leslie Pack Kaelbling, and Dieter Fox. ICRA, 2020.
  4. Sample-Based Methods for Factored Task and Motion Planning. Caelan Reed Garrett, Tomás Lozano-Pérez, and Leslie Pack Kaelbling. Robotics: Science and Systems, 2017.
  5. FFRob: An Efficient Heuristic for Task and Motion Planning. Caelan Reed Garrett, Tomás Lozano-Pérez, and Leslie Pack Kaelbling. WAFR, 2014.

Software

Selected open-source robotics tools

ScheduleStream GPU-accelerated multi-arm task and motion planning pddlstream Task and motion planning pybullet-planning PyBullet robot planning motion-planners Motion planning algorithms SS-Replan Real-world TAMP pyplanners STRIPS planners

Video

Talks and tutorials

Robot Planning and Learning YouTube Talk Lazy Belief-Space Task and Motion Planning University of Washington Robotics Colloquium, 2020 Task and Motion Planning 3rd Summer School on Cognitive Robotics, 2019

Blogs and press

Coverage and articles

R2D2: Improving Robot Manipulation with Simulation and Language Models Asawaree Bhide, NVIDIA Technical Blog, December 2025 R2D2: Perception-Guided Task & Motion Planning for Long-Horizon Manipulation Raffaello Bonghi and Edith Llontop, NVIDIA Technical Blog, November 2025 New system enables robots to solve manipulation problems in seconds Adam Zewe, MIT News, June 2025 R2D2: Adapting Dexterous Robots with NVIDIA Research Workflows and Models Asawaree Bhide, Yichao Pan, and Nathan Ratliff, NVIDIA Technical Blog, April 2025 Replanning for Success Lauren Finkle, NVIDIA Blog, May 2020

Experience

Employment

  • NVIDIA Research, Seattle Robotics Lab Senior Research Scientist, 2021 - present
  • NVIDIA Research, Seattle Robotics Lab Robotics Research Intern, 2019
  • Amazon Robotics Planning and Scheduling Research Intern, 2018
  • Optimus Ride Computer Vision and Perception Intern, 2017
  • Google Ad Quality Intern, 2014

Education

MIT

Personal

Outside the lab

I sang in and was president of the MIT Chorallaries, MIT's first coed a cappella group. I am also a parent of two Siberian Husky mixes, Rey and Niko.

Rey and Niko