Kota Kondo

Stanford Multi-Robot Systems Lab | VLMs | VLAs | World Models | Manipulation | Humanoids

kota-drone.jpg

I am a postdoc in the Multi-Robot Systems Lab (MSL) at Stanford University, working with Professor Mac Schwager. My research focuses on vision-language models (VLMs), vision-language-action models (VLAs), and world models for robot manipulation and humanoid robots.

I received my PhD from MIT AeroAstro in 2026, where I worked in the Aerospace Controls Lab (ACL) under the guidance of Professor Jonathan How. My PhD research focused on safe and fast trajectory planning in unknown dynamic environments, including spatiotemporal trajectory planning, multiagent trajectory planning robust to communication delays, heterogeneous robot teams, learning-based multiagent trajectory planning utilizing diffusion models, and perception-aware and uncertainty-aware trajectory planning. Before that, I worked on detumbling an under-actuated spacecraft with a single-axis magnetic actuator and quadcopter path planning with an onboard EMPC controller.

SANDO: Helping Robots Avoid the Unexpected (MIT)

news

Oct 2026 SANDO featured in MIT News: Planning system ensures a robot’s flight path will remain collision-free.
Oct 2026 SANDO accepted to IEEE Transactions on Robotics (T-RO). Paper / Code / Video
Oct 2026 Started a postdoc at the Stanford Multi-Robot Systems Lab (MSL) with Prof. Mac Schwager, working on VLMs, VLAs, and world models for manipulation and humanoid robots.
Sep 2026 Presented Multi MIGHTY at the IROS 2026 Workshop on Tightly Coupled Physical Interaction and Collaboration in Multi-Robot Systems.
Sep 2026 Gave an invited talk at the University of Pennsylvania.
Jul 2026 STORM accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026. Paper / Video
Jul 2026 Successfully defended my PhD thesis Safe and Fast Trajectory Planning in Unknown Dynamic Environments. Video
Jul 2026 SANDO conditionally accepted to IEEE Transactions on Robotics (T-RO). Paper / Code / Video
May 2026 MIGHTY featured in MIT News: New research enables a robot to chart a better course.
Apr 2026 Submitted SANDO: Safe Autonomous Trajectory Planning for Dynamic Unknown Environments to IEEE Transactions on Robotics (T-RO). Paper / Code / Video
Apr 2026 MIGHTY accepted to IEEE Robotics and Automation Letters (RA-L). Paper / Code
Nov 2025 Submitted MIGHTY: Hermite Spline-based Efficient Trajectory Planning to IEEE Robotics and Automation Letters. Paper / Code
Sep 2025 Paper on Efficient Navigation in Unknown Indoor Environments with Vision-Language Models accepted to IROS 2025 OWN Workshop.
Apr 2025 Submitted DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments to IEEE Transactions on Robotics. Paper / Code
Sep 2024 Submitted PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner to IEEE ICRA 2024. Paper
Aug 2024 Selected as MathWorks Fellow. MathWorks fellowship provides support to graduate students within the School of Science with a preference for students who are active users of MATLAB and/or Simulink.
Jul 2024 REAL accepted to IEEE Conference on Decision and Control (CDC) 2024.
Jun 2024 SOS-Match accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024.
Jan 2024 PUMA accepted to IEEE International Conference on Robotics and Automation (ICRA) 2024.
Dec 2023 Robust MADER published in IEEE Robotics and Automation Letters (RAL).
Jun 2023 Won Best Poster Award at ICRA 2023 CAMRS Workshop for Robust MADER.
Mar 2023 Robust MADER featured in MIT News: New algorithm keeps drones from colliding in midair. Also covered by MIT AeroAstro and TechCrunch.
Jan 2023 Robust MADER accepted to IEEE International Conference on Robotics and Automation (ICRA) 2023.
Jun 2021 Paper on Nonlinear Model Predictive Detumbling of Small Satellites published in Journal of Guidance, Control, and Dynamics (JGCD).

projects

project thumbnail

SANDO

safe autonomous trajectory planning for dynamic unknown environments
project thumbnail

STORM

robust dynamic object detection in cluttered indoor scenes via learned spatiotemporal cues
project thumbnail

MIGHTY

Hermite spline-based efficient trajectory planning
project thumbnail

DYNUS

uncertainty-aware trajectory planner in dynamic unknown environments
project thumbnail

VLM Navigation

efficient navigation in unknown indoor environments with vision-language models
project thumbnail

CGD

constraint-guided diffusion policies for UAV trajectory planning
project thumbnail

REAL

resilience and adaptation using large language models on autonomous aerial robots
project thumbnail

SOS-Match

segmentation for open-set robust correspondence search and robot localization
project thumbnail

PUMA

fully decentralized uncertainty-aware multiagent trajectory planner with image segmentation-based frame alignment
project thumbnail

Robust MADER

fully decentralized asynchronous multiagent trajectory planner robust to communication delays
project thumbnail

PRIMER

perception-aware robust learning-based multiagent trajectory planner
project thumbnail

Satellite Detumbling

nonlinear model predictive detumbling of under-actuated satellites with a single-axis magnetic actuator

publications

  1. sando.gif
    SANDO: Safe Autonomous Trajectory Planning for Dynamic Unknown Environments
    K. Kondo, J. Tordesillas, and J. P. How
    IEEE Transactions on Robotics, 2026
    arXiv Code Video
  2. storm.png
    Robust Dynamic Object Detection in Cluttered Indoor Scenes via Learned Spatiotemporal Cues
    J. Rached Viso, Y. Jia, K. Kondo, and 1 more author
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
    arXiv Video
  3. mighty.gif
    MIGHTY: Hermite Spline-Based Efficient Trajectory Planning
    K. Kondo, Y. Wu, V. Kumar, and 1 more author
    IEEE Robotics and Automation Letters, 2026
    arXiv Code Video
  4. dynus.gif
    DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments
    K. Kondo, M. Peterson, N. Rober, and 5 more authors
    arXiv preprint arXiv:2504.16734, 2025
    arXiv Code Video
  5. vlm_nav.png
    Efficient Navigation in Unknown Indoor Environments with Vision-Language Models
    D. Schwartz, K. Kondo, and J. P. How
    In IROS 2025 OWN Workshop, 2025
    arXiv Code
  6. cgd.png
    CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning
    K. Kondo, A. Tagliabue, X. Cai, and 4 more authors
    arXiv preprint arXiv:2405.01758, 2024
    arXiv
  7. real.png
    REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robots
    A. Tagliabue, K. Kondo, T. Zhao, and 3 more authors
    In IEEE Conference on Decision and Control (CDC), 2024
    arXiv
  8. sosmatch.png
    SOS-Match: Segmentation for Open-Set Robust Correspondence Search and Robot Localization in Unstructured Environments
    J. Kinnari, A. Thomas, P. C. Lusk, and 2 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    arXiv Code
  9. puma.gif
    PUMA: Fully Decentralized Uncertainty-aware Multiagent Trajectory Planner with Real-time Image Segmentation-based Frame Alignment
    K. Kondo, C. Tewari, M. Peterson, and 4 more authors
    In IEEE International Conference on Robotics and Automation (ICRA), 2024
    arXiv Code Video
  10. rmader.gif
    Robust MADER: Decentralized Multiagent Trajectory Planner Robust to Communication Delay in Dynamic Environments
    K. Kondo, R. Figueroa, J. Rached, and 3 more authors
    IEEE Robotics and Automation Letters, 2023
    arXiv Code Video
  11. rmader.gif
    Robust MADER: Decentralized and Asynchronous Multiagent Trajectory Planner Robust to Communication Delay
    K. Kondo, J. Tordesillas, R. Figueroa, and 4 more authors
    In IEEE International Conference on Robotics and Automation (ICRA), 2023
    arXiv Code Video
  12. primer.png
    PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner
    K. Kondo, C. Tewari, A. Tagliabue, and 3 more authors
    In IEEE International Conference on Robotics and Automation (ICRA), 2024
    arXiv Video
  13. detumbling.png
    Nonlinear Model Predictive Detumbling of Small Satellites with a Single-Axis Magnetic Actuator
    K. Kondo, I. Kolmanovsky, Y. Yoshimura, and 3 more authors
    Journal of Guidance, Control, and Dynamics, 2021
    arXiv
  14. detumbling.png
    Pulse Width Modulation Method Applied to Nonlinear Model Predictive Control on an Under-actuated Small Satellite
    K. Kondo, Y. Yoshimura, S. Nagasaki, and 1 more author
    In AIAA SciTech Forum, 2021
    arXiv
  15. detumbling.png
    Model Predictive Approach for Detumbling an Underactuated Satellite
    K. Kondo, Y. Yoshimura, M. Bando, and 2 more authors
    In AIAA SciTech Forum, 2020
    arXiv
  16. detumbling.png
    Detumbling with Model Predictive Control for an Underactuated Small Satellite
    K. Kondo, Y. Yoshimura, M. Bando, and 2 more authors
    In AIAA Region VII Australia/International Student Conference, 2019
    HTML