Sumit Patidar

Singapore

Hello and welcome! 👋

I’m a Robotics Engineer at the Dyson Robotics Research Lab in Singapore 🇸🇬, where I work on developing the next generation of autonomous robots. My interests span robot learning, robot manipulation, imitation learning, reinforcement learning, and robotics software, with the goal of building intelligent systems that can robustly interact with the real world.

This website is where I document my projects, research, technical notes, and occasional tutorials on robotics, machine learning, and software engineering. I enjoy sharing what I learn along the way and hope these resources are useful to others.

Outside of robotics, I enjoy staying active 💪 through sports 🏀⚽, playing chess ♟️, hiking 🥾, reading 📚 and traveling ✈️.

Thanks for stopping by!

news

Jan 16, 2026	Judging TECH NGO’s AI-Powered Search & Rescue Challenge at SUTD 🌏🤖
Dec 11, 2025	Judging Intelligent Robotics (30.119) at SUTD 🤖
Oct 29, 2025	Attended ROSCon25 in Singapore!
Aug 15, 2025	Judging the SUTD 30.007 Engineering Design Innovation Showcase 🚀
May 28, 2025	Inspiring Next Generations of Engineers at Linhua Primary School 💫

latest posts

Jun 25, 2026	Numerically Stable Softmax and Cross-Entropy
May 20, 2026	Unlimited Zotero PDF Sync with Google Drive or OneDrive Using ZotMoov
Oct 29, 2025	Reflections from ROSCon 2025 – Singapore 🇸🇬

selected publications

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

Xiao Ma, Sumit Patidar, Iain Haughton, and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Project page , Jun 2024

Bib HTML

@inproceedings{Ma_2024_CVPR,
  author = {Ma, Xiao and Patidar, Sumit and Haughton, Iain and James, Stephen},
  title = {Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2024},
  pages = {18081-18090},
}

Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation

Eugene Teoh, Sumit Patidar, Xiao Ma, and 1 more author

arXiv preprint arXiv:2407.07868. Project page , 2024

Bib HTML

@article{teoh2024green,
  title = {Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation},
  author = {Teoh, Eugene and Patidar, Sumit and Ma, Xiao and James, Stephen},
  journal = {arXiv preprint arXiv:2407.07868},
  year = {2024},
}

In-Hand Cube Reconfiguration: Simplified

Sumit Patidar, Adrian Sieler, and Oliver Brock

In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Project page , 2023

DOI Bib HTML

@inproceedings{10341521,
  author = {Patidar, Sumit and Sieler, Adrian and Brock, Oliver},
  booktitle = {2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {In-Hand Cube Reconfiguration: Simplified},
  year = {2023},
  volume = {},
  number = {},
  pages = {8751-8756},
  keywords = {Deep learning;Dynamics;Robustness;End effectors;Planning;Complexity theory;Complex systems},
  doi = {10.1109/IROS55552.2023.10341521},
}