Email Website LinkedIn Google Scholar Twitter/X GitHub Anonymous feedback

Gavin Cangan

About Me

I am a roboticist and PhD candidate at ETH Zürich, working at the intersection of sensing, control, and learning for dexterous manipulation using soft robots. My focus is on giving robots the kind of proprioception and feedback humans take for granted through a mix of modeling, machine learning, and good old creative engineering.

I have worked across academia, industry, and startups, from writing safety-critical software at Bosch and shipping production code at Dexai, to hacking together demos that got featured on Swiss national television and helped kick off a venture-backed startup. I enjoy building things that feel intuitive to users, to robots, or ideally, to both :)

Originally from Kanyakumari, at the southern tip of India, I’ve lived and worked in the U.S. and Switzerland. I quite like the Feynman approach to learning: understand deeply, explain clearly, and don’t bluff.

Portfolio & Projects

Here are some videos showcasing projects I’ve been involved in:

ETH Zürich - Soft Robotics Lab Research

Dexterous Hand Policy Learning

Overview of our Humanoids 2023 paper Getting the Ball Rolling, showing a tendon-driven hand trained in simulation with reinforcement learning and then transferred to hardware for in-hand ball rolling.

Soft Robot Proprioception

Demonstrates our RA-L 2023 approach combining multi-tap resistive sensing with FEM-based modeling to estimate the shape and forces of soft manipulators.

Marker-less Aerial Grasping

Shows the IROS 2023 work on autonomous aerial grasping with a drone-mounted soft gripper. The system performs onboard segmentation and rapid grasp planning without requiring object markers.

Faive Hand Dexterity Demo

Compilation of the Faive soft hand performing everyday tasks—pouring beer, solving a Rubik’s Cube, typing, playing piano and gently handling an egg.

Hackathon Projects

LePuppet - Emotional AI Robot

Weekend hackathon project exploring generative AI for a sock puppet that talks and moves expressively.

Dexai Robotics - Kitchen Automation

In the following projects, I worked primarily on the multi-robot motion planning, tool changing, and parts of the vision and learning pipeline.

Alfred Sous-Chef - Poke Bowl

Alfred prepares a poke bowl end to end—dispensing rice, fish, greens and sauces while switching tools.

Alfred Sous-Chef - Salad Assembly

Demonstrates the robot’s full salad assembly pipeline: bowl pickup, ingredient dispensing, lidding and labeling.

Multi-Robot Salad Team

Four Alfred robots coordinate to prepare a single salad order together.

Research Interests

My primary research areas include:

Experience

Education

Work History

Publications

† indicates shared first/equal contribution. For full list, visit my Google Scholar.

  1. E. Bauer, B. G. Cangan, and R. K. Katzschmann. Autonomous marker-less rapid aerial grasping. In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 6395-6402. IEEE, 2023.
  2. T. J. Buchner, S. Rogler, S. Weirich, Y. Armati, B. G. Cangan, J. Ramos, S. T. Twiddy, D. M. Marini, A. Weber, D. Chen, et al. Vision-controlled jetting for composite systems and robots. Nature, 623(7987):522-530, 2023.
  3. C. C. Christoph, M. Eberlein, F. Katsimalis, A. Roberti, A. Sympetheros, M. R. Vogt, D. Liconti, C. Yang, B. G. Cangan, R. J. Hinchet, et al. Orca: An open-source, reliable, cost-effective, anthropomorphic robotic hand for uninterrupted dexterous task learning. arXiv preprint arXiv:2504.04259, 2025.
  4. C. S. Plata, C. Rosel, B. G. Cangan, H. Alagi, B. Hein, R. K. Katzschmann, R. Fernández, Y. Mojtahedi, and S. E. Navarro. Model-based capacitive touch sensing in soft robotics: Achieving robust tactile interactions for artistic applications. IEEE Robotics and Automation Letters, 2025.
  5. B. G. Cangan†, L. Heintzman, A. Hashimoto, N. Abaid, and R. K. Williams. Anticipatory human-robot path planning for search and rescue. Workshop on Informed Scientific Sampling in Large-scale Outdoor Environments, IROS., 2019.
  6. B. G. Cangan†, S. E. Navarro†, B. Yang, Y. Zhang, C. Duriez, and R. K. Katzschmann. Model-based disturbance estimation for a fiber-reinforced soft manipulator using orientation sensing. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
  7. S. Tian, B. G. Cangan, S. E. Navarro, A. Beger, C. Duriez, and R. K. Katzschmann. Multi-tap resistive sensing and fem modeling enables shape and force estimation in soft robots. IEEE Robotics and Automation Letters, 2023.
  8. Y. Toshimitsu, B. Forrai, B. G. Cangan, U. Steger, M. Knecht, S. Weirich, and R. K. Katzschmann. Getting the ball rolling: Learning a dexterous policy for a biomimetic tendon-driven hand with rolling contact joints. In 2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids), pages 1-7. IEEE, 2023.
  9. W. Zhang†, B. G. Cangan†, T. Buchner, A. M. Kübler, R. Asmus, and R. K. Katzschmann. Task-defined pulley design for nonlinearly coupled tendon-driven actuation. In 2024 7th IEEE-RAS International Conference on Soft Robotics (RoboSoft). IEEE, 2024.
  10. H. Zheng, S. Pinzello, B. G. Cangan, T. J. Buchner, and R. K. Katzschmann. Vision-based online key point estimation of deformable robots. Advanced Intelligent Systems, 2024.

Last updated: May 2025. Theme: Cayman.