Soft Robotics Lab Project Pages

A list of SRL project websites.

Our Projects with Websites

  1. EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World

    Preprint (arXiv), 2026

    Punamiya et al., Robert K. Katzschmann

    EgoVerse is a living, consortium-scale egocentric dataset capturing diverse human demonstrations across tasks, scenes, and operators worldwide, purpose-built for human-to-robot transfer across embodiments.

  2. A Benchmark of Dexterity for Anthropomorphic Robotic Hands

    Preprint (arXiv), 2026

    Davide Liconti*, Yuning Zhou*, Yasunori Toshimitsu, Ronan Hinchet, Robert K. Katzschmann

    POMDAR is a taxonomy-grounded dexterity benchmark for anthropomorphic hands, measuring task throughput across grasping and manipulation configurations in real and simulated settings.

    *Equal contribution

  3. Simple Models, Real Swimming: Digital Twins for Tendon-Driven Underwater Robots

    Preprint (arXiv), 2026

    Mike Yan Michelis, Nana Obayashi, et al.

    Digital twins for tendon-driven underwater robots, validating simple models with real-world swimming behavior.

  4. SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

    Preprint (arXiv), 2026

    Chenyu Yang*, Denis Tarasov*, et al.

    Sample-efficient real-world dexterous policy fine-tuning with action-chunked critics and normalizing flows.

    *Equal contribution

  5. SORS: A Modular, High-Fidelity Simulator for Soft Robots

    IEEE RoboSoft, 2026

    Manuel Mekkattu*, Mike Yan Michelis*, et al.

    A modular, high-fidelity simulation framework for soft robots focused on contact-rich manipulation and sim-to-real transfer.

    *Equal contribution

  6. Latent Action Diffusion for Cross-Embodiment Manipulation

    IEEE ICRA, 2026

    Erik Bauer, Elvis Nava, Robert K. Katzschmann

    Latent action diffusion for cross-embodiment skill transfer and single-policy multi-robot manipulation control.

  7. mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity

    Preprint (arXiv), 2025

    Elvis Nava, Victoriano Montesinos, Erik Bauer, Benedek Forrai, et al., Robert K. Katzschmann

    A diffusion-based model recipe and data collection protocol for a 16-DoF tendon-driven dexterous hand, achieving up to 93.3% out-of-distribution success rates with emergent self-correcting behaviors.

  8. MAPLE: Encoding Dexterous Robotic Manipulation Priors Learned From Egocentric Videos

    Preprint (arXiv), 2025

    Alexey Gavryushin, Xi Wang, Robert J. S. Malate, Chenyu Yang, Davide Liconti, René Zurbrügg, Robert K. Katzschmann, Marc Pollefeys

    MAPLE learns dexterous manipulation priors from large-scale egocentric videos, producing vision features that enable efficient policy learning and strong zero-shot generalization for dexterous robotic manipulation.

  9. PokeFlex: A Real-World Dataset of Deformable Objects for Robotics

    Preprint (arXiv), 2024

    Jan Obrist*, Miguel Zamora*, Hehui Zheng*, Ronan Hinchet, Firat Ozdemir, Juan Zarate, Robert K. Katzschmann, Stelian Coros

    PokeFlex is a real-world multimodal dataset of 18 deformable objects—including 3D textured meshes, point clouds, RGB images, and depth maps—enabling online mesh reconstruction and sim-to-real transfer for deformable object manipulation.

    *Equal contribution

  10. VQ-ACE: Efficient Policy Search for Dexterous Robotic Manipulation via Action Chunking Embedding

    Preprint (arXiv), 2024

    Chenyu Yang*, Davide Liconti*, et al.

    Vector-quantized action chunk embeddings for efficient policy search in dexterous manipulation with MPC and reinforcement learning.

    *Equal contribution

  11. Sensorized Soft Skin for Dexterous Robotic Hands

    IEEE ICRA, 2024

    Jana Egli, Benedek Forrai, et al.

    Sensorized soft skin for high-resolution tactile perception in soft robotics.

  12. Sim-to-Real of Soft Robots with Learned Residual Physics

    IEEE RA-L, 2024

    Junpeng Gao*, Mike Yan Michelis*, et al.

    Hybrid sim-to-real modeling for soft robots that augments analytical simulation with learned residual physics.

    *Equal contribution

  13. ORCA: An Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning

    IEEE IROS, 2024

    Clemens C. Christoph, Maximilian Eberlein, Filippos Katsimalis, Arturo Roberti, Aristotelis Sympetheros, Michel R. Vogt, Davide Liconti, Chenyu Yang, Barnabas Gavin Cangan, Ronan J. Hinchet, Robert K. Katzschmann

    Open source Robotic Hand.

  14. An Open-Source Soft Robotic Platform for Autonomous Aerial Manipulation in the Wild

    CoRL, 2024

    Erik Bauer, Marc Blöchlinger, Pascal Strauch, Arman Raayatsanati, Curdin Cavelti, Robert K. Katzschmann

    An open-source platform for autonomous aerial manipulation using only onboard perception, enabling independent grasping in diverse indoor and outdoor settings with a released ROS 2 software stack and custom hardware designs.

  15. Aquarium: A Fully Differentiable Fluid-Structure Interaction Solver for Robotics Applications

    IEEE ICRA, 2023

    Jeong Hun Lee, Mike Y. Michelis, Robert K. Katzschmann, Zachary Manchester

    Aquarium is a fully differentiable 2D FSI solver using implicit Navier-Stokes integration and immersed-boundary coupling, providing analytical gradients for gradient-based gait and shape co-optimization of underwater robots.

  16. Getting the Ball Rolling: Learning a Dexterous Policy for a Biomimetic Tendon-Driven Hand with Rolling Contact Joints

    IEEE-RAS Humanoids, 2023

    Yasunori Toshimitsu, Benedek Forrai, et al.

    Adaptive dexterous manipulation for ball rolling tasks with soft robotic systems.

  17. Vision-controlled jetting for composite systems and robots

    Nature, 2023

    Thomas J. K. Buchner, Simon Rogler, et al.

    Vision-driven control and optimization for ink-jet based manufacturing.