Shivani Kamtikar

I am a Ph.D. candidate in Computer Science at the University of Illinois Urbana‑Champaign (UIUC). I work in the Distributed Autonomous Systems Laboratory (DASLab) with Prof. Girish Chowdhary. I was an Applied Scientist co-op at Amazon Robotics where I worked with Prof. Taskin Padir and Dr. Josh Migdal. I received my MSCS from UIUC in 2022. My master's thesis was Visual Servoing for Pose Control of Soft Continuum Arms. Previously, I was a research intern at the University of Notre Dame with Prof. Zhiyong Zhang. I got my BTech from Pune University, India.

I’m the Director for GradSWE @ UIUC 2025. Outside research, I enjoy hiking, traveling, painting, reading, and growing a small jungle of houseplants!

Email  /  CV  /  Scholar  /  LinkedIn

Research

My research lies at the intersection of Robotics, Computer Vision, and Machine Learning. I work on developing learning-based methods for manipulation with soft and hybrid robotic arms, focusing on dexterous control in cluttered and unstructured environments. I also work on tactile‑centric policies for manipulation, enabling vision‑free exploration and object reconstruction , for both rigid arms and anthropomorphic hands. This work finds use in many applications such as autonomous harvesting, human assistive devices, medical imaging, underwater exploration, manufacturing and more!

We present the first ever diffusion-based generative planner for feasible backbone trajectories of hybrid soft-rigid manipulators, conditioned on scene geometry and goal constraints.

We present a vision-free framework that enables a multi-fingered robot to autonomously explore confined workspaces, discover objects through contact, and identify them via tactile reconstruction

We present real-time, vision-guided hybrid manipulation frame-work that enables reliable object reaching in cluttered, unstructured, and previously unseen environments.

We present a study on how different contact modes affect object shape reconstruction using a tactile-enabled dexterous gripper.

We present a position and orientation controller for a hybrid rigid-soft manipulator arm.

Precision harvesting of fruits in cluttered environments.

A deep learning-based visual servoing framework enabling robust 3D positioning of soft continuum arms, achieving sub-2 cm translation error and sub-0.25 rad rotation error in structured settings.

Patents