|
Nidhya Shivakumar I am an M.S. student in Computer Science at Stanford University. I graduated from UC Berkeley with a B.S. in Electrical Engineering and Computer Science in 2026. I worked in Professor Ken Goldberg's AUTOLab on several projects related to robotics and computer vision. This past summer, I was a software engineering intern at Google Labs working on Stitch, their AI-powered UI design tool. I previously interned at Google in 2024 and 2025 on the Shopping Ads Infrastructure team and YouTube's Trust & Safety team, respectively. Email / GitHub / Google Scholar / CV / LinkedIn |
|
Research |
|
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
Justin Kerr*, Kush Hari*, Nidhya Shivakumar, Samarth Mahapatra, Carmelo Sferrazza, Jiahui Lei, Jitendra Malik, C. Karen Liu, Ken Goldberg, Angjoo Kanazawa arXiv, 2026 *Equal contribution Website / arXiv Policies with active stereo gaze match or exceed wrist camera setups in performance. |
|
TRACE: Interactive Bi-Directional Tracing of Monochrome Cables Amid Clutter
Nidhya Shivakumar*, Ethan Ransing*, Josh Zhang, Shamak Gowda, Kevin Yang, Miles Hua, Anika Agrawal, Justin Yu, Ken Goldberg arXiv, 2026 *Equal contribution Website / arXiv Bi-directional cable tracing combined with interactive perception primitives that actively resolve ambiguities among multiple monochrome cables in clutter. |
|
HANDLOOM 3.0: Interactive Bi-Directional Cable Tracing Amid Clutter
Justin Yu*, Nidhya Shivakumar*, Veena Sumedh*, Josh Zhang, Ethan Ransing, Osher Azulay, Ken Goldberg ICRA 2025 Deformable Objects Workshop, 2025 *Equal contribution Interactive bi-directional cable tracing system for robotic manipulation in cluttered environments. |
|
"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy
Yuchen Cui, Siddharth Karamcheti, Raj Palleti, Nidhya Shivakumar, Percy Liang, Dorsa Sadigh Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction, 2023 arXiv LILAC: a framework for incorporating natural language corrections online during execution, enabling robots to adapt to user feedback in real-time through shared autonomy with only a handful of demonstrations. |
|
Analysis of Aerial Images Using Deep Learning to Identify Critical Areas in Natural Disasters
Nidhya Shivakumar 2022 2nd International Conference on Robotics, Automation and Artificial Intelligence, 2022 IEEE Xplore Automated disaster assessment using Faster R-CNN and Mask R-CNN on UAV imagery to identify damaged buildings and critical areas with 90% precision, reducing response times for search and rescue operations. |
|
|
