S. Gulati

About

S. Gulati is a researcher working at the intersection of robotics, control systems, and machine learning, with a particular focus on intelligent robotic manipulation and human-robot interaction. Their most notable contribution lies in the development of neural network-based approaches for parameter learning and compliance control, addressing one of the fundamental challenges in robotics: enabling robots to safely and stably interact with uncertain or partially known environments. By leveraging terminal attractor dynamics within neural network architectures, Gulati's work provides a principled framework for robots to learn and adapt to environmental dynamics in real time — a critical capability for contact-rich tasks such as assembly, grasping, and physical collaboration. This research bridges the gap between classical control theory and modern learning-based methods, offering solutions that are both theoretically grounded and practically applicable. While still accumulating citations, the work addresses enduring problems in adaptive robotics that remain highly relevant as the field moves toward more autonomous and dexterous robotic systems operating in unstructured, real-world settings.

Research Focus

Key Achievements

Top Papers

1. 1
   Parameter learning and compliance control using neural networks

   2 citations · 2005

Key Collaborators

Contact & Links