About

Padmaja Kulkarni is a robotics researcher whose work focuses on making robots more adaptable, intuitive, and capable in real-world tasks. Her primary research areas include reinforcement learning for assembly, gesture-based robot control, and sensor-integrated grasping. Kulkarni’s most impactful contribution is her 2021 paper on combining impedance control with residual recurrent reinforcement learning, which enables robots to learn assembly tasks in just a few minutes—a significant leap in efficiency that has garnered 28 citations. This work addresses the critical challenge of adapting to uncertainties in real-world manufacturing. She also pioneered a gesture recognition framework using IMUs and an Online Lazy Neighborhood Graph search, allowing natural human-robot interaction without cumbersome physical controls. In agricultural robotics, Kulkarni developed a geometry-based grasping method for vine tomatoes, demonstrating how computer vision and geometric modeling can improve delicate harvesting. Her additional work on low-cost sensor integration for flexible robotic fingers shows her commitment to practical, accessible solutions. With a citation count approaching 40 across her key papers, Kulkarni is advancing the frontier of robotic dexterity and human-robot collaboration, making her research particularly valuable for students and engineers working on applied robotics and automation.

Research Focus

Key Achievements

3
H-Index
4
Papers
40
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Learning Assembly Tasks in a Few Minutes by Combining Impedance Control and Residual Recurrent Reinforcement Learning
28 citations · 2021
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: Delft University of Technology, Fraunhofer Institute for Communication, Information Processing and Ergonomics, Hochschule Bonn-Rhein-Sieg

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago