Mihir Parmar
Papers
1
Total Citations
20
H-Index
1
About
Mihir Parmar investigates the intersection of deep learning and robotics, with a primary focus on the fundamental challenges of modeling stiff contact dynamics—a critical barrier to advancing legged locomotion and robotic manipulation. His most-cited work, "Fundamental Challenges in Deep Learning for Stiff Contact Dynamics" (2021, 20 citations), provides compelling empirical evidence that learning-based approaches struggle with the nearly-discontinuous nature of frictional contact, which has long been a core yet difficult problem in robot planning and control. By systematically identifying these limitations, Parmar's research highlights where current deep learning methods fall short, guiding the community toward more robust architectures and training strategies. His contributions are particularly valuable for researchers seeking to bridge the gap between simulation and real-world robotic performance. With a growing citation impact, Parmar's work serves as a critical reference for anyone tackling contact-rich manipulation or locomotion tasks, offering both a clear diagnosis of present obstacles and a roadmap for future algorithmic innovations.
Research Focus
Key Achievements
Top Papers
- 1Fundamental Challenges in Deep Learning for Stiff Contact Dynamics20 citations · 2021