Amit Chakraborty

Papers

2

Total Citations

16

H-Index

2

About

Amit Chakraborty is a researcher at the forefront of machine learning and physics-informed neural networks, specializing in the intersection of differentiable programming and classical mechanics. His primary research focus is on developing neural network architectures that can learn and simulate complex physical dynamics by embedding fundamental physical principles as inductive biases. Chakraborty’s major contribution lies in extending Lagrangian and Hamiltonian Neural Networks to handle hybrid dynamics—systems that involve both continuous motion and discrete, discontinuous events like contact and collision. His most cited work, "Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models" (2021, 12 citations), introduces a novel differentiable contact model that allows neural networks to accurately simulate rigid-body interactions while preserving energy conservation laws. This breakthrough enables more realistic and physically consistent modeling of robotic systems, articulated structures, and mechanical assemblies. With a growing citation impact, Chakraborty’s research is paving the way for more robust and interpretable AI systems in robotics, engineering simulation, and computational physics, establishing him as an emerging leader in the field of differentiable physics and learned simulation.

Research Focus

Key Achievements

2
H-Index
2
Papers
16
Total Citations
8
Avg Citations/Paper
🏆 Most Cited Paper
Extending Lagrangian and Hamiltonian Neural Networks with Differentiable\n Contact Models
12 citations · 2021
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 2

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago