Keenon Werling
Papers
3
Total Citations
93
H-Index
3
About
Keenon Werling is a leading researcher at the intersection of robotics, physics simulation, and machine learning, whose work is redefining how robots learn and adapt through differentiable physics. He is best known as the creator of Nimble (nimblephysics.org), a fast and feature-complete differentiable physics engine for articulated rigid bodies with hard contact constraints. This engine, detailed in his highly cited 2021 paper (60 citations), provides a powerful platform for gradient-based optimization in robotics, enabling tasks like system identification and control synthesis that were previously computationally prohibitive. Werling’s impact extends to real-time applications; his 2022 work on model predictive control and system identification using differentiable simulation (10 citations) demonstrates a practical framework for continuously improving both modeling and control after deployment on physical hardware. By bridging the gap between simulation and reality, Werling’s contributions are pivotal for advancing robot autonomy, making his research essential reading for anyone interested in the future of learning-based robotics and simulation-driven design.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3