Thomas Asmar
Papers
3
Total Citations
45
H-Index
3
About
Thomas Asmar is a leading researcher in the field of robotics, specializing in the control of underactuated legged millirobots. His work focuses on overcoming the unique challenges posed by these small, highly dynamic platforms, including their power constraints and difficulty in navigating complex environments. Asmar’s major contributions lie in the development of learning-based approaches, particularly image-conditioned dynamics models, that enable precise control without relying on hand-engineered controllers. His most-cited paper, "Learning Image-Conditioned Dynamics Models for Control of Underactuated Legged Millirobots" (2018), has garnered 26 citations, demonstrating its influence in advancing millirobot autonomy. A related 2017 paper on neural network dynamics models has also been impactful with 16 citations, further solidifying his role in pioneering data-driven control strategies. Asmar’s work is notable for bridging computer vision and robotics, allowing millirobots to perceive and adapt to their surroundings in real time. His research has significant implications for applications in search-and-rescue, environmental monitoring, and medical devices, where small, agile robots are essential. Through his innovative use of machine learning, Asmar continues to push the boundaries of what is possible in millirobot locomotion and control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3