Abdullah Altawaitan

University of California San Diego, Kuwait University

Papers

Total Citations

H-Index

About

Abdullah Altawaitan is an emerging researcher at the forefront of robot learning and control, specializing in physics-informed machine learning, Hamiltonian dynamics, and model predictive control for robotic systems. His work addresses a fundamental challenge in modern robotics: bridging the gap between hand-designed analytical models and the complex, variable dynamics robots encounter in real-world conditions. Altawaitan's most influential contribution, "Port-Hamiltonian Neural ODE Networks on Lie Groups for Robot Dynamics Learning and Control" (2024, 22 citations), demonstrates his innovative approach of embedding geometric and physical structure into neural networks to achieve more accurate, generalizable robot dynamics models. This work reflects a broader theme across his research portfolio — leveraging the mathematical elegance of Hamiltonian mechanics to build data-driven controllers that are both principled and practically robust. His additional work on legged robot jumping maneuvers and point-cloud-based dynamics learning for nonholonomic mobile robots further highlights his versatility across diverse robotic platforms and sensing modalities. With over 30 citations accumulated within a single publication year, Altawaitan has quickly established himself as a promising voice in the intersection of geometric mechanics, deep learning, and autonomous robot control.