Research field

Learning from demonstration and physical interaction

Robots acquire skills from human demonstration or from their own exploration. These skills then transfer across objects, goals and embodiments.

Several thin demonstrated paths inside a shaded variance band converging into one bold reproduced motion, with a guiding arrow at the start and a target at the goal.

About this field

A robot has to come to have a skill in the first place. It can be shown by a person, or discovered through its own exploration and contact with the world. The skill must then survive the move to new objects, new goals and different bodies.

People

  • Nilay Kushawaha

    Nilay Kushawaha

    Postdoctoral researcher since 2026

    The research focuses on continual learning for robot manipulation. It also studies cross-embodiment transfer, so that skills carry over between different robots.

    Nilay Kushawaha is a Postdoctoral Associate at NYU Abu Dhabi, with a Ph.D. in Biorobotics and AI from the Scuola Superiore Sant'Anna, Italy.

    His research focuses on continual learning, brain-inspired AI, and adaptive robot control. He develops algorithms that let robots keep learning and adapting across their lifetime, the way humans do. His work spans both soft and rigid robotic systems, combining machine learning, robotics, and physics to build more intelligent and autonomous robots.

    Keywords: Continual Learning, Incremental Learning, Learning from Demonstrations, Reinforcement Learning, Soft & Rigid Robotics, Sensor Fusion.

  • Omar Mostafa

    Omar Mostafa

    PhD student since 2026

    The research is on stable robot learning, including stable dynamical-systems control. It also covers vision-language-guided policy learning and simulation environments for manipulation.

    Omar Mostafa is a Global PhD student in Electrical and Computer Engineering. His research interests are robot learning and control, with a focus on physics-informed reinforcement learning and world models for robotic manipulation.

    Previously: Graduated magna cum laude from NYU Abu Dhabi with a bachelor’s degree in Electrical Engineering.

Publications since 2024

  1. Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning

    IEEE Robotics and Automation Letters (RA-L), vol. 11, no. 3, pp. 3111–3118

    A. E. Binny, M. Anand, H. T. M. Kussaba, L. Chen, S. Agrawal, F. J. Abu-Dakka, A. Swikir

  2. MV-UMI: A Scalable Multi-View Interface for Cross-Embodiment Learning

    IEEE Access

    O. Rayyan, J. Abanes, M. Hafez, A. Tzes, F. Abu-Dakka

  3. MeshDMP: Motion Planning on Discrete Manifolds using Dynamic Movement Primitives

    IEEE International Conference on Robotics and Automation (ICRA)

    M. Dalle Vedove, F. J. Abu-Dakka, L. Palopoli, D. Fontanelli, M. Saveriano

  4. Learning Periodic Skills for Robotic Manipulation: Insights on Orientation and Impedance

    Robotics and Autonomous Systems (RAS)

    F. Abu-Dakka, M. Saveriano, L. Peternel

  5. A Unified Formulation of Geometry-Aware Discrete Dynamic Movement Primitives

    Neurocomputing

    F. J. Abu-Dakka, M. Saveriano, V. Kyrki

  6. Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview

    Information Fusion

    Y. Hu, F. J. Abu-Dakka, F. Chen, X. Luo, Z. Li, A. Knoll, W. Ding

  7. G3VLA: Geometric inductive bias for Vision-Language-Action Models

    Preprint arXiv preprint — not yet peer-reviewed

    Yue Peng, Yongzhe Zhao, Artur Habuda, Khuyen Pham, Yanheng Zhu, Tran Nguyen Le, Fares Abu-Dakka, Li Guo