Mr. Nilay Kushawaha is an innovative researcher in Artificial Intelligence and Robotics, specializing in continual learning, multimodal data fusion, and adaptive control for soft robotic systems. As a doctoral candidate at the Biorobotics Institute, Scuola Superiore Sant’Anna, his work bridges advanced AI modeling with experimental robotics, creating intelligent machines capable of learning and adapting in real time. His contributions reflect a deep understanding of neural computation, reinforcement learning, and data-driven control, with research outcomes published in leading journals such as IEEE Transactions on Neural Networks and Learning Systems and Advanced Robotics Research. Nilay’s approach combines theoretical insight with practical implementation, evident in his development of algorithms like SynapNet and AGPNN, which enhance robot perception and continual learning efficiency. His interdisciplinary expertise spans physics, machine learning, and robotic design, refined through global collaborations, including research at the National University of Singapore and Jefferson Lab in the USA. Recognized for academic excellence through multiple international scholarships and awards, Nilay also contributes to academic outreach by creating tutorials and coordinating robotics initiatives. His technical fluency in Python, C++, and ROS, along with proficiency in deep learning frameworks, complements his passion for intelligent system design. Dedicated to pushing the boundaries of bioinspired robotics, Nilay’s vision centers on developing autonomous systems capable of adaptive, human-like learning and perception. His research continues to contribute significantly to the advancement of continual learning in robotics, marking him as a promising scholar and innovator in intelligent autonomous systems.
Featured Publications
Kushawaha, N., Fruzetti, L., Donato, E., & Falotico, E. (2024). SynapNet: A complementary learning system inspired algorithm with real-time application in multimodal perception.
Kushawaha, N., & Falotico, E. (2025). Continual learning for multimodal data fusion of a soft gripper.
Kushawaha, N., Perovic, G., Donato, E., & Falotico, E. (n.d.). AGPNN: A dynamic architecture-based continual reinforcement learning algorithm for robotic control.
Kushawaha, N., Nazeer, S., Laschi, C., & Falotico, E. (n.d.). SMPL: A continual learning approach for dynamic modeling of modular soft robots.
Kushawaha, N., Pathan, R., Pagliarani, N., Cianchetti, M., & Falotico, E. (2025). Adaptive drift compensation for soft sensorized finger using continual learning.
Kushawaha, N., Alessi, C., Fruzetti, L., & Falotico, E. (2025). Domain translation of a soft robotic arm using conditional cycle generative adversarial network.