Projects
Reverse-engineering natural intelligence and designing artificial cognitive agents that act like (and alongside) natural agents, form the long-term goals of my research. I tread an interdisciplinary path connecting intelligent robotics, cognitive sciences and consumable AI technologies to investigate learning, memory, language and intelligence in cumulatively developing systems (humans and robots). Looking at intelligence from a holistic perspective and cognitive agents as integrated systems has led me investigate problems across multiple subdomains, particularly the ones listed below.
Causal Learning & Body Schema in Robotics
This project focuses on how robots can abstract cause-effect relations from experience, enabling intuitive actions with unseen objects. By developing body schema models and causal learning algorithms, robots gain the ability to understand their physical capabilities and predict interaction outcomes, leading to more natural and effective manipulation skills.
causal-learning, body-schema, motor-intelligence
Knowledge Graph Completion & AI-Recommender Systems
Developed innovative models for predicting missing graph links in knowledge graphs, with applications spanning drug discovery, recommendation systems, and human resources. This research leverages advanced machine learning techniques to solve complex graph completion problems and has been recognized at top-tier conferences including ACL, NeurIPS, and ICML.
knowledge-graphs, ai-recommendations, machine-learning
Language & Visual Exploration in Infants
This project developed computational models explaining how babies learn language through visual exploration patterns. By studying the intersection of vision and language development, we created AI systems that mirror infant learning processes and match behavioral patterns observed in developmental psychology studies.
developmental-ai, language-learning, visual-exploration
Memory-Driven Reasoning in Robots
This project explores how robots can simulate past experiences to solve new problems creatively and efficiently. By developing memory-driven reasoning systems, robots can leverage historical interactions to adapt to novel situations, demonstrating enhanced problem-solving capabilities in both experimental settings and industrial multi-robot environments.
robotics, memory-systems, cognitive-reasoning
Motor Intelligence & Cognitive Control
This project develops neural models that improve dexterity and tool use in complex manipulation tasks. By integrating cognitive control mechanisms with motor learning, robots achieve fast and adaptable motion capabilities. The research has been successfully applied to both humanoid robots like iCub and industrial robotic systems.
motor-control, cognitive-systems, dexterity
Spatial Planning & Multi-Robot Collaboration
This project addresses how robots coordinate in shared spaces through dynamic planning and task negotiation. By developing sophisticated spatial planning algorithms and communication protocols, teams of robots can work together efficiently in complex environments, enabling scalable teamwork in real-world assembly and manufacturing scenarios.
spatial-planning, multi-robot, collaboration
Word Learning Experiments Across Ages
This experimental study examined how children's attention patterns differ from adults during word learning tasks. The research revealed significant differences in attention mechanisms across age groups, challenging standard testing methodologies and supporting new computational models of language acquisition.
word-learning, developmental-psychology, attention-patterns