Omar Eldardeer
Papers
4
Total Citations
15
H-Index
2
About
Omar Eldardeer is a pioneering researcher at the intersection of cognitive robotics, human-robot interaction, and continual learning. His work centers on developing biologically inspired frameworks that enable robots to perceive, learn, and adapt autonomously in dynamic social environments. Eldardeer’s most cited paper, “A Biological Inspired Cognitive Framework for Memory-Based Multi-Sensory Joint Attention” (2021, 8 citations), addresses a fundamental challenge in collaborative robotics: enabling robots to share attentional focus with human partners through multi-sensory integration and memory-based mechanisms. He further advances the field with his multi-modal explainability approach for human-aware robots in multi-party conversations (2025, 4 citations), making robot decision-making transparent to human collaborators. Critically, Eldardeer challenges the dominance of deep learning in robotic audio classification, arguing in “When Deep is not Enough” (2023, 2 citations) that shallow and continual learning models are better suited for developmental robotics settings where data is scarce. His “Always-On” cognitive architecture (2025, 1 citation) proposes a paradigm shift toward continuous, self-supervised learning for social context awareness. Through these contributions, Eldardeer is shaping a future where robots are not isolated computational units but socially intelligent, adaptive partners capable of lifelong learning alongside humans.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4