Sounak Dey
Papers
6
Total Citations
68
H-Index
4
About
Sounak Dey is a pioneering researcher at the intersection of neuromorphic computing, collaborative robotics, and Industry 4.0 automation. His work bridges biological inspiration and industrial application, with key contributions spanning spiking neural networks for sensory processing, semantic knowledge frameworks for multi-robot coordination, and efficient data exchange in fog environments. Dey’s most impactful work, “A Reservoir-based Convolutional Spiking Neural Network for Gesture Recognition from DVS Input” (35 citations), demonstrates how third-generation neural networks can mimic mammalian neural circuits to process spatio-temporal spike patterns from event-based vision sensors. He has also advanced industrial robotics through knowledge-based hierarchical task decomposition and semantic-driven utility calculation for multi-robot task allocation, addressing critical challenges in autonomous manufacturing. Dey’s exploration of lightweight communication protocols like CoAP for semantic data exchange in fog environments, alongside his work on Hierarchical Temporal Memory for robotic path-learning, showcases his commitment to biologically plausible, distributed intelligence. With over 68 total citations across six key publications, Dey’s research provides foundational frameworks for deploying intelligent, collaborative robotic systems in real-world industrial and disaster-response scenarios.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Modelling HTM Learning and Prediction for Robotic Path-Learning3 citations · 2018
- 6A Distributed Semantic Knowledge Framework for Collaborative Robotics2 citations · 2019