Papers
7
Total Citations
115
H-Index
5
About
Gaurav Singal is a leading researcher at the intersection of deep reinforcement learning (DRL), autonomous robotics, and mobile security. His work focuses on creating robust, intelligent systems capable of operating in real-world, resource-constrained environments. Singal’s most significant contribution is his comprehensive survey on deep reinforcement learning techniques across diversified domains, which has garnered 55 citations and serves as a foundational resource for researchers exploring DRL’s applications in robotics, gaming, and autonomous systems. He has pioneered practical DRL solutions for autonomous navigation, including corridor segmentation for indoor robots using edge devices (25 citations), and developed novel person-identification systems using autonomous drones and resource-constrained hardware (15 citations)—a breakthrough with direct implications for search-and-rescue and surveillance. Singal also addresses critical security vulnerabilities in the age of smart devices, as highlighted by his work on PIN inference attacks against mobile-controlled robots (9 citations). His recent innovations, such as the QC_SANE framework for robust DRL control and the RSAC strategy for handling sensor perturbations, demonstrate his commitment to making autonomous systems more reliable and secure. Singal’s research is essential reading for anyone working to build the next generation of safe, efficient, and autonomous intelligent agents.
Research Focus
Key Achievements
Top Papers
- 1Deep Reinforcement Learning Techniques in Diversified Domains: A Survey55 citations · 2021
- 2
- 3
- 4
- 5
- 6
- 7Precise Control for Deep Driving using Dual Critic based DRL Approaches2 citations · 2021