Max Robotics — Global Service Robot Directory + US Certification

About

Deepak Garg is a leading researcher at the forefront of deep reinforcement learning (DRL), with a focused mission to make autonomous systems more robust and reliable. His work primarily addresses critical challenges in robotics and autonomous driving, where he tackles the fragility of DRL agents in real-world environments. Garg’s major contributions include pioneering the QC_SANE framework, which introduces a Quantile Critic with Spiking Actor and Normalized Ensemble to enhance control stability, and the RSAC strategy, designed to maintain performance under sensor malfunctions and dimensionality perturbations. His highly cited survey on "Deep Reinforcement Learning Techniques in Diversified Domains" (55 citations) serves as a foundational resource for the field, while his work on corridor segmentation for indoor robot navigation (25 citations) demonstrates practical, edge-device applications. Garg’s research on precise vehicle control using dual-critic DRL approaches further advances autonomous driving safety. With a growing citation impact exceeding 90 total citations, Deepak Garg is recognized for bridging the gap between theoretical DRL advances and robust, real-world deployment in autonomous systems.