Arpit Garg
Papers
1
Total Citations
14
H-Index
1
About
Dr. Arpit Garg is a leading researcher at the intersection of robotics, artificial intelligence, and formal verification, with a primary focus on developing safe and reliable autonomous navigation systems. His most-cited work, "Comparison of Deep Reinforcement Learning Policies to Formal Methods for Moving Obstacle Avoidance" (2019, 14 citations), makes a pivotal contribution by systematically benchmarking deep reinforcement learning (RL) approaches against formal methods for dynamic obstacle avoidance. This study critically evaluates how deep RL policies, which learn to predict obstacle motions and avoidance actions directly from sensor data, compare to mathematically rigorous formal verification techniques. By highlighting the trade-offs between learning-based flexibility and safety guarantees, Dr. Garg's research provides essential guidance for deploying autonomous systems in real-world environments where moving obstacles with diverse dynamics are present. His work is particularly notable for bridging the gap between cutting-edge machine learning and traditional control theory, offering a balanced perspective that informs both practitioners and theoreticians. Dr. Garg's contributions are foundational for advancing trustworthy AI in robotics, ensuring that autonomous vehicles and drones can navigate safely in unpredictable, dynamic settings.
Research Focus
Key Achievements
Top Papers
- 1