Nithish Kumar
Papers
1
Total Citations
8
H-Index
1
About
Nithish Kumar is a robotics researcher whose work lies at the intersection of motion planning, deep reinforcement learning (DRL), and human-aware navigation. His most cited paper, “Dynamically Feasible Deep Reinforcement Learning Policy for Robot Navigation in Dense Mobile Crowds” (2020, 8 citations), introduces a novel DRL-based policy that integrates the Dynamic Window Approach (DWA) with learned spatial awareness. This contribution enables robots to compute dynamically feasible velocities while safely navigating through dense, unpredictable crowds—a critical challenge for autonomous systems in human environments. By bridging classical control constraints with modern learning-based methods, Kumar’s work advances the practical deployment of mobile robots in real-world settings such as hospitals, warehouses, and public spaces. His research is particularly notable for addressing the trade-off between dynamic feasibility and reactive navigation, ensuring that generated trajectories respect the robot’s physical limits while avoiding collisions. With a focus on safety and efficiency in crowded scenarios, Kumar’s contributions are shaping the next generation of socially compliant robot navigation, making his work essential reading for students and researchers in field robotics and human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1