Senthilkumar CG Periaswamy
Papers
2
Total Citations
11
H-Index
2
About
Senthilkumar CG Periaswamy is a robotics researcher advancing autonomous navigation and long-horizon task learning. His work centers on reinforcement learning (RL) and imitation learning for complex, real-world robotic systems. In his highly cited 2020 paper, "Balanced Map Coverage using Reinforcement Learning in Repeated Obstacle Environments" (6 citations), Periaswamy introduced a novel Complete Coverage Path Planning framework that enables robots to achieve high-speed, efficient map coverage in cluttered, repetitive environments like factories and airline cabins—a critical capability for industrial automation. Building on this, his 2022 work "RIRL: A Recurrent Imitation and Reinforcement Learning Method for Long-Horizon Robotic Tasks" (5 citations) tackles the challenge of scaling RL to large-scale, temporally extended tasks. By integrating recurrent neural networks with imitation learning, RIRL embeds historical observations to overcome the exponential complexity that limits prior methods, enabling robots to learn and execute complex, multi-step operations. Periaswamy’s contributions directly address key bottlenecks in autonomous robotics—balancing speed with coverage and handling long-term dependencies—making his research impactful for both academic study and practical deployment in dynamic, obstacle-rich settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2