Nahas Pareekutty

Indian Institute of Technology Hyderabad, International Institute of Information Technology, Hyderabad

Papers

Total Citations

H-Index

About

Nahas Pareekutty is a roboticist whose research lies at the intersection of motion planning, autonomous navigation, and legged locomotion. His work tackles fundamental challenges in enabling robots to move intelligently through complex environments. Pareekutty’s most cited contribution, “Learning to Prevent Monocular SLAM Failure using Reinforcement Learning” (8 citations), presents a novel framework that integrates trajectory planning with single-camera ego-motion estimation. By using reinforcement learning to anticipate and avoid visual odometry failures, this work advances the robustness of autonomous navigation in GPS-denied settings. In the domain of legged robotics, his paper on “Implementation of gaits for achieving omnidirectional walking in a quadruped robot” (5 citations) proposes a sophisticated gait planning technique that enables static omnidirectional walking through optimized sequencing of leg motions—a key step toward agile, terrain-adaptive locomotion. Additionally, his work on “RRT-HX: RRT With Heuristic Extend Operations for Motion Planning in Robotic Systems” (4 citations) introduces a sampling-based planner that learns cost-to-go information heuristically, gradually biasing the search toward efficient paths without requiring prior knowledge. Collectively, Pareekutty’s research demonstrates a strong commitment to bridging perception, planning, and control, making meaningful contributions to the autonomy of mobile robots.