Murali Krishna

Carnegie Mellon University, Defence Research and Development Organisation

Papers

Total Citations

H-Index

About

Murali Krishna’s research lies at the intersection of robotics, biomechanics, and human-machine interaction, with a focus on nonlinear hydraulic systems and biologically inspired locomotion. His most impactful work, “Constructing Hydraulic Robot Models Using Memory-Based Learning” (1999, 15 citations), addresses the challenge of modeling the complex actuator nonlinearities in hydraulic machines used for mining and excavation. By developing memory-based learning approaches, Krishna enabled more accurate models for optimal motion planning, a critical step toward automating heavy machinery. He extended this line of inquiry in “Constructing Fast Hydraulic Robot Models for Optimal Motion Planning” (2018, 2 citations) and “Optimal motion generation for hydraulic robots” (1998, 3 citations), refining methods for efficient real-time control. In parallel, Krishna explored legged robotics with “Implementation of CPG-based locomotion controller on Minimule Robot” (2014, 3 citations), where he applied Central Pattern Generators (CPGs)—a biologically inspired framework—to achieve adaptive locomotion in unknown environments. His work also ventures into assistive technology: “EEG-Controlled Wheelchair Movement: Using Wireless Network” (2018, 4 citations) demonstrates a brain-computer interface that translates neural signals into wheelchair commands, offering a non-muscular communication channel for individuals with severe motor impairments. Across these diverse domains, Krishna’s contributions highlight a commitment to bridging theoretical modeling with practical, real-world robotic systems.