Max Robotics — Global Service Robot Directory + US Certification

About

Pramod J. Nathan is a researcher in evolutionary robotics and embodied artificial intelligence, whose work explores how robots can autonomously design their own sensory systems and control programs. His primary research areas include evolutionary computation, sensor morphology, and adaptive robotics, with a focus on legged robots. Nathan’s major contribution lies in demonstrating that co-evolving a robot’s sensor configuration—such as sensor type, heading angle, and range—alongside its neural controller can significantly improve task performance and environmental adaptability. His most cited paper, "Co-Evolution of Sensor Morphology and Control on a Simulated Legged Robot" (2007, 9 citations), introduces a genetic algorithm approach that automatically designs both morphology and control for specific tasks across diverse environments. This work was extended in "Concurrently evolving sensor morphology and control for a hexapod robot" (2010, 6 citations), which showed how this co-evolution enables adaptation to environmental changes. Nathan also contributed to hardware neural networks, with a 2005 paper on implementing backpropagation for XOR learning. Though his citation counts are modest, his pioneering ideas on morphology-control co-evolution have influenced later work in self-designing robotic systems.