Pranav Nashikkar

Papers

Total Citations

H-Index

About

Pranav Nashikkar is pioneering the frontier of autonomous robotics through the automated discovery of symbolic control algorithms. His research centers on creating AI systems that can generate their own adaptable control policies from scratch, without human intervention or pre-existing neural architectures. In his landmark 2023 paper, "Discovering Adaptable Symbolic Algorithms from Scratch," Nashikkar introduced AutoRobotics-Zero (ARZ), a groundbreaking method that evolves zero-shot adaptable policies for robots operating in unpredictable environments. This work directly addresses one of robotics' most pressing challenges: enabling machines to rapidly adjust to environmental changes without retraining. While his citation count is still growing, the conceptual impact of ARZ is significant—it represents a paradigm shift from hand-crafted or learned neural policies to autonomously discovered symbolic programs that are inherently interpretable and generalizable. Nashikkar's approach draws inspiration from AutoML-Zero, but uniquely applies it to the domain of robotic adaptation, opening new pathways for creating resilient, explainable autonomous systems. His work is particularly relevant for researchers interested in the intersection of evolutionary computation, symbolic regression, and real-world robot deployment.