Suraj Bajracharya

Papers

Total Citations

H-Index

About

Suraj Bajracharya is a researcher whose work lies at the intersection of robotics, artificial intelligence, and cognitive architectures, with a particular focus on enabling machines to learn and represent complex behaviors. His most notable contribution, detailed in his highly cited 2013 paper "Learning behavior hierarchies via high-dimensional sensor projection," proposes a novel knowledge-representation architecture that allows robots to learn arbitrarily complex, hierarchical relationships between sensors and actuators. By encoding these relationships in high-dimensional, low-precision vectors, his approach achieves remarkable robustness to noise, a critical challenge in real-world robotics. This work, which has garnered 13 citations, demonstrates a pioneering method for bridging low-level sensor data with high-level symbolic reasoning, effectively creating a pathway for robots to build and refine behavioral hierarchies autonomously. Bajracharya’s research is particularly impactful for students and engineers working on scalable learning systems, as it offers a computationally efficient framework that sidesteps the brittleness of traditional symbolic AI. His achievements underscore a deep commitment to developing intelligent systems that can adapt and generalize in noisy, unstructured environments, making his contributions a cornerstone for future advances in autonomous robotics and hierarchical reinforcement learning.