Malayandi Palaniappan

Papers

Total Citations

H-Index

About

Malayandi Palaniappan is a researcher whose work lies at the critical intersection of artificial intelligence, human-robot interaction, and value alignment. His primary research focuses on ensuring that AI systems can correctly identify and act according to their human users' objectives—a challenge central to building trustworthy autonomous systems. Palaniappan's most influential contribution, "Pragmatic-Pedagogic Value Alignment" (2019), has garnered 16 citations and introduces a novel framework for teaching AI systems human values through pragmatic communication. This work addresses the fundamental problem of how robots can infer human preferences not just from explicit demonstrations, but from the subtle, context-dependent ways humans naturally convey their goals. Additionally, his paper "An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning" (2018) advances the theoretical foundations of CIRL, a formal game-theoretic approach to value alignment where humans and robots cooperate despite asymmetric knowledge. Palaniappan's contributions are particularly notable for bridging rigorous mathematical formalism with practical considerations of human-robot collaboration, making his work essential reading for researchers tackling the value alignment problem in AI safety and human-centered robotics.