Max Robotics — Global Service Robot Directory + US Certification

About

Shiwali Mohan is a cognitive systems and robotics researcher whose work sits at the intersection of human-robot interaction, grounded language learning, and autonomous agent development. Her research centers on building intelligent systems capable of expanding their knowledge through natural, situated interactions with human instructors — a challenge that demands integrating perception, language understanding, and task execution into unified cognitive frameworks. Mohan's most influential contribution, "Learning Goal-Oriented Hierarchical Tasks from Situated Interactive Instruction" (2014, 49 citations), demonstrates how robots can acquire complex task structures directly from human guidance. Complementing this, her work on the Soar cognitive architecture (2012, 45 citations) advances the long-term vision of robots with human-like cognitive abilities, including adaptive learning and coordination. Her research on grounded word acquisition — spanning papers from 2012 to 2025 — reveals a sustained commitment to understanding how agents learn perceptual, semantic, and procedural meaning from mixed-initiative dialogue. Collectively, her publications reflect a coherent research trajectory: designing robots that don't just execute pre-programmed instructions but genuinely learn language and tasks the way humans do — through interaction. Her work offers foundational insights for anyone studying embodied AI, cognitive architectures, or natural language grounding in real-world robotic systems.