Max Robotics — Global Service Robot Directory + US Certification

About

Marius Wiggert is a robotics researcher whose work sits at the intersection of human-robot interaction, reward learning, and autonomous systems. His research primarily focuses on enabling robots to learn adaptable, nuanced behaviors directly from human input — a challenge that lies at the heart of making robots genuinely useful in complex, real-world environments. Wiggert's most significant contributions center on rethinking how robots model and update reward functions. Rather than relying on rigid, hand-crafted features specified in advance, his work on Feature Expansive Reward Learning and the broader "Inducing Structure in Reward Learning" framework explores how robots can autonomously discover and learn relevant features from human corrections. This represents a meaningful step forward in making reward learning scalable and practical, moving beyond the limitations of traditional linear reward models. His most-cited paper on this topic has garnered 20 citations since 2022, reflecting growing interest in the field. Beyond reward learning, Wiggert has demonstrated a practical engineering sensibility through his work on RAPID-MOLT, an open-source, low-cost agricultural robotics testbed designed to study precision irrigation — illustrating his range across both theoretical and applied domains. His body of work reflects a commitment to building robots that are not only intelligent, but genuinely responsive to human needs.