Max Robotics — Global Service Robot Directory + US Certification

About

Santosh Thoduka is a robotics researcher whose work sits at the intersection of robot perception, fault detection, and dependable autonomous systems. His research centers on equipping robots with the introspective capabilities they need to operate reliably in real-world, dynamic environments — a challenge that remains fundamental to practical robot deployment. Thoduka's most influential contributions focus on failure detection and execution monitoring. His 2021 work on visual anomaly detection (10 citations) introduced a learning-based approach that enables robots to identify unexpected deviations during task execution without requiring exhaustive failure enumeration. This was complemented by his research on sensor fusion and multimodal learning (7 citations), which demonstrated how combining heterogeneous sensor streams through neural networks improves grasp verification reliability. His 2022 work on dependable robotic systems (6 citations) offers a broader framework for practical robot deployment, addressing introspection and fault recovery holistically. Earlier contributions include action execution models for service robots (4 citations) and RGB-D-based object recognition, reflecting a consistent thread of making robots more perceptive and self-aware. His 2024 dataset on multimodal handover failure detection further underscores his commitment to rigorous, reproducible research. Across his portfolio, Thoduka advances the goal of robots that don't just perform tasks, but recognize and recover when things go wrong.