Max Robotics — Global Service Robot Directory + US Certification

About

Andreas Eitel is a robotics and computer vision researcher whose work centers on multimodal perception, deep learning for object recognition, and autonomous robot interaction with real-world environments. He is perhaps best known for his 2015 paper "Multimodal Deep Learning for Robust RGB-D Object Recognition," which garnered 133 citations and introduced a novel convolutional neural network architecture that fuses RGB and depth information to dramatically improve recognition robustness — a foundational contribution to the field of robot perception. His 2016 release of the Freiburg Groceries Dataset (50 citations) further cemented his role in advancing benchmarking standards for object recognition research. Eitel's work spans an impressive breadth: from detecting people and their mobility aids in hospital environments, to self-supervised instance segmentation that reduces reliance on costly hand-labeled data, to agricultural robotics applications enabling time-invariant plant localization. His 2020 work on multimodal contrastive learning addresses a critical real-world deployment challenge — leveraging multi-sensor training to enhance single-modality inference. Across more than a decade of research, Eitel has consistently bridged the gap between machine learning innovation and practical robotic deployment, making meaningful contributions to how robots see, understand, and interact with the complex world around them.