Max Robotics — Global Service Robot Directory + US Certification

About

Markus Schoeler’s research lies at the intersection of robotic perception, cognitive robotics, and autonomous learning, with a focus on enabling robots to understand and interact with their environments in human-like ways. His most influential work, “Convexity based object partitioning for robot applications” (65 citations), introduces a bottom-up approach to segment 3D point clouds by exploiting the perceptual principle that objects are composed of connected convex surfaces separated by concave boundaries—a foundational idea for robotic scene understanding. In “A model-based approach to finding substitute tools in 3D vision data” (27 citations), Schoeler tackles a critical challenge for robots operating outside controlled settings: recognizing and using unfamiliar objects as functional substitutes for known tools, thereby advancing robotic adaptability. He also pioneered self-supervised and unsupervised methods for generating training data, as seen in “Fast Self-supervised On-line Training for Object Recognition Specifically for Robotic Applications” (9 citations), reducing the need for human-labeled datasets. Notably, his work “Testing Piaget’s ideas on robots” explores implementing psychological learning mechanisms—assimilation and accommodation—in machines, bridging cognitive science and robotics. Schoeler’s contributions have shaped how robots perceive objects, learn autonomously, and generalize skills to novel contexts.