Max Robotics — Global Service Robot Directory + US Certification

About

M. Zeller is a robotics researcher whose work spans neural network-based motion planning, sensor integration, and biologically inspired control systems for robotic manipulators. Working primarily through the late 1990s and early 2000s, Zeller made significant contributions to the field of autonomous robot operation by developing frameworks that bridge sensory perception and motion planning — a critical challenge in robotics. Zeller's most influential contribution, "Motion Planning of a Pneumatic Robot Using a Neural Network" (1997, 33 citations), introduced the concept of the Perceptual Control Manifold (PCM), an innovative theoretical framework that extends traditional robot configuration space to incorporate sensor data, enabling robots to navigate complex, uncertain environments more effectively. Building on this foundation, Zeller pioneered the use of Topology Representing Networks (TRNs) — a class of neural networks with strong topology-preserving properties — to learn and represent these perceptual manifolds for vision-based planning tasks. A recurring theme across Zeller's publications is the application of biologically plausible neural architectures, as evidenced by early work on visuo-motor control inspired by biological movement learning. With a focused and coherent body of research accumulating over 56 citations, Zeller's work remains a meaningful reference point for researchers exploring learning-based, sensor-driven robotic motion planning.