Game-Changing Development for Transparent and Reflective Surface Measurement
The measurement of visually uncooperative surfaces, such as transparent glass, black plastic, or reflective metal, has long posed a challenge for conventional sensor systems. But researchers at the Fraunhofer Institute for Applied Optics and Precision Engineering (IOF) have developed a game-changing advancement: the goROBOT3D system, which uses intelligent thermal imaging and new single-shot technology to reduce measurement time from 15 seconds to under two.
This latest development builds upon Fraunhofer IOF’s ongoing research into thermal 3D sensor technology. By integrating a novel projection method and advanced image processing, the system can now capture and analyze 3D data from challenging surfaces in just 1.5 seconds – more than a tenfold improvement in speed.
Tackling the ‘Uncooperative’ Surface Problem
Transparent, reflective, or dark materials tend to absorb or scatter light in ways that conventional 3D vision systems cannot reliably detect. To overcome this, goROBOT3D employs structured thermal illumination, enabling precise surface mapping even when the object’s material properties disrupt traditional optical measurement methods.
“With our method, the surface of the measurement scene is heated in a structured manner. A statical thermal point pattern is emitted from the surface of the objects and recorded using two thermal imaging cameras. Using spatial cross-correlation, a 3D result can be obtained from the recorded image pair,” explains Dr. Martin Landmann, research scientist in the Imaging and Sensing department at Fraunhofer IOF.
The Leap to Single-Shot Measurement
The key innovation is the shift from sequential image acquisition to single-shot thermal measurement. Instead of using time-consuming fringe projection methods, Fraunhofer’s team now employs diffractive optical elements (DOEs) to rapidly project an irregular thermal point pattern across the object’s surface. These DOEs diffract the incoming laser light into a predefined pattern in a fraction of a second.
This allows the goROBOT3D system to capture the necessary thermal data in just one image pair, slashing data acquisition and evaluation times dramatically. According to Dr. Landmann, “Instead of capturing several hundred pairs of thermal images, as was the case with the previous method, our newly developed method can reconstruct the 3D information with just a single pair of images within a few milliseconds. This reduces the overall measurement and evaluation time by an order of magnitude,” says Dr. Landmann.
AI-Driven Bin Picking from 3D Thermal Data
Once the thermal images are captured, the system uses artificial intelligence to identify gripping points and determine the correct orientation for handling. This information is then relayed to a robotic arm equipped with a suction gripper, enabling efficient bin picking of mixed or disordered components.
“The entire process—from 3D capture to actuation – is optimized for high-speed, real-time operation,” says Dr. Landmann. “It enables robots to handle transparent or dark materials without interrupting production cycles.”
Seamless Integration into Smart Production
The accelerated performance of goROBOT3D opens new pathways for automated quality inspection, parts handling, and real-time manufacturing feedback. With measurement and gripping happening in near-parallel, production can continue in a smooth, uninterrupted flow.
“While one object is being gripped, the system is already measuring the next,” Landmann adds. “This continuous loop supports highly efficient, flowing industrial processes – something that was previously impossible with conventional 3D vision systems when dealing with difficult materials.”
The innovation at Fraunhofer IOF not only overcomes longstanding technical barriers but also aligns with the broader drive toward real-time, AI-enabled metrology in smart factories. As manufacturers increasingly demand flexible and robust inspection systems, thermal 3D vision may prove essential in automating what were once manual or unreliable processes.
For more information: www.iof.fraunhofer.de
