Robots can now grasp transparent and reflective objects using a new RGB-based vision method without depth sensors.
Researchers at Tokyo University of Science have developed a new vision-based system that allows robots to accurately grasp transparent and reflective objects without relying on depth sensors. The method addresses a key limitation in automated material handling, where such objects have traditionally been difficult to detect and manipulate.
Handling items like glass, shiny metal, and clear plastics has remained a major challenge for robots, as these materials distort or confuse conventional 3D sensing systems, often requiring human intervention and slowing operations.The system, called HEAPGrasp, reconstructs object shapes using only visual outlines captured through an RGB camera, enabling robots to reliably identify and grasp objects regardless of their optical properties.Instead of relying on specialized sensors, the system uses a standard RGB camera to capture images from multiple angles. It then extracts object silhouettes and reconstructs their 3D shape using a technique that remains stable even when dealing with transparent or reflective surfaces.Seeing beyond surface limits“Traditionally, transparent or mirrored objects have been unstable to detect when using depth sensors, making automatic grasping by robots difficult and ultimately leading to human intervention,” explained Shogo Arai.“Our approach is based on the idea that even when depth information is unreliable, object shape estimation and grasping are still possible as long as the object’s contours or silhouettes can be captured reliably in images.”The system begins by separating objects from the background using semantic segmentation. It uses a deep learning model to classify each pixel in the image, isolating objects before reconstructing them in three dimensions.To build a 3D model, the method applies Shape from Silhouette, a technique that estimates object volume by combining outlines captured from different viewpoints.Because it depends only on silhouettes, the method avoids errors caused by transparency or glare.However, capturing more viewpoints typically increases processing time. To address this, the researchers added a deep learning-based planning system that determines the most efficient camera path, reducing unnecessary movement while maintaining accuracy.Faster grasping smarter robotsThe team tested HEAPGrasp on a real robotic setup across 20 scenarios involving different combinations of transparent, opaque, and reflective objects. The system consistently outperformed existing grasping methods.It achieved a 96 percent success rate using a single camera, while also cutting camera movement by 52 percent and reducing execution time by 19 percent compared to conventional approaches.“Our approach achieves accurate 3D measurement of objects while minimizing camera movement and execution time,” said Ginga Kennis.“By reducing the amount of pre-adjustment required, HEAPGrasp simplifies on-site implementation and operation, especially since it can be retrofitted to existing robotic systems.”The ability to work with standard cameras and existing hardware could make the system easier to deploy across industries such as logistics, food handling, and manufacturing, where mixed materials are common.The study was published in IEEE Robotics and Automation Letters.
Automation Computer Vision Grasping Logistics Manufacturing RGB Imaging Robotics
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Strange Modular Robots Are Writhing Across LandscapesAt Futurism, my work has often centered on bringing a sense of clarity and insight to complex topics ranging from the regulation of emerging technologies to the esoteric ideologies of Silicon Valley executives, while striving not to lose the poetic sense of awe inspired by often-obscure fields like astrophysics and quantum computing.
Read more »
Delivery robots shatter Chicago bus shelter glass in separate incidents, including one caught on cameraServe Robotics and Coco Robotics delivery robots reportedly crashed into Chicago bus shelters days apart, shattering glass with no injuries reported.
Read more »
Fantastic Four's New Appearance Introduces Permanent New Superpower for A-List Herovanessa kirby's invisible woman and the fiery avengers logo
Read more »
New Images From DC Showcase Superman And Batman's New Matching CostumesBatman and Superman aka the World's Finest fight in official DC Comics art for Sideshow
Read more »
New Balance’s Futuristic Lifestyle Sneaker Is Getting New Multicolor Styles for SpringNew Balance is giving its futuristic Abzorb 2000 sneaker two new 'Liquid Metal' colorways with gradient fade multicolor looks. Find the release info.
Read more »
Three Reasons to Believe in Virginia Tech In 2026The Hokies welcome a new head coach — and 50 new players.
Read more »