Industrial robots estimate pose and size of unknown objects using verified 3D models
OV-PEAR: Observation-Verified Pose-Scale Estimation and Reconstruction for Unknown Industrial Manipulation Objects
RoboticsArtificial Intelligence
Summary
Fine manipulation tasks by industrial robots need to know exactly where and how big objects are, but current methods often struggle with new or unseen items. The authors developed OV-PEAR, a system that uses multiple camera views and depth sensing to build reliable 3D models of unknown objects without prior knowledge. Their method verifies these models by checking consistency across views, which helps the robot grasp and assemble parts accurately. This approach improves manipulation success and maintains a fast, efficient record of object information.
What this means in practice
- •For industrial robot operators: Create accurate 3D models and pose estimates for unknown objects to improve robot grasping and assembly in flexible manufacturing lines.
- •For warehouse automation teams: Enhance automated handling of diverse and unseen parts by reconstructing reliable object shapes and sizes from multi-view RGB-D data.
Authors
Guoqin Tang, Qingxuan Jia, Yichen Tan, Zihang Lv, Ruiquan Wang, Zeyuan Huang, Gang Chen
Abstract
Fine industrial robotic manipulation requires 6D pose, scale, and an operation-ready 3D model. Existing industrial pose estimation relies on CAD models, object-specific training data, or stable workcells, limiting use with unseen objects; zero-shot methods suffer from single-view occlusion, generative bias, and scale uncertainty. We present OV-PEAR, an observation-verified framework for 3D reconstruction and pose-scale estimation of unknown industrial objects. Its three-stage object-centric pipeline: (1) segments RGB-D instances and generates object-level 3D hypotheses; (2) anchors them to the robot frame via appearance-aware view retrieval, explicit scale search, and visibility-sensitive registration; (3) back-projects multi-view RGB-D evidence into the object-canonical frame to verify voxel occupancy, suppress hallucinations, and produce reusable trusted object models. On BOP-Industrial, OV-PEAR achieves 0.657 average AR and improves pose and voxel-level geometric consistency in real scenes; real-robot connector assembly reaches 99.67% grasp and 84.00% assembly success. The model library and pose-scale log enable short-term object-level state maintenance at 0.02 ms/frame.