A Multilevel Similarity Approach for Single-View Object Grasping: Matching, Planning, and Fine-Tuning

Abstract

Grasping unknown objects from a single view has remained a challenging topic in robotics due to the uncertainty of partial observation. Recent advances in large-scale models have led to benchmark solutions such as GraspNet-1Billion. However, such learning-based approaches still face a critical limitation in performance robustness for their sensitivity to sensing noise and environmental changes. To address this bottleneck in achieving highly generalized grasping, we abandon the traditional learning framework and introduce a new perspective: similarity matching, where similar known objects are utilized to guide the grasping of unknown target objects. We newly propose a method that robustly achieves unknown-object grasping from a single viewpoint through three key steps: 1) leverage the visual features of the observed object to perform similarity matching with an existing database containing various object models, identifying potential candidates with high similarity; 2) use the candidate models with pre-existing grasping knowledge to plan imitative grasps for the unknown target object; 3) optimize the grasp quality through a local fine-tuning process. To address the uncertainty caused by partial and noisy observation, we propose a multilevel similarity matching framework that integrates semantic, geometric, and dimensional features for comprehensive evaluation. Especially, we introduce a novel point cloud geometric descriptor, the clustered fast point feature histogram descriptor, which facilitates accurate similarity assessment between partial point clouds of observed objects and complete point clouds of database models. In addition, we incorporate the use of large language models, introduce the semioriented bounding box, and develop a novel point cloud registration approach based on plane detection to enhance matching accuracy under single-view conditions. Real-world experiments demonstrate that our proposed method significantly outperforms existing benchmarks in grasping a wide variety of unknown objects in both isolated and cluttered scenarios, showcasing exceptional robustness across varying object types and operating environments.