Jul 2026· Italian National Conference on Sensors· Vol 26· 0 citations· 38 references
Medicine
TL;DR
An iterative closed-loop optimization framework that deeply couples SAM with FoundationPose and designs a multi-dimensional confidence assessment module that integrates both the 2D image domain and the 3D geometric domain to comprehensively evaluate the reliability of the current pose.
Abstract
In complex backgrounds and under severe occlusions, the accuracy of vision-based robotic grasping pose estimation decreases significantly, further making objects difficult to manipulate and grasp. This paper proposes an iterative closed-loop optimization framework that deeply couples SAM with FoundationPose. The framework breaks through the open-loop logic bottleneck of “segmentation first, then estimation” found in traditional vision algorithms and constructs a mask correction mechanism based on rendered projection. By performing 3D rendering of the initially estimated 6D pose, a geometric prior mask of the object is generated and then fed back into SAM’s prompt encoder, thereby guiding the model to achieve pixel-level refinement of the target’s boundary in the next perception cycle. Meanwhile, to overcome the blind spots of a single metric, the framework designs a multi-dimensional confidence assessment module that integrates both the 2D image domain and the 3D geometric domain to comprehensively evaluate the reliability of the current pose. The SAM prior, the closed-loop iterative mechanism, and the multi-dimensional confidence assessment module work in synergy to form a complete optimization loop. In robustness experiments on pose estimation under cluttered and stacked scenes, the proposed method achieves an overall ADD-S recall rate of 91.7%, with the average translation and rotation errors reduced to as low as 3.5 mm and 2.1°. In 200 real-world robotic grasping verification trials, the overall grasping success rate reaches 96.5%. These experimental results demonstrate the effectiveness and enhanced robustness of the proposed closed-loop optimization framework in the tested unstructured environments.
Reliable manipulation of small, densely stacked objects remains a significant challenge due to severe occlusions and geometric ambiguities. When observed from a single RGB-D viewpoint, adjacent surfaces of featureless cuboids like Jenga blocks often merge in depth measurements, hindering accurate instance separation and pose estimation. This paper presents a unified perception and manipulation framework designed for the robotic rearrangement of randomly stacked Jenga blocks using a single Intel RealSense D435 sensor. Our approach integrates a perception pipeline based on heightmaps, which combines color extraction with geometric reasoning to robustly segment individual blocks and estimate poses directly compatible with grasp planning. To overcome the inherent limitations of sensing from a single view in dense clutter, we propose an iterative strategy of scanning, evaluating, and regrasping. When no immediate grasp is feasible, the system performs controlled actions of grasping and releasing to induce local reconfiguration, transforming cluttered states into graspable arrangements. Experimental results, conducted under conditions equivalent to the actual competition, demonstrate a 99.02% task success rate. The proposed framework ensures stable pick-and-place operations that inherently consider manipulation constraints, proving that robust task execution is achievable using a single RGB-D sensor.
Dongwoon Song, Yeri Park, Min-Seong Jo et al.· 2026 23rd International Conf...· 1 citation
A novel 7-DoF grasping pose generation framework that integrates sparse attention and null convolution is introduced, which enhances the model’s ability to capture fine-grained features from point clouds, significantly improving the accuracy of parallel gripping pose estimation.
Hui Zhang, Yue Wang, Kang An et al.· Signal, Image and Video Proc...· 0 citations
A reinforcement learning-based framework for robotic grasp refinement, integrating keypoint-based object representations with a Deep Q-Network (DQN), is proposed, offering a scalable and adaptable solution for contact-rich manipulation tasks.
Amir Arsalan Nematollahi, Shayan Ahmadi, M. T. Masouleh et al.· 0 citations
Achieving high-precision perception is a critical prerequisite for autonomous robotic grasping, yet balancing geometric accuracy with the low-latency demands of closed-loop control remains an inherent challenge in unstructured environments. This paper proposes a robust, hierarchical 3D pose estimation framework designed to bridge this gap through a coarse-to-fine registration strategy. The pipeline integrates a lightweight YOLOv11 detector with a multi-stage refinement process. Experiments on the HV8 industrial dataset demonstrate that the detector achieves an Average Precision of 0.98, ensuring reliable Region of Interest (ROI) extraction even under significant clutter. For pose initialization, a specialized PointNet architecture provides a preliminary estimate in 0.02 s, effectively bounding positional and rotational errors to 1.38 mm and 3.64
°
, respectively. The final refinement employs an Iterative Closest Point (ICP) algorithm enhanced by Density-Based Spatial Clustering of Applications with Noise (DBSCAN), which suppresses sensor outliers and achieves a registration overlap of 95.01%. Quantitatively, the framework yields a registration Root Mean Square Error (rRMSE) of 2.89 mm, statistically comparable to the global Go-ICP baseline while reducing computational latency by several orders of magnitude. Specifically, the system completes the perception loop in 0.26 s, facilitating real-time feasibility. Furthermore, systematic bin-picking trials substantiate the operational reliability of the framework, achieving an average cycle time of 12.6 s per part. These results confirm the frameworks efficacy for high-speed, high-precision industrial manipulation.
Juan Zhao, Shuo Yang, Quanguo Fu· Unmanned Systems· 0 citations