paper-with-me

Papers

Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks

2021-11-22 · Stefan Ainetter, Christoph Böhm, Rohit Dhakate, Stephan Weiss, Friedrich Fraundorfer

In this paper, we present a novel deep neural network architecture for joint class-agnostic object segmentation and grasp detection for robotic picking tasks using a parallel-plate gripper. We introduce depth-aware Coordinate Convolution (CoordConv), a method to increase accuracy for point proposal based object instance segmentation in complex scenes without adding any additional network parameters or computation complexity. Depth-aware CoordConv uses depth data to extract prior information about the location of an object to achieve highly accurate object instance segmentation. These resulting segmentation masks, combined with predicted grasp candidates, lead to a complete scene description for grasping using a parallel-plate gripper. We evaluate the accuracy of grasp detection and instance segmentation on challenging robotic picking datasets, namely Sil\'eane and OCID_grasp, and show the benefit of joint grasp detection and segmentation on a real-world robotic picking task.

📄 PDF Abstract BibTeX arXiv:2111.11114

Code (1)

stefan-ainetter/grasp_det_seg_cnn pytorch

Tasks

Instance SegmentationObjectRobotic GraspingSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

CoordConv A CoordConv layer is a simple extension to the standard convolutional layer. It has the same functional signature as a convolutional layer, but accomplishes the mapping by…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Tracking

2025-08-11 · Xudong Han, Pengcheng Fang, Yueying Tian, Jianhui Yu 외 arxiv

Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle to resolve owing to a lack of geometric…

Monocular Depth EstimationMulti-Object TrackingInstance SegmentationPoint Clouds

Modular Anti-noise Deep Learning Network for Robotic Grasp Detection Based on RGB Images

2023-10-30 · Zhaocong Li

While traditional methods relies on depth sensors, the current trend leans towards utilizing cost-effective RGB images, despite their absence of depth cues. This paper introduces an interesting approach to detect graspin…

SegmentationSemantic Segmentation

Language-Guided Grasping under Partial Observation for Mobile Manipulation in Field Inspection and Maintenance

2026-03-09 · Dilermando Almeida, Juliano Negri, Guilherme Lazzarini, Thiago H. Segreto 외 arxiv

Offshore inspection and maintenance have increasingly been using legged robots for routine sensing, yet many useful interventions still require physical interaction with tools, containers, and task-relevant objects. Empl…

ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera

2024-05-09 · Jun Shi, Yong A, Yixiang Jin, Dingzhe Li 외

In this paper, we tackle the problem of grasping transparent and specular objects. This issue holds importance, yet it remains unsolved within the field of robotics due to failure of recover their accurate geometry by de…

ObjectObject Reconstruction

LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping

2023-11-14 · Sujal Vijayaraghavan, Redwan Alqasemi, Rajiv Dubey, Sudeep Sarkar

Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces…

Objectobject-detectionObject DetectionPose Estimation+1