Graspability-Aware Object Pose Estimation in Cluttered Scenes
Authors:
- Dinh-Cuong HoangDHDinh-Cuong Hoang
- Anh-Nhat NguyenANAnh-Nhat Nguyen
- Van-Duc VuVVVan-Duc Vu
- Thu-Uyen NguyenTNThu-Uyen Nguyen
- Duy-Quang VuDVDuy-Quang Vu
- Phuc-Quan NgoPNPhuc-Quan Ngo
- Ngoc-Anh HoangNHNgoc-Anh Hoang
- Khanh-Toan PhanKPKhanh-Toan Phan
- Duc-Thanh TranDTDuc-Thanh Tran
- Van-Thiep NguyenVNVan-Thiep Nguyen
- Quang-Tri DuongQDQuang-Tri Duong
- Ngoc-Trung HoNHNgoc-Trung Ho
- 9 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (4) , 3124-3130
Abstract
Object recognition and pose estimation are critical components in autonomous robot manipulation systems, playing a crucial role in enabling robots to interact effectively with the environment. During actual execution, the robot must recognize the object in the current scene, estimate its pose, and then select a feasible grasp pose from the pre-defined grasp configurations. While most existing methods primarily focus on pose estimation, they often neglect the graspability and reachability aspects. This oversight can lead to inefficiencies and failures during execution. In this study, we introduce an innovative graspability-aware object pose estimation framework. Our proposed approach not only estimates the poses of multiple objects in clustered scenes but also identifies graspable areas. This enables the system to concentrate its efforts on specific points or regions of an object that are suitable for grasping. It leverages both depth and color images to extract geometric and appearance features. To effectively combine these diverse features, we have developed an adaptive fusion module. In addition, the fused features are further enhanced through a graspability-aware feature enhancement module. The key innovation of our method lies in improving the discriminability and robustness of the features used for object pose estimation. We have achieved state-of-the-art results on public datasets when compared to several baseline methods. In real robot experiments conducted on a Franka Emika robot arm equipped with an Intel Realsense camera and a two-finger gripper, we consistently achieved high success rates, even in cluttered scenes.Keywords
This publication has 29 references indexed in Scilit:
- Occlusion-Robust Pallet Pose Estimation for Warehouse AutomationIEEE Access, 2024
- Grasp Configuration Synthesis from 3D Point Clouds with Attention MechanismJournal of Intelligent & Robotic Systems, 2023
- Object-RPE: Dense 3D reconstruction and pose estimation with convolutional neural networksRobotics and Autonomous Systems, 2020
- Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation2019
- Squeeze-and-Excitation Networks2018
- Pyramid Scene Parsing Network2017
- Sub-OBB based object recognition and localization algorithm using range imagesMeasurement Science and Technology, 2016
- Deep Residual Learning for Image Recognition2016
- Learning 6D Object Pose Estimation Using 3D Object Coordinates2014
- ImageNet: A large-scale hierarchical image database2009