An Object-Oriented Semantic SLAM System towards Dynamic Environments for Mobile Manipulation

Peng, Jichao; Shi, Xiaoyu; Wu, Jianhua; Xiong, Zhenhua

doi:10.1109/aim.2019.8868371

Cited by 6 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies [15], [18], [19] treat objects as landmarks to estimate camera poses or for relocalization [13]. Some studies [20] leverage object size to constrain the scale of monocular SLAM, or remove dynamic objects to improve pose estimation accuracy [7], [21]. In recent years, the combination of object SLAM and grasping [22] has also attracted many interests, and facilitate the research on autonomous mobile manipulation.…”

Section: B Object Slammentioning

confidence: 99%

EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

Zhang

Zhu

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Object-level data association and pose estimation play a fundamental role in semantic SLAM, which remain unsolved due to the lack of robust and accurate algorithms. In this work, we propose an ensemble data associate strategy for integrating the parametric and nonparametric statistic tests. By exploiting the nature of different statistics, our method can effectively aggregate the information of different measurements, and thus significantly improve the robustness and accuracy of data association. We then present an accurate object pose estimation framework, in which an outliers-robust centroid and scale estimation algorithm and an object pose initialization algorithm are developed to help improve the optimality of pose estimation results. Furthermore, we build a SLAM system that can generate semi-dense or lightweight object-oriented maps with a monocular camera. Extensive experiments are conducted on three publicly available datasets and a real scenario. The results show that our approach significantly outperforms stateof-the-art techniques in accuracy and robustness. The source code is available on https://github.com/yanmin-wu/ EAO-SLAM.

show abstract

Section: B Object Slammentioning

confidence: 99%

EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

Zhang

Zhu

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…However, such approaches are based purely on the exclusive use of 2D images. Similar to [11], the algorithm proposed in this paper makes full use of semantic and depth information. The object identification provided by YOLOv3 is based on 2D images.…”

Section: B Determination Of K Based On Semantic Detectionmentioning

confidence: 99%

“…For example, Wei et al realized real-time monitoring of railway tracks via YOLOv3 and surveillance video [10]. Peng et al extracted dynamic objects from visual data by developing graph-based image segmentation combined with YOLOv3 [11]. Despite the advantageous characteristics of YOLOv3, the running time and precision of the graph-based image segmentation algorithm are extremely dependent on the quality of the input image.…”

Section: Introductionmentioning

confidence: 99%

Image Object Extraction Based on Semantic Detection and Improved K-Means Algorithm

et al. 2020

View full text Add to dashboard Cite

Object extraction is an important tool in many applications within the image processing and computer vision communities. You Only Look Once version 3 (YOLOv3) has been extensively applied to many fields as a state-of-the-art technique for object semantic detection. Despite its numerous characteristics, YOLOv3 has to be combined with appropriate image segmentation technologies to achieve effective 2D object extraction in real-time monitoring, robot navigation, and target search. In this paper, the K-means algorithm is applied to the segmentation of depth images. Considering the inherent sensitivity to the randomness of the initial cluster center and the uncertainty of cluster number K in the initialization phase of the K-means algorithm, this paper proposes a new method that combines the semantic image information with the image depth information. Specifically, this method proposed to pre-classify the center depth of the object to determine the appropriate value of K required in the K-means algorithm. At the same time, the proposed algorithm improves the selection of the initial center via the maximin method. This paper introduces a multi-parameter extraction method to enable to correctly identify the object of interest after image segmentation. The technique considers three parameters to achieve this: i) the elements of size, ii) the connected domain, and iii) the diagonal detection. Experiments using open-source datasets demonstrate that the average processing time and the segmentation accuracy of the improved K-means algorithm are 20.36% faster and 3.12% higher than the conventional K-means algorithm, respectively. The extraction accuracy of the proposed method is 6.69% higher than that of the SuperCut extraction method.

show abstract

“…With extended networks, the robot can determine its location in unfamiliar environments. For dynamic environments, the work of [ 39 ] presents a SLAM system that automatically projects objects into dynamic environments for semantic processing and creates a global 3D environment map to eliminate the influence of dynamic objects and unknown objects.…”

Section: Related Workmentioning

confidence: 99%

Mobile Manipulation Integrating Enhanced AMCL High-Precision Location and Dynamic Tracking Grasp

Zhou

Chou

Tuo

et al. 2020

Sensors

View full text Add to dashboard Cite

Mobile manipulation, which has more flexibility than fixed-base manipulation, has always been an important topic in the field of robotics. However, for sophisticated operation in complex environments, efficient localization and dynamic tracking grasp still face enormous challenges. To address these challenges, this paper proposes a mobile manipulation method integrating laser-reflector-enhanced adaptive Monte Carlo localization (AMCL) algorithm and a dynamic tracking and grasping algorithm. First, by fusing the information of laser-reflector landmarks to adjust the weight of particles in AMCL, the localization accuracy of mobile platforms can be improved. Second, deep-learning-based multiple-object detection and visual servo are exploited to efficiently track and grasp dynamic objects. Then, a mobile manipulation system integrating the above two algorithms into a robotic with a 6-degrees-of-freedom (DOF) operation arm is implemented in an indoor environment. Technical components, including localization, multiple-object detection, dynamic tracking grasp, and the integrated system, are all verified in real-world scenarios. Experimental results demonstrate the efficacy and superiority of our method.

show abstract

An Object-Oriented Semantic SLAM System towards Dynamic Environments for Mobile Manipulation

Cited by 6 publications

References 18 publications

EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

Image Object Extraction Based on Semantic Detection and Improved K-Means Algorithm

Mobile Manipulation Integrating Enhanced AMCL High-Precision Location and Dynamic Tracking Grasp

Contact Info

Product

Resources

About