Figure 3- - uploaded by Rafael Arrais
Content may be subject to copyright.
Download
View publication
Selected parts for the use case on the sub-assembly (engine) [5]. 

Selected parts for the use case on the sub-assembly (engine) [5]. 

Source publication
Figure 1-Kitting Task [5]. 
Figure 2-STAMINA Software Architecture: Partners role. Adapted from [6]. 
Figure 3-Selected parts for the use case on the sub-assembly (engine) [5]. 
Figure 4-Engine pipe, engine support, thermal shield, alternator,...
+46 Table 4 -Microsoft Kinect technical specifications [51]. 
Automatic Inconsistency detection in a Logistic World Model (European Project STAMINA)
Thesis
Full-text available
  • Jul 2015
The new sensing hardware and its associated perception have slowly become the new standard in robotics vision system. The advent of new depth camera systems made three- dimensional perception the cheaper and most effective solution to create reliable and high- quality three-dimensional dynamical representations of space. This dissertation project...
Cite
Download full-text

Similar publications

View
Outline of the proposed method. (a) CNN training module. (b) Colour...
Illustration of the architecture of our Caffenet.
The mean image (MI) of 18 classes in the Indoor dataset.
Heat map of scene knowledge of all classes found in the Indoor dataset.
+1 Pipeline of application. (a) Input video. (b) Extraction of proposed...
Prior knowledge-based deep learning method for indoor object recognition and application
Article
Full-text available
  • May 2018
Indoor object recognition is a key task for indoor navigation by mobile robots. Although previous work has produced impressive results in recognizing known and familiar objects, the research of indoor object recognition for robot is still insufficient. In order to improve the detection precision, our study proposed a prior knowledge-based deep lear...
View
Fig 1: Showcase of DLO3DS capabilities in reconstructing the shapes of...
Fig. 4: Scaling process. The shortest spline is selected as the...
Deformable Linear Objects 3D Shape Estimation and Tracking From Multiple 2D Views
Article
Full-text available
  • Jun 2023
This paper presents DLO3DS , an approach for the 3D shapes estimation and tracking of Deformable Linear Objects (DLOs) such as cables, wires or plastic hoses, using a cheap and compact 2D vision sensor mounted on the robot end-effector. DLO3DS can be applied in all those scenarios in which the perception and manipulation of DLO-like structures...
View
View
Figure 1. Outline of the proposed method. (a) CNN training module. (b)...
Figure 3. The mean image (MI) of 18 classes in the Indoor dataset.
Figure 4. Heat map of scene knowledge of all classes found in the...
Figure 5. Pipeline of application. (a) Input video. (b) Extraction of...
+2 Figure 6. Some detection results. (a) The first output frame from our...
Prior knowledge-based deep learning method for indoor object recognition and application
Article
Full-text available
  • May 2018
Indoor object recognition is a key task for indoor navigation by mobile robots. Although previous work has produced impressive results in recognizing known and familiar objects, the research of indoor object recognition for robot is still insufficient. In order to improve the detection precision, our study proposed a prior knowledge-based deep lear...
View