Indoor localization by denoising autoencoders and semi-supervised learning in 3D simulated environment

Shantia, Amirhossein; Timmers, Rik; Schomaker, Lambert; Wiering, Marco A.

doi:10.1109/ijcnn.2015.7280715

Cited by 12 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By training the input and output data to be as equal as possible, the auto encoder can extract the feature e ciently [18]. e auto encoder is used to remove and restore noise and image noise and can be used for image classi cation [19][20][21][22][23][24]. As the amount of research on sensor data utilization and analysis has increased in recent years, it is also possible to use an auto encoder as a correction technique for sensor data.…”

Section: Auto Encodermentioning

confidence: 99%

Defect Inspection in Display Panel Using Concentrated Auto Encoder

2019

International Journal of Optics

View full text Add to dashboard Cite

In this paper, concentrated auto encoder (CAE) is proposed for aligning photo spacer (PS) and for local inspection of PS. The CAE method has two characteristics. First, unaligned images can be moved to the same alignment position, which makes it possible to move the measured PS images to the same position in order to directly compare the images. Second, the characteristics of the abnormal PS are maintained even if the PS is aligned by the CAE method. The abnormal PS obtained through CAE has the same alignment as the reference PS and has its abnormal characteristics. The presence or absence of defects and the location of defects were identified without precisely measuring the height of the PS and critical dimension (CD). Also, alignment and defect inspection were performed simultaneously, which shortened the inspection time. Finally, inspection performance parameters and inspection time were analyzed to confirm the validity of the CAE method and were compared with the image similarity comparison methods used for defect inspection.

show abstract

Section: Auto Encodermentioning

confidence: 99%

Defect Inspection in Display Panel Using Concentrated Auto Encoder

2019

International Journal of Optics

View full text Add to dashboard Cite

show abstract

“…The three dimensional case is called the unique signatures of histograms (SHOT) [16]. The two dimensional case (HoG) has been applied to human detection [9], indoor localization [17], object recognition [16], and many other applications. Therefore, we believe that it is also a suitable method for our application.…”

Section: A Unsupervised Environmental Situation Analysismentioning

confidence: 99%

Dynamic parameter update for robot navigation systems through unsupervised environmental situational analysis

Shantia

Bidoia

Schomaker

et al. 2016

2016 IEEE Symposium Series on Computational Intelligence (SSCI)

Self Cite

View full text Add to dashboard Cite

A robot's local navigation is often done through forward simulation of robot velocities and measuring the possible trajectories against safety, distance to the final goal and the generated path of a global path planner. Then, the computed velocities vector for the winning trajectory is executed on the robot. This process is done continuously through the whole navigation process and requires an extensive amount of processing. This only allows for a very limited sampling space. In this paper, we propose a novel approach to automatically detect the type of surrounding environment based on navigation complexity using unsupervised clustering, and limit the local controller's sampling space. The experimental results in 3D simulation and using a real mobile robot show that we can increase the navigation performance by at least thirty percent while reducing the number of failures due to collision or lack of sampling.

show abstract

“…The three dimensional case is called the unique signatures of histograms (SHOT) (Tombari et al 2010). The two dimensional case (HoG) has been applied to human detection (Dalal and Triggs 2005), indoor localization (Shantia, Timmers, Schomaker and Wiering 2015), object recognition (Tombari et al 2010), and many other applications. Therefore, we believe that it is also a suitable method for our application.…”

Section: Customized Histograms Of Oriented Gradientsmentioning

confidence: 99%

“…With the popularity of deep neural networks (Schmidhuber 2015), different approaches were made to tackle the navigation problem using deep neural networks. Previously, we transferred the knowledge from a traditional map to a stacked denoising autoencoder (SDA) in which the robot used grid mapping for training data, and could localize its position using a camera after training in a small environment (Shantia, Timmers, Schomaker and Wiering 2015). Bidoia et al (Bidoia et al 2018), used a semi-supervised approach to create a graph map using deep CNNs.…”

Section: Previous Workmentioning

confidence: 99%

“…A set of images is recorded during the data gathering phase that are tagged with the estimated location from the GMapping algorithm. In our previous research (Shantia, Timmers, Schomaker and Wiering 2015), we showed that a stacked denoising autoencoder (SDA) can learn the geometrical relation between the images and the robot location in a small 3D simulated environment. In this paper, we use deep convolutional neural networks (CNNs) (LeCun et al 1998) to test the scalability and precision of this approach and compare the results to that of SDAs in order to select the best type of network architecture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Robotic Navigation: Deep Visual Localization and Adaptive Control

Shantia¹

View full text Add to dashboard Cite

Samenvatting 114Where is the robot? Humans have an excellent notion of their current surroundings. Even if somebody kidnaps us and puts us in an unknown location, we can describe the characteristics of this new place without much effort. Our knowledge and experience of our world allow us to identify shapes, geometry, and objects that are around us. Besides, we can correctly connect a series of observations from our senses to build a spatial map. We are so good at it that even without vision, and with some training, we can move around a block and find our starting position. We do get lost, but usually, with a hint of a landmark, a passerby, or our phone's GPS, we adjust our estimated location. We can program robots to partially perform the localization and mapping tasks by using a variety of sensors such as cameras and range Chapter

show abstract

Indoor localization by denoising autoencoders and semi-supervised learning in 3D simulated environment

Cited by 12 publications

References 21 publications

Defect Inspection in Display Panel Using Concentrated Auto Encoder

Defect Inspection in Display Panel Using Concentrated Auto Encoder

Dynamic parameter update for robot navigation systems through unsupervised environmental situational analysis

Machine Learning in Robotic Navigation: Deep Visual Localization and Adaptive Control

Contact Info

Product

Resources

About