This study investigates the use of satellite imagery for robotics applications, specifically focusing on evaluating a hybrid satellite image segmentation method against conventional soft-computing techniques. The research is conducted in Ankara, where a satellite image is processed and segmented into road, building, vegetation/forest, and ground categories using several methods. Supervised methods are trained on sample images from the city district satellite image and compared to manual segmentation conducted in Adobe Photoshop. Results from the Feed-forward Neural Network (FNN) and Probabilistic Neural Network (PNN) are contrasted with the Hybrid method, which demonstrates robust performance in identifying features such as buildings, roads, ground, and forest. The hybrid method achieves a higher Kappa coefficient (0.4060) compared to FNN (0.3908) and PNN (0.3757), indicating superior segmentation accuracy. Challenges persist in distinguishing similar color spectrums, particularly between ground and other classes. Future research directions involve refining color-based feature extraction methods and exploring advanced machine learning techniques to enhance segmentation accuracy, especially in complex urban environments. The application of satellite imagery holds great potential for robotic mapping and navigation, with opportunities to integrate multi-modal data sources and deploy deep learning architectures for more reliable performance. As researchers continue to innovate in satellite image analysis, the prospects for transformative advancements in robotics applications remain compelling.

This paper presents a Deep Neural network (DNN) system that uses a large set of geometric and categorical features for classification of secondary structure elements (SSEs) in the protein’s trace that consists of $C\alpha$ atoms on the backbone. A systematical approach is implemented for classification of protein SSE problem. This approach consists of two network architecture search (NAS) algorithms for selecting (1) network architecture and layer connectivity, and (2) regularization parameters. Each algorithm uses a different search space and they are used in succession to develop a DNN. The DNN system generates over 93% classification rate on average for multiple test sets without any post processing for amino acid configurations.

This paper introduces a clustering algorithm, called principal coordinate clustering. It takes in a similarity matrix SWof a data matrix W and computes the singular value decomposition of SWto determine the principal coordinates to convert the clustering problem to a simpler domain. It is a relative of spectral clustering, however, principal coordinate clustering is easier to interpret, and gives a clear understanding of why it performs well. In a fashion, this gives intuition behind why spectral clustering works from a more simple, linear algebra perspective, beyond the typical explanations via graph cuts, or other techniques. Moreover, it was demonstrated through experimentation on real and synthetic data that the proposed method performs equally well on average as spectral clustering, and that the method has the ability to scale quite easily to truly large data.

This paper presents a novel technique for the segmentation of data W = [w1· · · wn] ⊂ RDdrawn from a union u = ∪Mi=1of subspaces {Si}Mi=1. First, an existing subspace segmentation algorithm is used to perform an initial data clustering {Ci}Mi=1, where Ci= {wi1· · ·wik} ⊂ W is the set of data from the ithcluster. Then, a local subspace LSiis matched for each Ciand the distance dijbetween LSiand each point wij∊ Ciis computed. A data-driven threshold η is computed and the data points (in Ci) whose distances to LSiare larger than η are eliminated since they are considered as outliers or erroneously clustered data points in Ci. The remaining data points Ci⊂ Ciare considered to be coming from the same subspace with high confidence. Then, {Ci}Mi=1are used in unsupervised way to train a convolution neural network to obtain a deep learning model, which is in turn used to re-cluster W. The system has been successfully implemented using the MNIST dataset and it improved the segmentation accuracy of a particular algorithm (EnSC-ORGEN) from 93.79% to 96.52%.

This paper provides a comprehensive analysis of skeleton decomposition used for segmentation of data W = [w1···WN] ⊂ ℝddrawn from a union U = ∪i=1MSiof linearly independent subspaces {Si}i=1Mof dimensions of {di}i=1M. Our previous work developed a generalized theoretical framework for computing similarity matrices by matrix factorization. Skeleton decomposition is a special case of this general theory. First, a square sub-matrix A ϵ ℝr×rof W with the same rank r as W is found. Then, the corresponding row restriction R of W is constructed. This leads to P = A-1ℝ and corresponding similarity matrix SW= (pTp)dmax, where dmaxis the maximum subspace dimension. Since most of the data matrices are low-rank in many subspace segmentation problems, this is computationally efficient compared to the other constructions of similarity matrices. It is also shown (with some limitations) that center-of-mass based sorting of data columns in SWcan be used to quickly assess clustering performance while algorithm development in both noisy or noise-free cases.

As a part of a “lab-at-home” education paradigm for control engineering courses, this paper proposes (and elaborates) a novel hardware-in-the-loop simulator with 3D animation capabilities. The developed software, which can be tailored to simulate any dynamic systems in non-real-time, is designed to work in conjunction with a control hardware. In the paper, the specific application of the software to a graduate-level course is presented within the framework of a final term project involving the control of a satellite tracking antenna. The success of the software (along with the methodology) is rigorously evaluated through the information collected in three academic semesters including the course instructor's feedback and the questionnaires filled out by the students.

Teleoperation of an unmanned vehicle is a challenging task for human operators especially when the vehicle is not within line of sight. Lack of situational awareness and increased workload due to limited perception channels result in degraded task performance. If these teleoperation missions are human-critical then it becomes more important to improve the operator performance by decreasing workload and improving situational awareness. In this paper, a new teleoperation interface which provides force feedback based on the path generated by an obstacle avoidance algorithm is presented. The purpose of this interface is to overcome the difficulties imposed by limited field of view and lack of situational awareness. Teleoperation tests are performed to verify that haptic feedback generated from the dynamic obstacle information of the environment improves teleoperation performance by supporting the operator and decreasing the workload.

Localization is one of the major research fields in mobile robotics. With the utilization of satellite images and Monte Carlo localization technique, the global localization of an outdoor mobile robot is studied in this paper. The proposed method employs satellite images downloaded from the Internet to localize the robot iteratively. To accomplish this, the proposed method matches the local laser scanner data with the segmented satellite images. Initial test results conducted on the METU campus are found to be quite promising. Further improvement of this approach has the potential of cutting down not only the operational costs but also the preparation period of the mobile robot enabling researchers to operate their robots in diverse outdoor settings.

Localization of mobile robots has been studied rigorously in the last decade. A number of successful approaches such as Extended Kalman Filter, Markov Localization, and Monte Carlo Localization assume that the map of the environment is originally presented to the robot. However, an important information package like the map of the environment could not be taken for granted in most real- world problems. In this study, a novel technique composed of a combination of Fuzzy C-Means and Fuzzy Neural Network methods is proposed to segment and convert a satellite image into a digital map for outdoor mobile robot applications.

Teams of humans and robots working together can provide effective solutions to problems. In such applications, effective human-robot teaming relies on being able to communicate information about the current perception or understanding of the environment. In this paper, human-robot teaming on navigational tasks is discussed. The role of the human user will be to specify the goal point(s) for the robot, and also to interact with the robot in the event of perceptual errors. A novel navigation method, Egocentric Navigation (ENav), has been developed based on egocentric representations. In this paper, two knowledge sharing methods are described which exploit the characteristics of ENav. In the first method, robots share Landmark EgoSpheres, and in the second method the robot shares it Sensory EgoSphere with the human user for visual perception correction.

In this research, some human-robot interaction mechanisms that allow a human commander to control a mobile robot via a cellular phone have been developed and successfully tested. Two different control architectures have been implemented using different software technologies. The system includes two main modes, manual and autonomous controls. The manual control mode gives the user full control over the robot whereas the autonomous control mode allows the user to activate some built-in functions of the robot such as "navigate the meeting room". Two mobile robots, a Trilobot and a Pioneer, have been used as the development platforms in order to show the distinct features of mobile robot control with cellular phones.

Shows how a Sensory EgoSphere (SES), a robot-centric geodesic dome that represents the short term memory of a mobile robot, could enhance a human-robot interface. It is proposed that the addition of this visual representation of the sensor data on a mobile robot enhances the effectiveness of a human-robot interface. The SES migrates information presentation to the user from the sensing level to the perception level. The composition of the vision with other sensors on the SES surrounding the robot gives clarity and ease of interpretation. It enables the user to better visualize the present circumstances of the robot. The human-robot interface (HRI) will be implemented through a graphical user interface (GUI) which contains the SES, command prompt, compass, environment map, sonar and laser display. This paper proposes that the SES increases situational awareness and allows the human supervisor to accurately ascertain the present perception (sensory input) of the robot and use this information to assist the robot in getting out of difficult situations.

Robots are integrating more and more into our lives, However, to become an integral part of daily life, they should be socially accepted by humans. Evidently, the acceptance rate will increase as human-robot interaction gets closer to human-human interaction. The article describes the development of a Web based information filtering system, which enables a humanoid robot to initiate interaction with a human by generating human-like daily conversations.