To avoid risking the lives of victims and rescue team personnel in the event of disasters like earthquakes, volcanic eruptions, hurricanes, etc., search and rescue (SAR) robots are increasingly incorporated into the operation. One of the major challenges in integrating SAR robots into rescue operations is the potentially severely damaged infrastructure within the disaster site. A critical component of this is a functional communication system which is essential for exchanging real-time information between the robots in the field and the base station (BS). Given that there might be either limited coverage or a complete failure of standard communication systems in a severely affected disaster site, a novel disaster management system named Titan disaster management system (DMS), which is based on low-power wide-area networks (LPWANs) LoRa technology is proposed. Its development consists of three solutions, which are Titan coordination, communication, and navigation solutions. The Titan coordination solution based on a robot platoon configuration has been developed to assist the rescue team in establishing a BS within the disaster-affected area. The victims, the BS, and the SAR robots may all communicate with one another using the Titan communication system. For guiding the SAR robot through the devastated disaster scene, the Titan navigation solution named fuzzy inference system vector field histogram (FISVFH) was developed. The different phases of the development of Titan DMS are discussed, and the results obtained from field tests are presented in this article.

Autonomous Vehicles society is blooming and evolving as driving safety is expected to improve by autonomous vehicles (AVs) compared with human driving. Intersection mobility is one of the challenging tasks for AVs; thus, this paper proposes two algorithms. The first proposed algorithm uses a driving space to generate a motion trajectory based on LiDAR data and road geometry. The other algorithm provides C2smooth path Bézier curve by joining two cubic Bézier curve segments. Information pieces from Polaris car's position during turning are utilized to compute the intersection road's corner radius. The proposed algorithms have been tested in multiple simulation environments with different traffic conditions in Gazebo using Polaris car. Simulation results show that Polaris car can turn continuously and smoothly through the intersection square, demonstrating the effectiveness of the proposed algorithms.

Robots that perform autonomous maneuvering in a disaster environment usually dont have perfect understanding of the environment in advance. The robot is continuously evaluating the environment as it proceeds, deciding the optimal way to traverse the environment to get to the goal. A critical aspect of this decision is the robot estimate of the terrain accessibility index, which quantifies how easy it is to navigate through the immediate terrain. This paper represents a new method to calculate terrain accessibility index based on obstacle distance to the robots position. In addition, a Fuzzy Inference System Vector Field Histogram (FISVFH) method has been designed for automating the selection of the robots linear and angular velocities in the VFH (Vector Field Histogram) algorithm, based on the calculated sector accessibility index. The proposed method is a two-input and two-output Fuzzy Inference System, where the current robot heading, and sector accessibility index serve as the input, and the corresponding linear and angular velocities to the VFH algorithm are outputs. The VFH, VFH + and FISVFH are tested both in simulation and experimentation in 4 environments that are known to result in failures in VFH and VFH +, for comparison purposes. In addition, the algorithm was verified through experimental setup of a disaster prone environment. In both simulation and experimentation the results show that FISVFH outperforms VFH and VFH +. It is also shown that the FISVFH algorithm is capable of handling the disaster prone environment. Overall, the FISVFH algorithm enables the robot to get to the goal faster and also produces a smoother path while doing so.

A novel biologically-motivated neural networks approach associated with developed vector-driven autonomous robot navigation is proposed in this paper. The biologically-motivated neural networks (BNN) algorithm is employed to guide an autonomous robot to reach goal with obstacle avoidance motivated by Grossberg's model for a biological neural system. As the robot plans its trajectory toward the goal, unreasonable path will be inevitably planned. A vector-based guidance paradigm is developed for guidance of the robot locally so as to plan more reasonable trajectories. In addition, square cell map representations are proposed for realtime autonomous robot navigation. The BNN based scheme demonstrates that the algorithms avoid the issue of local minima in path planning. In this paper, both simulation and comparison studies of an autonomous robot navigation demonstrate that the proposed model is capable of planning more reasonable and shorter collision-free paths in non-stationary and unstructured environments compared with other approaches.

A neural network architecture for carrying out signature verification was developed and tested in an earlier study using a segment-based autoregressive characterization of the signatures. In this work the model and classifier are subjected to a more rigorous test using an extended database of realistic forgeries. While there is some deterioration in performance, it is shown that the proper selection of the modalities of training and the inclusion of time of execution of the signature as an additional feature make the model fairly robust. False Acceptance and False Rejection error rates of 0.78% and 1.6% respectively were obtained in tests conducted using 1920 skilled forgeries.

A segmentation technique based on dynamic time warping is investigated as a means of obtaining improved alignment between multiple signatures from a writer; the segments generated through this approach are represented by an autoregressive model. The signature verification performance is evaluated with a neural network based classifier, and shown to be a significant improvement over previous results obtained by the authors that were based on uniform segmentation.

An autoregressive hidden Markov model (ARHMM) is introduced for the analysis and classification of shape boundaries. The principal features of this model are: an autoregressive shape representation that is invariant to scaling, rotation and translation; a nonstationary contour characterization providing descriptions of abrupt and gradual changes in complex boundaries typical in image analysis; and a hidden Markov model (HMM) for description of such changes. An experimental study is presented which demonstrates the model's effectiveness.>

A survey of research efforts in the area of speaker recognition indicate that for the same choice of speaker-dependent speech parameters the recognition accuracy is significantly affected by the distance measure used. In this work several distance classifiers are evaluated for use in text-independent speaker identification. The four distance measures investigated are the Mahalanobis distance, maximum a posteriori probability, nearest neighbor criterion and the correlation distance measure. It is found that both the maximum a posteriori probability criterion and the correlation distance measure yield extremely poor results. The Mahalanobis distance and the nearest neighborhood criterion yield relatively poor results (error\sim20-30%) with the former consistently superior to the latter. It is shown that these scores can be improved through a proposed variation of the nearest neighbor method.

This work addresses the development of a reliable, high accuracy text-independent speaker recognition system for a small population, with the reference parameters characterizing each speaker obtained from short segments of speech. Initially the potential for speaker discrimination of several different vocal parameter sets was investigated. These included the LPC, Reflection, Cepstrum and Log Area Ratio coefficients, speech power spectrum parameters and the inverse filter spectral coefficients. It was then decided to use any two parameter sets in a composite decision-making scheme. A "repeat feature" was incorporated into the speaker recognition system, whereby a speaker was asked to read a fresh test speech segment if the decisions made by using the two different parameter sets individually were not coincident. Test results indicate that a significant improvement in accuracy is realizable.

The main objective of this work was to investigate the effectiveness of long-term averages of the orthogonal linear prediction parameters in text-independent speaker recognition. To investigate the possibility of feature selection, a technique using dynamic programming (1) was used to select a subset of k best features among the entire set N. The results indicate that the parameters comprising the optimal set chosen are speaker-dependedt. Verification accuracies of 96.5% were obtained using the selected optimal 8- parameter (out of 12) feature set for each speaker in a verification scheme, in which the reference parameters were generated from 100 seconds of time-spaced voiced speech and the test parameters were generated from 5 seconds of voiced speech.