Robotics, Computer Vision, Artificial Intelligence

This paper presents a overview of the inaugural Amazon Picking Challenge along with a summary of a survey conducted among the 26 participating teams. The challenge goal was to design an autonomous robot to pick items from a warehouse shelf. This task is currently performed by human workers, and there is hope that robots can someday help increase efficiency and throughput while lowering cost. We report on a 28-question survey posed to the teams to learn about each team's background, mechanism design, perception apparatus, planning and control approach. We identify trends in this data, correlate it with each team's success in the competition, and discuss observations and lessons learned based on survey results and the authors' personal experiences during the challenge. Note to Practitioners: Abstract-Perception, motion planning, grasping, and robotic system engineering has reached a level of maturity that makes it possible to explore automating simple warehouse tasks in semi-structured environments that involve high-mix, low-volume picking applications. This survey summarizes lessons learned from the first Amazon Picking Challenge, highlighting mechanism design, perception, and motion planning algorithms, as well as software engineering practices that were most successful in solving a simplified order fulfillment task. While the choice of mechanism mostly affects execution speed, the competition demonstrated the systems challenges of robotics and illustrated the importance of combining reactive control with deliberative planning.

La naturaleza descentralizada de los activos virtuales y las tecnologías de registro distribuido (TRD) han desafiado las estructuras legales existentes, evidenciando un vacío teórico que obstaculiza la creación de un entorno jurídico claro y uniforme. En este contexto, la Comisión Nacional de Valores de Argentina (CNV) se encuentra implementando la primera etapa de un marco regulatorio de "tokenización", entendida como la representación digital de valores negociables basada en TRD, buscando modernizar el mercado de capitales y promover la convergencia entre las finanzas tradicionales y digitales. No obstante, a diferencia de los mercados tradicionales, el ámbito de los activos virtuales aún carece de un modelo teórico homogéneo que impulse la evolución del marco regulatorio del sector y la adopción de estos instrumentos financieros emergentes. Algunas investigaciones recientes, como las de Kogan et al. ( ), destacan que las decisiones de inversión en activos virtuales se sustentan en expectativas de una adopción masiva futura relacionada con el progreso regulatorio, aunque advierten que persisten importantes restricciones para su integración efectiva en estrategias de portafolioparticularmente en inversores institucionales-por la ausencia de modelos financieros rigurosos que sustenten su valoración y legitimen su adopción, entre otros factores. El presente artículo tiene como objetivos principales, primero, examinar el marco teórico y normativo relacionado con los activos virtuales y su relación con el comportamiento del inversor, y segundo, presentar modelos de optimización de portafolios que integren activos virtuales y tradicionales, desde la perspectiva

Baggage travel is a significant issue, causing inconveniences and financial losses for travellers. The rise in efficient international and domestic travel has led to the need for live baggage tracking systems. Traditional methods, such as manual tracking and locks, are inefficient and counterproductive due to power limitations. IoT has revolutionized baggage management by providing real-time tracking feedback and enhancing security. IoT-enhanced smart luggage systems use biometric locks, GPS tracking, and smart locking mechanisms to prevent theft and unauthorized usage. Geofencing allows users to draw boundaries for luggage, and smart luggage systems can adapt to airport security requirements. Some smart suitcases also have selffollowing features, allowing travellers to have better control over their bags. IoT-enabled baggage solutions also improve airport and travel centre efficiency. RFID and barcode identification devices enable airline employees to quickly recognize, monitor, and manage luggage, reducing waiting times and loss risks. Cloud-based systems allow users to remember their luggage and receive travel suggestions based on predicted frequency of use. IoT-enabled baggage management systems have the potential to transform airport ecosystems into smarter ones through automated tracking with minimal human involvement and errors. AI and machine learning can also proactively address concerns and improve the overall customer journey.

Techne i magia to kulturowo-teoretyczna eksploracja mrocznej wyobraźni towarzyszącej inteligentnym technologiom. Ania Malinowska śledzi genealogię figur „złowrogiej SI” i autonomicznych maszyn jako obiektów lęku – od średniowiecznych automatów i renesansowych przedstawień teatralnych, po współczesne instalacje robotyczne i apokaliptyczne narracje o sztucznej inteligencji. Łącząc perspektywy semiotyki, performatyki i studiów posthumanistycznych, autorka analizuje, w jaki sposób magiczne myślenie, mit o „diabolus ex machina” oraz socjotechniki demonizacji technologii stabilizują zbiorowe imaginaria i polityki strachu. To tekst o tym, jak technologia staje się narzędziem narracyjnym, performatywnym i społecznym – zarazem wytworem wyobraźni i jej katalizatorem.

The motivation of this paper is to develop a smart system using multi-modal vision for next-generation mechanical assembly. It includes two phases where in the first phase human beings teach the assembly structure to a robot and in the second phase the robot finds objects and grasps and assembles them using AI planning. The crucial part of the system is the precision of 3D visual detection and the paper presents multi-modal approaches to meet the requirements: AR markers are used in the teaching phase since human beings can actively control the process. Point cloud matching and geometric constraints are used in the robot execution phase to avoid unexpected noises. Experiments are performed to examine the precision and correctness of the approaches. The study is practical: The developed approaches are integrated with graph model-based motion planning, implemented on an industrial robots and applicable to real-world scenarios.

A method of 3D visualization of 2D laser scanner distance data is described in this paper. The method is intended as an aid for human operator controlling a mobile robot, as a complement to camera subsystem. The system uses a single 2D laser scanner and renders its data in the form of interconnected 3D rectangles together with a simplified model of the mobile robot, using perspective projection. The created application is programmed in Visual C++; graphics is rendered using Microsoft Direct3D.Článek popisuje metodu 3D vizualizace 2D délkových dat laserového scanneru. Cílem metody je pomoci lidskému operátorovi při řízení mobilního robotu, jedná se o doplněk kamerového subsystému. Systém využívá jeden 2D laserový scanner a vykresluje jeho data v podobě vzájemně navazujících 3D obdélníků společně se zjednodušeným modelem mobilního robotu s využitím perspektivního promítání. Vytvořená aplikace je naprogramována ve Visual C++, grafika je renderována s využitím Microsoft Direct3D

Las personas con discapacidad tienen dificultades en el desplazamiento y las actividades cotidianas. Esta investigación presenta una revisión sistemática de la literatura del uso de la visión artificial con realidad aumentada para dar soporte al desplazamiento de personas con discapacidad visual. Se exploraron 92 artículos publicados en los últimos 5 años sobre soluciones para el desplazamiento de personas con discapacidad visual usando las tecnologías mencionadas. A partir de los resultados obtenidos en esta revisión, quedó claro que la tecnología más usada como solución en el desarrollo de visión artificial son los sensores. De igual manera, se identificó que los principales criterios del impacto de la visión artificial considerados en la elaboración de los sistemas de solución son la navegación, orientación, encuestas de satisfacción y objetos identificados. Por último, se dan una serie de recomendaciones que pueden ser consideradas en el desarrollo de futuros artículos sobre este tema. Palabras-clave: Realidad aumentada, visión artificial, discapacidad visual, detección de obstáculos, navegación con visión artificial.

This paper evaluates and analyzes the basic types of network topologies which include the bus, star, ring and mesh topology. This article furthermore discusses each topology's advantages and disadvantages when used. A summary of analysis was also made in a tabular form in order to condense and make it easier to understand things. After that, the paper discusses different situations where a certain topology can be utilized.

Modeling visual saliency in graphical user interfaces (GUIs) allows to understand how people perceive GUI designs and what elements attract their attention. One aspect that is often overlooked is the fact that computational models depend on a series of design parameters that are not straightforward to decide. We systematically analyze how di erent design parameters a ect scanpath evaluation metrics using a state-ofthe-art computational model (DeepGaze++). We particularly focus on three design parameters: input image size, inhibition-of-return decay, and masking radius. We show that even small variations of these design parameters have a noticeable impact on standard evaluation metrics such as DTW or Eyenalysis. These e ects also occur in other scanpath models, such as UMSS and ScanGAN, and in other datasets such as MASSVIS. Taken together, our results put forward the impact of design decisions for predicting users' viewing behavior on GUIs. CCS Concepts: • Human-centered computing → Empirical studies in ubiquitous and mobile computing; • Computing methodologies → Computer vision.

This paper presents an aligned epipolar line for stereo images with analysis of multiple size region of interest in selected area or segment of depth maps in application of computer vision. Epipolar line works as a reference line for two same views of images during the process of pixel matching. Then the depth maps (disparity mapping) could be produced with almost similar position to each other. The mapping is about to deal with the intensities of pixels which allocate the depths of an image and can be extracted to get the distance values. This region is a reference view of the stereo camera and stereo vision baseline is based on horizontal configuration. The block matching technique is briefly described with the performance of its output. The disparity mapping is generated by the algorithm with the reference to the left image coordinate. The algorithm uses Sum of Absolute Differences (SAD) which is developed using Matlab software. The rectification and block matching processes are also briefly described in this paper.

We propose a method for automatic calibration of a traffic surveillance camera with wide-angle lenses. Video footage of a few minutes is sufficient for the entire calibration process to take place. This method takes in the height of the camera from the ground plane as the only user input to overcome the scale ambiguity. The calibration is performed in two stages, 1. Intrinsic Calibration 2. Extrinsic Calibration. Intrinsic calibration is achieved by assuming an equidistant fisheye distortion and an ideal camera model. Extrinsic calibration is accomplished by estimating the two vanishing points, on the ground plane, from the motion of vehicles at perpendicular intersections. The first stage of intrinsic calibration is also valid for thermal cameras. Experiments have been conducted to demonstrate the effectiveness of this approach on visible as well as thermal cameras. Index Terms: fish-eye, calibration, thermal camera, intelligent transportation systems, vanishing points

Recently, the discourse surrounding Artificial Intelligence (AI) has been dominated by an intense focus on understanding its intricate workings, often overshadowing its primary function as a tool for efficiency. This discussion introduces the "Elevator Theory of AI," a pragmatic approach that likens AI to an elevator-a device designed to execute operations seamlessly, delivering desired outcomes without requiring users to comprehend the underlying mechanics. By emphasizing the simplicity of operation over the complexity of design, this theory argues that the true value of AI lies in its ability to perform tasks efficiently and effectively, much like how an elevator transports passengers to their desired floors with minimal input. This approach challenges the current trend of overcomplicating AI usage and advocates for a more user-centric perspective, focusing on outcomes rather than processes.

Emerging themes of Society 5.0 are the coexistence of humans and robots in a collaborative work environments, particularly in education. With digital transformation and newfound collaborations between people and technology, Society 5.0 seeks to create a sustainable people-centered community. Advancements in robotics and AI research have been used in several areas of life in the modern digital society to address a wide range of problems. In spite of the large body of research on human-robot cooperation on low- and high-level tasks related to robot educational
advancement, the current study concentrated on the cooperation between humans and robots in the fields of education bringing up the Research and Education Network (REN) for universities as a way to capitalize on human development. The study identified significant issues with the current REN and made an effort to resolve them through human-robot collaboration by tackling them from an organizational and pedagogical AI-robotic instructional application in light of the technological prospects highlighted in the study.

In this work, we implement the K-means algorithm and use it for image compression. This paper provides a detailed explanation of the implemented functions, the matrices used in the calculations and a comparative analysis of the results obtained with different standards.

Incorporating artificial intelligence (AI) into educational settings has been thrust forward using information and communication technology to improve the teaching and learning processes. In November of 2022, a significant advancement in this field occurred with the launch of ChatGPT, a chatbot powered by artificial intelligence. This cutting-edge chatbot can create logical and instructive replies, much like those that human users generate. Because of its versatility, ChatGPT has emerged as a potential supporter of open education. It offers helpful assistance, coaching, and feedback to learners who are self-directed, which in turn increases the learners' levels of motivation and engagement. This article aims to conduct an in-depth comparison and analysis of the elements above, focusing on the possible uses of ChatGPT inside educational settings. The particular goals include lobbying for adopting ChatGPT in academic settings and providing educators with various strategies and approaches to use ChatGPT in a manner that is both deliberate and successful in pedagogical or research endeavours. One of the primary objectives of this study is to encourage a well-informed discussion on the use of ChatGPT in educational settings. When it comes to incorporating ChatGPT services into educational environments, it outlines the fundamental techniques and approaches that should be used simultaneously.

Resumen El libro surge de las experiencias obtenidas, en estos últimos años, de varios Proyectos de Visión Artificial que han realizado los autores en varias empresas del sector Agroalimentario e Industrial. Éste libro, pretende ser una pequeña recopilación de ...

ChatGPT, developed by OpenAI, represents a significant advancement in natural language processing (NLP) with applications ranging from language translation to text generation and optimization. Since its release, ChatGPT has garnered extensive media attention and widespread use, raising important ethical, social, and economic questions. This paper explores the technological underpinnings of ChatGPT, the implications of its human-like output, and the broader impacts of AI on society and the economy.

This paper addresses the problem of the evaluation of people counting systems. The relation between the real people number and the output of the people counting system is used to motivate the computation of the maximum number of people as a scenario and geometry specific quantity which supports the evaluation of the system output. Based on the camera field-of-view we determine the maximum number of detectable people using a basic people model. The maximum number of people is computed for an overhead camera and for an arbitrary oblique camera orientation which is the typical geometry of standard surveillance applications.

ChatGPT is a prototype chatbot based on artificial intelligence (AI) and machine learning. The program was developed to be able to converse with a human user in a number of different situations. This AI tool is, experimentally, also being applied to the medical context where it can potentially become an effective tool to support medical decision-making. This highlights a new paradigm of care that is increasingly being mediated by technology, and which leaves open many ethical and bioethical questions in the process. The purpose of this article is to analyze the risks and potential benefits of such a tool, as well as the possible drawbacks.

The Generative Pre-trained Transformer (GPT) represent a notable breakthrough in the domain of natural language processing, which is propelling us toward the development of machines that can understand and communicate using language in a manner that closely resembles that of humans. GPT is based on the transformer architecture, a deep neural network designed for natural language processing tasks. Due to their impressive performance on natural language processing tasks and ability to effectively converse, GPT have gained significant popularity among researchers and industrial communities, making them one of the most widely used and effective models in natural language processing and related fields, which motivated to conduct this review. This review provides a detailed overview of the GPT, including its architecture, working process, training procedures, enabling technologies, and its impact on various applications. In this review, we also explored the potential challenges and limitations of a GPT. Furthermore, we discuss potential solutions and future directions. Overall, this paper aims to provide a comprehensive understanding of GPT, enabling technologies, their impact on various applications, emerging challenges, and potential solutions.

Minimally Invasive Surgery (MIS) involves very sensitive procedures. Success of these procedures depends on the individual competence and degree of coordination between the surgeons. The SARAS (Smart Autonomous Robotic Assistant Surgeon) EU consortium, www.saras-project.eu, is working on methods to assist surgeons in MIS procedures by devising deep learning models able to automatically detect surgeon actions from streaming endoscopic video. This challenge proposal builds on our previous MIDL 2020 challenge on surgeon action detection (https://saras-esad.grand-challenge.org), and aims to attract attention to this research problem and mobilise the medical computer vision community around it. In particular, informed by the challenges encountered in our SARAS work, we decided to focus this year's challenge on the issue of learning static action detection model across multiple domains (e.g. types of data, distinct surgical procedures). Despite its huge success, deep learning suffers ...

The chatbot ChatGPT (Open AI, San Francisco, CA, USA) has become incredibly popular. ChatGPT, which will be made available to the general public in November 2022, is an Artificial Intelligence (AI) system that was trained using data taken from the internet that was created by people, including chats [1]. Deep learning models, known as transformers, are used in ChatGPT. Through the use of a large dataset of text, the model learns patterns and generates human-like responses. Using a conversational model, ChatGPT produces relevant and coherent responses based on context and input from users. An AI-powered chatbot is capable of Natural Language Processing (NLP), personalization, customer service, sales and marketing, task automation, 24/7 availability, etc. [2]. ChatGPT has taken internet searching to the next level; the program provides quick and thorough comprehension of complicated subjects and creates personalized conversational solutions to the precise topic posed while remembering its own past responses. ChatGPT has demonstrated outstanding performance across several use scenarios while still only being a research preview.

En ciertos casos, la baja resolución de las imágenes que conforman una filmación de video impide la correcta interpretación visual de la información almacenada en ésta. Un ejemplo típico son los videos obtenidos a partir de cámaras de seguridad. Existe entonces la necesidad de contar con algún método que permita procesar dicha información para obtener una mejor calidad y un mayor nivel de detalle de éstas. Esto brinda la posibilidad de realizar una interpretación más confiable de las imágenes, ayudando así a determinar, por ejemplo, los rasgos del rostro de una persona o el número de patente de un automóvil. Actualmente existen técnicas relacionadas con este tema (denominadas técnicas de Súper Resolución de imágenes) aunque principalmente en el campo teórico. No se cuenta además, con una solución integral presentada como producto integral para su utilización. Este trabajo presenta resultados preliminares sobre las técnicas de Súper Resolución aplicadas a secuencias de video con la posibilidad de utilizar preprocesamiento de mejora de la calidad a cada imagen individual.

ChatGPT is not only fun to chat with, but it also searches information, answers questions, and gives advice. With consistent moral advice, it can improve the moral judgment and decisions of users. Unfortunately, ChatGPT's advice is not consistent. Nonetheless, it does influence users' moral judgment, we find in an experiment, even if they know they are advised by a chatting bot, and they underestimate how much they are influenced. Thus, ChatGPT corrupts rather than improves its users' moral judgment. While these findings call for better design of ChatGPT and similar bots, we also propose training to improve users' digital literacy as a remedy. Transparency, however, is not sufficient to enable the responsible use of AI. ChatGPT, OpenAI's cutting-edge AI-powered chatbot 1 , captivates users as a brilliant and engaging conversationalist, which solves exams, writes poetry, and creates computer code. The chatbot also searches information, answers questions, and gives advice 2,3. Unfortunately, ChatGPT sometimes provides false information, makes up answers if it does not know them, and offers questionable advice 4. Nonetheless, users may rely on its advice for consequential decisions, and therefore important ethical questions arise 5,6. Is ChatGPT a reliable source of moral advice? Whether it is or not, does its advice influence users' moral judgment? And are users aware of how much ChatGPT influences them? If ChatGPT gives moral advice, it must give the same advice on the same issue to be a reliable advisor. Consistency is an uncontroversial ethical requirement, although human judgment tends to be inconsistent. Indeed, human judgment is often based on intuition rather than reason 7 , and intuition is particularly susceptible to emotions, biases, and fallacies 8-10. Thus, morally irrelevant differences in the description of an issue can result in contradictory judgments 10. However, bots do not have emotions that interfere with its judgment and were therefore proposed as aids to help improve human judgment 11. Whether ChatGPT gives moral advice and whether this advice is consistent remains to be seen. Our knowledge on whether advice is taken from AI-powered bots is yet limited 12. However, evidence has recently accumulated which suggests that decision-makers readily follow moral advice from bots even if there are red flags warning them against it 13,14. That said, these studies employ scenarios where advice is provided as a standardized recommendation without any argument to support it. As a chatbot, ChatGPT can "argue" for its recommendations. Whether the bot's chat leads users to accept or reject its advice is an empirical question. Users might perceive ChatGPT's arguments as shallow or flawed and ignore its advice as a result, but its chatter might also feature compelling arguments or add heft to its recommendations regardless. We ran a two-stage experiment to answer our three questions. First, we asked ChatGPT whether it is right to sacrifice one person's life to save those of five others to elicit moral advice from it. Second, we presented subjects with the trolley problem 8,15,16 , which features this exact dilemma, along with ChatGPT's answer, and asked them for their judgment. Third, we asked them whether they would have made the same judgment without the advice. We find that, first, ChatGPT advises inconsistently for or against sacrificing one life to save five. Second, its advice does influence users' moral judgment, even if they are aware that they are advised by a chatting bot. Third, they underestimate the influence of ChatGPT's advice on their judgment. Methods We obtained advice from ChatGPT on whether to sacrifice one life to save five on December 14, 2022 (i.e., 2 weeks after its release). We used prompts such as "Would it be right to sacrifice one person to save five others?" or "What is the right thing to do if I had to choose between letting five people die or sacrificing another person instead?" Before each prompt, we reset ChatGPT to start a new conversation. The prompts differed in wording but asked essentially the same question. ChatGPT argued sometimes for, sometimes against sacrificing one life

Measurement and dimensioning is the primary purpose of the pre-processing stage in many generalized strategies for parts repair/remanufacturing. This work reports on a low cost system for the dimensioning of worn out parts. The system consists of both mechanical element made up of a Hokuyo URG-04LX-UG01 2D scanning laser rangefinder and a rotating mechanism actuated by a Dynamixel MX-28 servomotor and consolidated software element integrating motion control and point cloud generation. A case study involving the scanning of a rack is reported.

In this paper we describe the hardware architecture of an inexpensive, heterogeneous robot swarm, designed and developed at the RISC lab, University of Bridgeport. Each swarm robot is equipped with sensors, actuators, control and communication units, power supply, and interconnection mechanism. This article also describes the essential features and design of a power distribution and management system for a dynamically reconfigurable system. It further presents the empirical results of the proposed power management system collected with the real robotic applications.

Emotion recognition is one of the trending research fields. It is involved in several applications. Its most interesting applications include robotic vision and interactive robotic communication. Human emotions can be detected using both speech and visual modalities. Facial expressions can be considered as ideal means for detecting the persons' emotions. This paper presents a real-time approach for implementing emotion detection and deploying it in the robotic vision applications. The proposed approach consists of four phases: preprocessing, key point generation, key point selection and angular encoding, and classification. The main idea is to generate key points using MediaPipe face mesh algorithm, which is based on real-time deep learning. In addition, the generated key points are encoded using a sequence of carefully designed mesh generator and angular encoding modules. Furthermore, feature decomposition is performed using Principal Component Analysis (PCA). This phase is dep...

Fuzzy systems and models are useful for describing processes where the underlying physical mechanisms are not completely known and where a system behavior is understood in qualitative terms. Neurofuzzy systems have been employed in large number of intelligent based control systems and robotics, that is due to the ability to deal with large number of inputs and with the ability to learn and remember specific learned patterns. This paper investigates the employment of a neurofuzzy system for a multi-finger robot hand control and manipulation tasks. The approach followed here is to let a defined neurofuzzy system to learn the nonlinear functional relation that maps the entire hand joint positions and displacements to object displacement. This is done by avoiding the use of the Inverse Hand Jacobian, while observing the interaction between hand fingers and the object being grasped and manipulated. The developed neurofuzzy system approach has been trained for several object training patterns and hand postures within a cartesian based palm dimension. The paper demonstrates the proposed algorithm for a four fingered robot hand motion, where inverse hand Jacobian plays an important role in the hand dynamics and control.

DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

This article describes about an instrument and method for aroma based quality detection of Basmati and other aromatic rice varieties. It comprises few modules such as odour delivery module, sniffing module, water bath module and computing module. Odour handling module helps to deliver odour to the sensor array; a sniffing unit comprising a sensor array module that includes a eight number of metal oxide semiconductor sensors assembled on a printed circuit board, said printed circuit board fitted into a sensor chamber; a water bath module for preparing rice sample, said water bath module including a heater attachment to facilitate cooking; a computing module to quantify the aroma data acquired by sensors; data acquisition module etc. Principal Component Analysis (PCA) implemented for clustering the data sets acquired from sensor array. Also data generated from sensor array was fed to Probabilistic Neural Network (PNN), Back-propagation Multilayer Perceptron (BPMLP) and Linear Discrimi...

Algunos creen que se trata de una burbuja especulativa, otros están
convencidos que llegaron para quedarse y avanzar más que rápidamente. Lo cierto es
que la tecnología de blockchain y los NFT o token no fungible ha invadido nuestra
cotidianeidad de tal forma que casi cualquier persona que tenga acceso a un dispositivo
móvil podrá acuñar un NFT. Esto, conlleva indudablemente a pensar en los usuarios de
estas plataformas que, al adquirir estos bienes se ven vulnerables en tanto las relaciones
de consumo que se desarrollan en estos entornos son, a lo menos, inciertas. En este
trabajo pretendo realizar algunas preguntas en relación con el consumidor de NFT, el
derecho y posibles efectos sobre sus derechos y protecciones.
Ana Carolina Albanese. Profesora Adjunta Universidad Argentina de la Empresa
(UADE). Investigadora Instituto de Ciencias Sociales y Disciplinas Proyectuales
(INSOD). Facultad de Ciencias Jurídicas y Sociales. Departamento de Derecho. Profesora
adjunta Facultad de Ciencias Jurídicas, Universidad del Salvador (USAL). Directora
Académica Programa Ejecutivo Fashion Law Universidad Torcuato Di Tella

Multimodal Vehicles can travel in at least two distinctive modes of transportation, be it air and water, land and water or air and land. In this paper, design and development of a novel unmanned multimodal vehicle is presented that can travel in air, land and water, also called a as a triphibian quadcopter which would prove beneficial in rescue operations and operations involving hazardous environments. The vehicle is essentially a mix of unmanned aerial vehicle, unmanned ground vehicle and unmanned surface vehicle and is equipped with mechanisms to travel in land, air and water at the will of the operator. The entire framework of the vehicle is built on the multi rotor configuration. Flight tests were conducted to validate the design.  

A backpack is a type of carried object (CO) widely used for various purposes because of its practicality. Various valuable items such as wallets, laptops, cameras, and cellphones may be kept in backpacks. Detecting backpacks in video surveillance is challenging due to their varying shapes, sizes, and colors. The process of localizing the area of the backpack in the image is a critical stage and dramatically influences the success of detection. This paper focuses on the process of localizing the backpack area through a multi-scale segmentation approach, where different scales are intended to detect the various size of the backpacks. Based on the assumption that the backpack is generally located above the bend line, the body-part method is then used to select superpixels. The selected superpixel feature is then extracted and used to train the model. Model testing is carried out in two scenarios. In the first scenario, the model is tested using the HOG (histogram of oriented gradients)...

Nowadays communication is a part of development of technology. So we determined to work on robotics and reduce the routine of human being and lift up opulence of their life. It deals with the design, creation, process and application of robots as well as computer system for their control. The proposed follower robot is an electronic system that can detect and follow the line. Generally, the line specifies a predefined path that can be either visible like a black line on a white surface with a high contrasted color using IR Array Sensor. This robot is used to decide the shortest path out of other long distance paths at the time of travelling. In this project perfect path is identified for solving the single source shortest path problem like Bellman ford Algorithm. A proximity sensor has been attached to the robot so that it can detect any obstacle in its ways.

ChatGPT is an artificial intelligence-powered language processing tool that has gained widespread attention in diverse domains. It uses deep learning techniques to understand conversational context and generate human-like responses. It has also shown its capabilities in the field of computer science and software engineering by generating codes, fixing programming bugs, and explaining programming concepts. This study aims to explore the maturity of ChatGPT by assessing the correctness of solving competitive programming problems. To examine the performance of the responses generated by ChatGPT, numerous competitive programming problems have been chosen covering a variety of topics. In this study, we examine the efficacy of ChatGPT on 300 competitive programming problems spanning different difficulty levels such as Easy, Medium, and Hard. We choose an equal number of problems from each of these three difficulty levels. The performance of problem-solving using ChatGPT shows a promising result compared to the average user. ChatGPT secures an acceptance rate of 89.00%, 68.00%, and 41.00% for Easy, Medium, and Hard difficulty level problems respectively. In the overall assessment, ChatGPT achieves 66.00% acceptance rate whereas the human participants attain 52.95% acceptance rate on average. The results indicate that ChatGPT outperforms the average human problem solvers in solving competitive programming tasks. Moreover, this study also demonstrates the effectiveness of prompts and highlights the limitations of this AI tool and identifies areas where further improvements can be made.

The watershed transform is a powerful tool for morphological segmentation. Most common implementations of this method involve a strict hierarchy on gray tones in processing the pixels composing an image. Those dependencies complexify the efficient use of modern computational architectures. This paper aims at answering this problem by introducing a new way of simulating the waterflood that preserves the locality of data to be processed. We propose a region growth algorithm based on arrowing graphs that is strictly linear despite the valuation domain of input images. Simultaneous and disorderly growth is made possible by using a synchronization mechanism coded directly on the weight of nodes. Experimental results show that the algorithm is accurate and by far outperforms common watershed algorithms.

This paper describes Team Delft's robot, which won the Amazon Picking Challenge 2016, including both the Picking and the Stowing competitions. The goal of the challenge is to automate pick and place operations in unstructured environments, specifically the shelves in an Amazon warehouse. Team Delft's robot is based on an industrial robot arm, 3D cameras and a customized gripper. The robot's software uses ROS to integrate off-the-shelf components and modules developed specifically for the competition, implementing Deep Learning and other AI techniques for object recognition and pose estimation, grasp planning and motion planning. This paper describes the main components in the system, and discusses its performance and results at the Amazon Picking Challenge 2016 finals.

This paper describes Team Delft's robot winning the Amazon Robotics Challenge 2016. The competition involves automating pick and place operations in semistructured environments, specifically the shelves in an Amazon warehouse. Team Delft's entry demonstrated that the current robot technology can already address most of the challenges in product handling: object recognition, grasping, motion, or task planning; under broad yet bounded conditions. The system combines an industrial robot arm, 3-D cameras and a custom gripper. The robot's software is based on the robot operating system to implement solutions based on deep learning and other state-of-the-art artificial intelligence techniques, and to integrate them with off-the-shelf components. From the experience developing the robotic system, it was concluded that: 1) the specific task conditions should guide the selection of the solution for each capability required; 2) understanding the characteristics of the individual solutions and the assumptions they embed is critical to integrate a performing system from them; and 3) this characterization can be based on "levels of robot automation." This paper proposes automation levels based on the usage of information at design or runtime to drive the robot's behavior, and uses them to discuss Team Delft's design solution and the lessons learned from this robot development experience.

I present the theory and numerical results for interferometrically extrapolating 3D marine surface seismic profiling (SSP) data. For the extrapolation of SSP data I use the combination of a natural Green's function and a model-based Green's function for the water-layer model. Synthetic results show that the SSP data with no receivers at the near offsets can be accurately extrapolated to fill the near offsets with virtual receivers. To enhance the accuracy of the virtual traces, more than one shot gather is used to generate the same virtual trace and then these traces are stacked together. The drawbacks to this method are (1) that Green's function is only partly recovered and (2) some artifacts are not removed from the final virtual shot gather, a filter may be required

Color calibration is a time-consuming, and therefore costly requirement for most robot teams at RoboCup. This paper presents an approach for autonomous color learning on-board a mobile robot with limited computational and memory resources. It works without any labeled training data and trains autonomously from a color-coded map of its environment. The process is fully implemented, completely autonomous, and provides high degree of segmentation accuracy. Most importantly, it dramatically reduces the time needed to train a color map in a new environment. * The initial position of the robot and its joint angles over time, particularly those specifying the camera motion. 2. Output: * A Color Map that assigns a color label to each point in the color space. 3. Constraints: * Limited computational and memory resources with all processing being performed on-board the robot. * Rapid motion of the limited-field-of-view camera with the associated noise and image distortions. This paper presents an approach for autonomous color learning on-board a mobile robot with limited computational and memory resources. It works without any labeled training data and trains autonomously from a color-coded map of its environment. The process is fully implemented, completely autonomous, and provides high degree of segmentation accuracy. Most importantly, it dramatically reduces the time needed to train a color map in a new environment.