ABSTRACT
In epidemic prevention and control measures, unmanned devices based on autonomous driving technology have stepped into the front lines of epidemic prevention, playing a vital role in epidemic prevention measures such as protective measures detection. Autonomous positioning technology is one of the key technologies of autonomous driving. The realization of high-precision positioning can provide accurate location epidemic prevention services and a refined intelligent management system for the government and citizens. In this paper, we propose an unmanned vehicle (UV) positioning system REW_SLAM based on lidar and stereo camera, which realize real-time online pose estimation of UV by using high-precision lidar pose correction visual positioning data. A six-element extended Kalman filter (6-element EKF) is proposed to fusion lidar and stereo camera sensors information, which retains the second-order Taylor series of observation and state equation, and effectively improves the accuracy of data fusion. Meanwhile, considering improving lidar outputs quality, a modified wavelet denoising method is introduced to preprocess the original data of lidar. Our approach was tested on KITTI datasets and real UV platform, respectively. By comparing with the other two algorithms, the relative pose error and absolute trajectory error of this algorithm are increased by 0.26 m and 2.36 m on average, respectively, while the CPU occupancy rate is increased by 6.685% on average, thereby proving the robustness and effectiveness of the algorithm.
ABSTRACT
Advanced Driver Assistance Systems (ADAS) are enabling technologies in Intelligent Transportation Systems. Modern ADAS include algorithms to classify drivers' actions and distractions, aiming at identifying situations in which the driver is inattentive. Such systems typically include components for Driver Action Recognition (DAR) and Visual Distraction Classification (VDC), which prevent risky situations during semi-autonomous driving. DAR and VDC often rely on cameras that track the driver and classify actions based on image recognition algorithms. The COVID-19 pandemic has changed several common social behaviours, including the widespread use of face mask even during driving. In some cases (taxi, bus) face covering policies are compulsory in many legislations. We here show that these behavioural changes challenge state-of-the-art DAR and VDC systems, with the average F1-score in some scenarios dropping by around 30% when exposed to images of drivers wearing masks. Noting a lack of public datasets to update the ML classifiers performing such tasks, we contribute Maskdar, a dataset for Action Recognition of Drivers wearing face Masks. Finally, using Maskdarwe show the importance of including subjects with face masks in datasets for DAR. © 2022 IEEE.
ABSTRACT
LiDAR sensors are widely used in autonomous driving, mobile robotics, aerospace, manufacturing, and many other fields. The speed, reliability, and range of LiDAR sensors can be affected by environmental conditions and usage patterns. Each application requires a deep understanding of sensor limitations. This paper explores the operational parameters of one of the most miniature and least expensive LiDAR sensors packaged in a wearable case. The target application, in this case, is social distancing during pandemics. This study focuses on the performance of miniature LiDAR sensors under different levels of light intensity, temperature, distance to the object, object size, angle of view, and object color. The experimental data enables a match between the sensor capabilities and application scenarios and provides direction for future work in improving the wearable sensors of this class. © 2022 IEEE.
ABSTRACT
Multi-object tracking is of great importance in autonomous driving. However, with the outbreak of COVID-19, multi-object tracking faces new challenges in areas gripped by epidemics because of complex motion blur, frequent occlusions, and appearance deformations. To reliably improve object trajectory association in epidemic-plagued areas, we propose a temporal-spatial aggregation embedding network (TSAEN) for multi-object tracking. Our embedding network contains a temporal-aware correlation module (TACM) and spatial-aggregate embedding module (SAEM) that can fully obtain and aggregate appearance clues related to moving objects in previous frames. The TACM learns the temporal homogeneity features of the current and previous frames to perceive features with correlated appearance cues. Then, the SAEM adjusts the spatial deformation for each perceived temporal homogeneity feature and aggregates them for re-ID embedding learning. The experimental results demonstrate that our proposed method is able to achieve excellent overall performance. IEEE
ABSTRACT
In recent years, engineering degree programs have become fundamental to the teaching of robotics and incorporate many fundamental STEM concepts. Some authors have proposed different platforms for teaching different topics related to robotics, but most of these platforms are not practical for classroom use. In the case of teaching autonomous navigation algorithms, the absence of platforms in classrooms limits learning because students are unable to perform practice activities or cannot evaluate and compare different navigation algorithms. The main contribution of this study is the implementation of a free platform for teaching autonomous-driving algorithms based on the Robot Operating System without the use of a physical robot. The authors present a case study using this platform as a teaching tool for instruction in two undergraduate robotic courses. Students evaluated the platform quantitatively and qualitatively. Our study demonstrates that professors and students can carry out different tests and compare different navigation algorithms to analyze their performance under the same conditions in class. In addition, the proposed platform provides realistic representations of environments and data visualizations. The results claim that the use of simulations helps students better understand the theoretical concepts, motivates them to pay attention, and increases their confidence.
ABSTRACT
Autonomous vehicles have become important with the emergence of Logistics 4.0. Moreover, truck-based transport has become the critical means of transport in the logistics market. Thus, to deal with the pending issues of the logistics market, it is not enough to merely expand the workforce. Adopting autonomous trucks will also help change the truck allocation structure. This may enable horizontal and vertical integration based on the new logistics model and help address various problems faced by shipping companies. Thus, adopting autonomous trucks can provide various benefits for the logistics business, society, and consumers. However, adopting autonomous trucks does not only have benefits. Here, this study suggests truck platooning as a method of adopting autonomous trucks more efficiently. Furthermore, we approach the potential issues regarding autonomous truck adoption from various perspectives by demonstrating the efficiency of autonomous trucks as well as their problems.
ABSTRACT
The Covid-19 pandemic caused worldwide tragic loss of human life along with social and economic disruptions. The hospitality and tourism sectors were particularly hit hard due to lockdowns for maintaining social distancing to handle the spread of the disease. In this crisis scenario, the adoption of artificial intelligence (AI) and robotics gave massive support to hospitals, hotels, airports, transportation systems, scenery areas and society. Technology played a significant role to reduce human contact and the potential spread of the virus. Humanoid robots, drones, autonomous driving vehicles, and socially intelligent robots performed essential tasks like disinfecting public areas, delivering necessities at people's doorstep, giving safety, measuring body temperature and comforting the patients. This article depicts different roles played by the robots in various sectors during the pandemic and particularly highlights the opportunity that AI and robotics can provide to the hospitality and tourism industry. Tourism and hospitality scholars should develop and adopt robotic applications to foster guests' experiences and protect natural and cultural resources. The use of robotic applications in future can be further used to improve people's collaboration in tourism development. © 2021 IEEE.
ABSTRACT
The paper shows best-practice examples to bring “Smart Cities” with focus on self-driving cars into a classroom. Target group are students from engineering education institutions. Theory concepts and practical concepts of Smart Cities are implemented with students of the department of mechanical engineering at the TGM Vienna, a higher technical college. The students with whom the experimental set-up is being developed focus on robotics and vehicle technology. Existing systems such as a racetrack, self-driving model cars with Arduino microcontrollers are used. The simulation of electronics and programming is partly done via distance learning due to the limitations of the Covid-19 pandemic. Together with the students, a demo system is built step by step in which central aspects of Smart Cities in relation to self-driving cars can be investigated. Because there are so many disciplines combined in Smart Cities, we split them into different learning sessions. The topics are basics of autonomous driving and vehicle-to-everything (V2X) communication. We use available online tools, so that the students can do their exercises at home. The concept of Smart Cities is presented and implemented jointly by students and teachers in the classroom with demonstrative practical concepts. Teamwork and interdisciplinary learning are actively supported. The experimental set-up can be reused and extended. The paper discusses key aspects and concepts and gives useful examples of how this topic can be taught in class using a demo system. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The spread of Covid-19 has raised the importance of unmanned and disinfection tasks, therefore the development and commercialization of service robots, such as disinfection robots, is actively underway. In addition, modern society is a personalized, where individuality is valued, with understanding and interaction of individual tastes and preferences, playing an important factor in value creation. Individual understanding starts with communication, and in this context, popularization of service robots believes that smooth interaction between humans and robots is a factor that determines success, and research is needed. In this research, the design of robots performing disinfection tasks in subway stations is studied for interactions in which robots coexist with humans and facilitate disinfection tasks. Through this work, a designed subway disinfection robot system and an appearance design considering human-centered factors are proposed. It also designed practical Human-Robot Interaction elements such as displays, voice, and laser projectors, and presented ways to utilize them to respond to possible situations in the subway. In particular, measures are shown to solve the structural problems of robots through human consideration and interaction in disinfection tasks and elevator boarding situations.
ABSTRACT
The responsibility of transporting COVID-19 patients usually falls on the Emergency Medical Service (EMS) department in a hospital. This responsibility exposes EMS workers to high coronavirus infection risks, and we cannot bear the cost of the collapse of EMS. In this paper we explore the feasibility of utilizing autonomous vehicles for patient transportation for reducing the risks of care workers. © 2021 IEEE.