• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.33-38
• /
• 2024

In this paper, we propose the implementation of a drone delivery system using artificial intelligence in a situation where the use of drones is rapidly increasing and human errors are occurring. This system requires the implementation of an accurate control algorithm, assuming that last-mile delivery is delivered to the apartment veranda. To recognize the delivery location, a recognition system using the YOLO algorithm was implemented, and a delivery system was installed on the drone to measure the distance to the object and increase the delivery distance to ensure stable delivery even at long distances. As a result of the experiment, it was confirmed that the recognition system recognized the marker with a match rate of more than 60% at a distance of less than 10m while the drone hovered stably. In addition, the drone carrying a 500g package was able to withstand the torque applied as the rail lengthened, extending to 1.5m and then stably placing the package down on the veranda at the end of the rail.

• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.443-450
• /
• 2021

The study is devoted to the formation of a economic principles cargo delivery management in global supply chains. Mathematical model of delivering special categories of goods by road is a key element of these principles. The article analyzes the existing studies on solving the problem of cargo delivery in various aspects. It was noted that the greatest attention is paid to legal regulation, last mile delivery, optimization of routes and delivery schemes, information support, technological innovations, cluster routing, etc. In the developed mathematical model a minimum of total costs of forming loading units and freight shipments was defined as the criterion of optimality of organizing delivery by motor transport. The authors propose the creation of logistics clusters allowing the integration of urban transport flows and global supply chains.

• 항공우주시스템공학회지
• /
• 제14권6호
• /
• pp.1-9
• /
• 2020

Global e-commerce and delivery companies are actively pursuing last-mile delivery service using drones, and various delivery schedule planning studies have been conducted. In this study, separate individual route networks were constructed to reflect drone route constraints such as prohibited airspace and truck route constraints such as rivers, which previous studies did not incorporate. The A* algorithm was used to calculate the shortest path distance matrix between the starting point and destinations. In addition, we proposed an optimal delivery schedule plan using genetic algorithms and applied it to compare the efficiency with that of vehicle-only delivery.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권4호
• /
• pp.132-139
• /
• 2022

The development of the fourth industrial revolution and logistics 4.0 related technology, the growth of the e-commerce market, and the transition to a non-face to face society due to the pandemic are accelerating the growth of the logistics industry. Due to the growth of the logistics industry, various services are emerging to meet the requirements of the market, and research and technology development related to the parcel storage, which is an important element of the last mile service, is also underway. In the past, if it was difficult to deliver the goods directly to the recipient, the parcel storage installed near the delivery location was used, but the usability was not good and the storage of the goods was limited. In addition, the existing parcel storage has a lot of functional limitations compared to the advanced logistics technology, so it is necessary to develop a device that improves it. Therefore, this study conducted to secure safety for unmanned parcel storage devices with robot technology to improve usability and functionality in line with the advanced logistics industry. Based on ISO 10218, an industrial robot related standard, risk identification studies were conducted to derive results that contribute to the development of devices under development.

• ETRI Journal
• /
• 제45권2호
• /
• pp.329-337
• /
• 2023

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.220-229
• /
• 2023

The development of logistics technology due to the 4th Industrial Revolution and logistics 4.0 has changed the logistics environment from offline to online, and the growth of the online market has accelerated due to the recent increase in non-face-to-face delivery due to COVID-19. Such growth in the online market has expanded the logistics market for delivery, and contributes to creating an advanced logistics ecosystem as last mile services and logistics technologies begin to grow together. As traffic and environmental problems arise as a result, interest in transportation means of cargo increases, and changes to cargo electric vehicles and delivery cycles are being considered. However, since mass transportation of transportation focused on terminal delivery such as cargo electric vehicles and delivery cycles is limited in handling large quantities in urban areas, methods for efficiently transporting cargo while considering the environment are being devised. In order to solve such environmental problems and increase the efficiency of logistics delivery in urban areas, technologies using underground spaces based on existing urban railroads are being developed. In this study, a study was conducted on the establishment of evaluation criteria for selecting a test bed, which is a space for applying the system.

• 경영정보학연구
• /
• 제24권4호
• /
• pp.1-22
• /
• 2022

코로나19 이후 비대면 소비 사회로의 전환이 일어나며 생활밀착형 라스트마일 물류 서비스인 택배 기반의 세분화된 도시 물류의 중요성이 대두되고 있다. 본 연구는 소셜 네트워크 분석(SNA)을 활용하여 지역 및 상품 특성별로 수요의 관계성을 분석하고자 한다. 전자상거래에서 수요 파악에 활용되었던 장바구니 네트워크와 공동 구매 상품 네트워크를 확장한 분석 결과 택배 주문 건 수 데이터 속에서 상품 카테고리 패턴을 발견하고 지역별 차이를 확인하였다. 이를 바탕으로 본 연구에서 제시하는 SNA 기반 분석이 도시 물류의 재고 분산 배치나 상품(SKU) 선정 전략에 효과적으로 적용될 수 있음이 확인되었다.

• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.37-47
• /
• 2022

자율배송 운행 데이터는 코로나 시대의 라스트마일 배송에 대한 패러다임 변화를 주도하는 핵심이다. 국내 자율배송로봇과 해외 기술선도국가 간의 기술격차 해소를 위해서는 인공지능 학습에 사용 가능한 대규모 데이터 수집과 검증이 최우선으로 요구된다. 따라서 해외 기술선도국가에서는 인공지능 학습데이터를 누구든 사용가능한 공공데이터 형태로 오픈하여 검증과 기술발전에 기여하고 있다. 본 논문은 자율배송로봇 학습을 목적으로 326개의 객체를 수집하고 Mask r-cnn, Yolo v3 등의 인공지능 모델을 학습하고 검증하였다. 추가적으로 두 모델을 기반으로 비교하고 향후 자율배송로봇 연구에 요구되는 요소를 고찰하였다.

• Journal of information and communication convergence engineering
• /
• 제18권2호
• /
• pp.100-105
• /
• 2020

With the advent of the 5G era, the rapid growth in demand for mobile content services has increased the need for additional backhaul investment. To meet this demand, employing a content delivery network (CDN) and optical access solution near the last mile has become essential for the configuration of 5G networks. In this paper, a cache-enabled architecture using the passive optical network (PON) is presented to serve video on demand (VoD) for users. For efficient use of mobile backhaul, I propose a request deduplication scheme (RDS) that can provide all the requested services missed in cache with minimum bandwidth by eliminating duplicate requests for movies within tolerable range of the quality of service (QoS). The performance of the proposed architecture is compared with and without RDS in terms of the number of requests arriving at the origin server (OS), hit ratio, and improvement ratio according to user requests and cache sizes.

• 산업경영시스템학회지
• /
• 제45권4호
• /
• pp.134-141
• /
• 2022

Transportation in urban area has been getting hard to fulfill the demand on time. There are various uncertainties and obstacles related with road conditions, traffic congestions, and accidents to interrupt the on-time deliveries. With this situation, the last mile logistics has been a keen issue for researchers and practitioners to find the best strategy of the problem. A way to resolve the problem is to use parcel lockers. Parcel locker is a storage that customers can pick up their products. Transportation vehicles deliver the products to parcel lockers instead of all customer sites. Using the parcel lockers, the total delivery costs can be reduced. However, the inconvenience of customer has to increase. Thus, we have to optimal solution to balance between the total delivery costs and customers' inconvenience. This paper formulates a mathematical model to find the optimal solution for the vehicle routing problem and the location problem of parcel lockers. Experimental results provide the viability to find optimal strategy for the routing problem as well as the location problem.