People sit at home and their meals come from the sky. This is a future scenario rendered by countless logistic drone manufacturers. Since the establishment of intelligent logistics, Chinese companies such as SF Express, JD.com, and Ali are actively exploring the development and commercial application of logistics drones. At the end of July, Meituan UAV signed a contract with the Shenzhen Bay SIC Super Headquarters Center to complete the pilot operation mechanism of the UAV distribution business circle, including automated airport facilities that integrate the city’s low-altitude logistics network in the architectural design. As a carrier, it serves the needs of residents in the surrounding 3km business district. At that time, users only need to place an order on the Mei tuan APP, and they will be able to receive the items delivered from the SIC Super Headquarters in as little as 10 minutes.
“Technological change is an indispensable service in future urban life”, the person in charge of Meituan UAV stated that the pilot UAV distribution business circle jointly created by Meituan, Shenzhen Metro, and Vanke is to improve the efficiency of urban digital distribution. , To provide better services to surrounding users.
As early as 2015, the JD UAV team was established, aiming to create a “trunk, branch, and terminal three-level UAV + general aviation logistics system” to meet the goal of reducing costs and increasing efficiency in different application scenarios. Layout, and then gradually establish trunk and branch logistics, and finally build a smart logistics network integrating air and ground.
Liu Yanguang, Head of JD smart logistics, said at present, the demographic dividend is decreasing and labor costs are increasing. Starting from the countryside, technology is used to solve the high cost of rural logistics. It ensures that JD.com goes faster and better on the road of rural e-commerce.
In order to build the terminal branch line and better do the courier service work, JD.com currently has proposed to build 10,000 airports within 5 years and realize the distribution plan of 1 million UAVs.
“It is estimated that in 2023, drones will be rapidly applied to our industry.” Jin Bing, the inspector of Chinese Policy and Regulations Department of the State Post Bureau, revealed that there are currently 330 million deliveries in China every day, and it is expected that in 5 years, it may reach 1 billion items per day. A large number of transportation vehicles and various networking modes are in need. For remote mountainous and rural areas with inconvenient transportation, the cost is difficult to estimate if only human distribution is required. At this time, the lower-cost drone is the best way to distribute agricultural products to cities and industrial products to the countryside.
In fact, SF Express has already implemented this industrial operation model in parts of western Sichuan and northern Yunnan and has built a large logistics drone operation base in Yulin, Shanxi, to serve the aviation logistics operation network in Shanxi, Gansu, Ningxia, Qinghai, and other places.
Compared with JD and SF Express, Meituan’s drone logistics is more inclined to urban logistics distribution.
Meituan started its drone delivery project in 2017. As of June this year, it has completed 2,500 drone delivery orders. By July this year, the Shenzhen Bay SIC Super Headquarters Center completed the pilot demonstration cooperation agreement for the drone delivery business circle. Meituan is very optimistic about the prospects of drone delivery.
At the 2021 World Artificial Intelligence Conference at the beginning of the year, Meituan demonstrated the results of drone delivery research and development. The vice president of Meituan and the head of drone business Mao Yinian said that Meituan plans to achieve large-scale commercial use of drone distribution.
However, is the development of drone logistics really so smooth?
From an international perspective, it does not. Amazon is the earliest company to carry out drone logistics. It should be quite mature in terms of technology and operation. However, news of the “gradual collapse” of the drone delivery project has also been reported. In addition, the German DHL express company has also said that it has stopped. “parclecopter” small logistics drone express project.
So, can Meituan achieve large-scale commercial use of drone distribution within 5 years?
Yang Jiong, an engineer at the Institute of Unmanned Systems, Beijing University of Aeronautics and Astronautics, said: “The logistics of drones need to be considered from three aspects: aircraft, space management, and airports.”
The first is the airplane. The last mile of drone delivery needs to take into account the application of aircraft in dense crowds. This has high requirements for the reliability of the aircraft itself. For example, how many flights are trouble-free when the aircraft is delivered back and forth, and what is the mission completion rate? At present, no one can accurately determine these parameters. That is to say, the current aircraft is still in the test or far away from the research stage, and has not reached the stage of large-scale commercialization.
The second is space management. This involves comprehensive urban planning issues, including municipal administration, transportation, and public security.
“The environment in the city is complex, with various buildings and terrain obscured, and wire interference. If you want to commercialize drones in the city on a large scale, how can you monitor and track the aircraft’s trace and location in real-time? After an aircraft malfunctions, How managers determine the status of the aircraft and cooperate with the city’s municipal transportation and municipal police. If these solutions are not resolved, the large-scale commercialization of drones remains to be verified.” Yang Jiong analyzed.
As for the airport problem, it’s relatively simple. It just needs a large-scale management point to clarify the take-off and landing positions of the aircraft, and at the same time ensure the normal maintenance and storage of these aircraft.
In this way, the large-scale distribution of drone logistics still needs to be practiced step by step. However, from the perspective of the drone industry alone, people are still very optimistic about its prospects. After all, drone logistics has reached the stage of “ready to go”. Many industry players are advancing together to achieve the scale of drone logistics. It is only a matter of time for large-scale development of drone distribution.
Just as a triangle needs three sides to stabilize its shape, artificial intelligence will also need all three elements to perfect itself: algorithm, no bias data sample, and the training process.
It is well known that the performance of an AI model depends more on the data than the code. Getting high-quality labeled data is the toughest part of building a machine learning model. If the training data has a bias, the algorithm model cannot be well developed, AI company needs to label the data again. Timing is important, once the company is behind the schedule, the product may be overtaken by competitors.
Common Labeling Types in Express Delivery
Common Labeling Types in Express Delivery
- Object Recognition
- Object Tracking in Video
- Industrial Robot Navigation
- Robot Arm Guidance Crack Detection
① Robotic sorting and material handling, like Package Delivery, Warehouse Inventory Handling
ByteBridge is a data labeling SAAS platform with robust tools and real-time workflow management. It provides high-quality training data for the machine learning industry.
- ML-assisted capacity can help reduce human errors by automatically pre-labeling
- The real-time QA and QC are integrated into the labeling workflow as the consensus mechanism is introduced to ensure accuracy.
- Consensus — Assign the same task to several workers, and the correct answer is the one that comes back from the majority output.
- All results are thoroughly assessed and verified by a human workforce and machine
In this way, ByteBridge can affirm the data acceptance and accuracy rate is over 98%.
Flexibility — Configure Your 2D Images Labeling Project
On ByteBridge’s dashboard, developers can define and start the data labeling projects and get the results back instantly. Clients can set labeling rules directly on the dashboard. In addition, clients can iterate data features, attributes, and workflow, scale up or down, make changes based on what they are learning about the model’s performance in each step of test and validation.
As a fully managed platform, it enables developers to manage and monitor the overall data labeling process and provides API for data transfer. The platform also allows users to get involved in the QC process.
These labeling tools are available: Image Classification, 2D Boxing, Polygon, Cuboid.
We can provide personalized annotation tools and services according to customer requirements.
A collaboration of the human-work force and AI algorithms ensure a 50% lower price compared to the conventional market.
Please feel free to contact us: [email protected]