您的位置: 首页 > 院士专题 > 专题列表


[前沿资讯] Septentrio launches new GNSS/INS receiver for drones 进入全文

Future Farming

The AsteRx-i D UAS multi-frequency receiver combines reliable centimeter-level positioning with 3D orientation. Provider of high-precision GNSS positioning solutions Septentrio has announced its new AsteRx-i D UAS GNSS/INS receiver. This multi-frequency receiver combines reliable centimeter-level positioning with 3D orientation, enabling automated navigation of aerial drones and robots. Compact and lightweight With a high-performance IMU (Inertial Measurement Unit) from Analog Devices integrated directly into the board, AsteRx-i D UAS is compact and lightweight. Aboard the drone, its small form-factor combined with low power consumption results in extended battery life and longer flight times, says Septentrio. “With this product we introduce into our inertial-GNSS portfolio an IMU which allows us to reduce the weight and power consumption of our UAS boards while making them easier to integrate. These are all key elements for a successful UAV platform,” says the company. Single and dual antenna AsteRx-i D UAS is the first commercial product resulting from Septentrio’s collaboration with Analog Devices. Both single antenna and dual antenna versions are available. The single antenna version provides a lightweight solution optimising the system SWaP (size, weight and power). The dual antenna version is ideal for machines that need reliable heading directly from the start. Advanced Interference Mitigation (AIM+) technology AsteRx-i D UAS comes with Advanced Interference Mitigation (AIM+) technology. According to Septentrio, in aerial drones, where many electronics are crammed into a small space, neighboring devices can emit electromagnetic radiation, interfering with GNSS signals. AIM+ offers protection against such interference resulting in faster set-up times and robust continuous operation. The company says the on-board IMU from Analog Devices is exceptionally robust against mechanical vibrations. This IMU combined with Septentrio’s anti-shock LOCK+ technology is to make AsteRx-i D UAS resilient against impact during takeoff and landing.

[前沿资讯] California dreamin’: a French weeding robot in America 进入全文

Future Farming

Naïo Technologies is currently running its Dino autonomous vegetable weeding robot in California. Naïo’s local representative Simon Belin shares his experiences with Dino in the USA. The Dino autonomous vegetable weeding robot by French company Naïo Technologies has actually been on American soil for over a year now. Currently, Dino is being deployed on farms in the Salinas Valley, San Juan Batista and Hollister, all in California. Identify Dino’s limitations In 2019 Dino made its debut in the USA. “The first season in Salinas introduced local farmers to Dino – our bed straddling robot used for weeding salad crops. Thanks to our partners’ trust (such as Top Flavor Farm, Bonipak and Church Brothers Farms), we were able to weed many acres on their farms and gather precious feedback. We were thus able to identify Dino’s few limitations, and correct them immediately,” says Simon Belin, Naïo’s local representative, who is responsible for operating the robots on the various farms. “Several of my French colleagues regularly travelled to California and Arizona to conduct other tests and adapt our robot according to the needs expressed by American farms. Indeed, there are notable differences between European and American practices – which led us to modify certain aspects of the machine,” said Simon Belin. Improve camera guidance “We started by adjusting Dino’s guiding system over the crop beds. Its itinerary is now perfectly straight and accurate, in compliance with the map it is instructed to follow. A second team came to improve the tool’s camera guidance – which was another significant advancement for Dino. The third and final team went to Yuma in Arizona, to implement the active tool developed at the end of last year.” Fully autonomous robots “Other aspects were also adjusted, making the mechanics more reliable, ensuring more compact batteries, making it possible to use new weeding tools, and lastly providing operators with a reliable and secure remote control. All these improvements mean we now have fully autonomous robots, and we can consider operating several machines at the same time within the same plot of land.” Last season, Dino operated across dozens of hectares of farmland in the United States. This year, Naïo Technologies has scheduled hundreds more thanks to the arrival of other Dino machines throughout the USA. 7 acres per day for one machine In the past three weeks the Dino weeding robots have covered 100 acres, approximately 7 acres per day for one machine. The Dino robots are being deployed in cabbage (4 rows), romaine lettuce (5, 6 and 8 rows), leek (4 rows) and baby lettuce (10 rows). What does a day’s work with Dino look like? “Well, first I need to know what the farmer wants Dino to do, so I can equip the robot with the appropriate tools for the job,” says Simon. “Next I create a GPS map of the plot, using a manual GPS tag. The map is processed using a computer, and then the file can be uploaded to the Dino robot. The map tells the robot the number of rows and what the plot looks like.” U-turns The Dino robot then sets off to work in the plots, says Simon. “The entire process of mechanical weeding is being done fully autonomous. With the help of the map and the camera system on the tool carrier Dino finds its way and is able to make U-turns. I just watch the robot work from a distance, and make sure the area is secure, so I keep an eye out for look for moving objects like vehicles, or people walking around the plots.” The robot runs for between 6 and 9 hours, depending on soil conditions and the number of weeding knives that ure used. Approximately 1 acre per hour can be done. Once the robot has completed its task, or when the battery is low, it sends a text message to the operator. “Then it is time to take Dino back to the farm for recharging, which takes around 6 hours before it’s ready for another day of weeding.” According to Simon, the whole process is fairly simple from an operator’s point of view. “Once the map is created and the right tools are implemented, all I have to do is watch the robot work from my car.” Waas – Weeding As A Service At the moment, Naïo Technologies is running the robots for the farmers in California, as part of its Waas programme (Waas stands for weeding as a service, see the box below for more information). “We want to show them what Dino can do, and how it works. The farmers we‘re working with are quite impressed. I get comments like: “We‘re not able to a job that good with our cultivator”. Or: “We‘ve never been able to cultivate our leek like that before”. Right now, we have enough work to run two robots for six days a week, so the growers we‘re working with really like it.”

[学术文献] A hybrid modelling approach to understanding adoption of precision agriculture technologies in Chinese cropping systems 进入全文


Precision agriculture has the potential to deliver improved and more sustainable food production. Despite the various Chinese policy initiatives to strengthen national food security, there is evidence that the adoption of precision agriculture technologies in China has been much lower when compared to other developed agricultural economies. This study therefore aims to explore factors that determine Chinese farmers' adoption of precision agriculture technologies in cropping systems and to provide recommendations on technology promotion in the future. The current status of precision agriculture adoption by smallholder farmers within crop farming systems in the North China Plain was explored. An integrated model of "Adapted Unified Theory of Acceptance and Usage of Technology (AUT(2))" was developed to explain individual farmers' intention to adopt precision agriculture. 456 surveys were conducted via face to face interviews in the North China Plain and structural equation modelling analysis was used to estimate the proposed AUT(2) model. The results showed that perceived need for technology characteristics (PNTC), perceived benefits, perception of the efficacy of facilitating conditions and perceived risks of adoption have significant impacts on farmers' intention to adopt precision agriculture. The facilitating conditions (e.g. knowledge, resources and access to consultant services) were the best predictor improving Chinese farmers' willingness to adopt these technologies. Policy makers and service providers need to consider these factors in the promotion of technologies.

[科技报告] WIPO Technology Trends 2019 – Artificial Intelligence 进入全文



[学术文献] A field-tested robotic harvesting system for iceberg lettuce 进入全文


Agriculture provides an unique opportunity for the development of robotic systems; robots must be developed which can operate in harsh conditions and in highly uncertain and unknown environments. One particular challenge is performing manipulation for autonomous robotic harvesting. This paper describes recent and current work to automate the harvesting of iceberg lettuce. Unlike many other produce, iceberg is challenging to harvest as the crop is easily damaged by handling and is very hard to detect visually. A platform called Vegebot has been developed to enable the iterative development and field testing of the solution, which comprises of a vision system, custom end effector and software. To address the harvesting challenges posed by iceberg lettuce a bespoke vision and learning system has been developed which uses two integrated convolutional neural networks to achieve classification and localization. A custom end effector has been developed to allow damage free harvesting. To allow this end effector to achieve repeatable and consistent harvesting, a control method using force feedback allows detection of the ground. The system has been tested in the field, with experimental evidence gained which demonstrates the success of the vision system to localize and classify the lettuce, and the full integrated system to harvest lettuce. This study demonstrates how existing state-of-the art vision approaches can be applied to agricultural robotics, and mechanical systems can be developed which leverage the environmental constraints imposed in such environments.

[学术文献] A low-cost and efficient autonomous row-following robot for food production in polytunnels 进入全文


In this paper, we present an automatic motion planner for agricultural robots that allows us to set up a robot to follow rows without having to explicitly enter waypoints. In most cases, when robots are used to cover large agricultural areas, they will need waypoints as inputs, either as premeasured coordinates in an outdoor environment, or as positions in a map in an indoor environment. This can be a tedious process as several hundreds or even thousands of waypoints will be needed for large farms. In particular, we find that in unstructured environments such as the ones found on farms, the need for waypoints increases. In this paper, we present an approach that enables robots to safely traverse not only between straight rows but also through curved rows without the need for any predetermined waypoints. Most types of infrastructure found in agriculture, such as polytunnels, are built on uneven terrain, thus containing a mix of straight and curved plant rows, for which traditional methods of row following will fail. Different from traditional approaches of row following that only consider straight-line-of-sight rows, our approach identifies the rows on each side with the goal of staying in the middle of the rows, even if the rows are not straight. Waypoints are only needed on the very extreme of the rows, and these will be automatically generated by the system. With our approach, the robot can just be placed in the corner of the field and will then determine the trajectory without further input from the user. We thus obtain an approach that can reduce the installation time from potentially hours to just a matter of minutes. The final autonomous system is low cost and efficient for various tasks that requires moving between plant rows inside a polytunnel. Several experiments were performed and the robot demonstrates 1.4% position drift over 21 m of navigation path.


意 见 箱