Archive 03.08.2025

Weed that grow among crops is a problem in many ways since humanity started agriculture. Weeds compete with crops for water, soil nutrients, sunlight. They can host pets, harbor diseases. They cost labor to remove them, either manually or chemically. This also increases overall costs and chemical removal may mean environmental impacts. Overall, weeds cause lower crop yield, decrease in quality, and higher costs. Considering all these, it is a very critical task, to remove them as efficiently as possible, which is where robots can be very useful and bring the costs down.

A robot that is developed in Spain, which is called “The GreenBot” aims to undertake such task. The robot is still in development stage but according to the press release provided by the team, it completed its successful field trials. The robot is developed by GMV (www.gmv.com), and a consortium made of University of Seville’s AGR-278 “Smart Biosystems Laboratory” research group, GMV, TEPRO, PIONEER HiBred Spain SL, and Cooperativas Agroalimentarias de Andalucía, where each participant undertook tasks belonging to different disciplines. The collaboration was initially scheduled to continue for 21 months, which concluded end of June, 2025.

The robot is basically a robotic vehicle and a robotic arm, equipped with AI, autonomous navigation and machine vision technologies, which are all essential to accurately identify and treat weeds such as the ones that grow near almond, citrus and olive trees.

During field tests, the robot effectively completed its tasks under different light, soil and plant combinations. Detection of smaller weeds under shade however, still remains a challenge, which the team plans to tackle by training the model with further data. The robot operates in real time, with an inference frequency of 1 second per image. This eliminated the need of using external servers, and enabled seamless integration between perception, navigation and application. The robot runs with the popular open source operating system ROS2 (Robot Operating System).

The robot basically works by approaching the tree, encircling the trunk by its robotic arm, and while further movement of the robot body (basically the vehicle) still continues, the half circular arm sprays precisely targeted chemicals on identified weeds. This not only automates weed treatment but also significantly reduces the use of chemicals, and hence, the environmental impact. The weed detection core, which was developed by the University of Seville, can identify position, species and dimensions of weeds within a tolerance of 2 cm.

The project was funded by grants for European Innovation Partnership (EIP) Operational Groups, within the framework of Rural Development Program of Andalusia, which operates under Spanish Ministry of Agriculture.

The project specific details in this post were obtained from a press release shared by Ariadne Comunicación (www.ariadne.es), who handles press communications for GMV (www.gmv.com), the maker of the robot.

Post By: A. Tuter

---

Terms of use:
Copying or republishing of our content is not allowed without written permission from us. We make dated records and keep originals of our posts and images. The content in this website may be incorrect or incomplete. User assumes all liability and risk as a result of using this website. Also see our Terms page.

Robots excel at many things, but having a good sense of touch is not among them. Whether dropping items or pinching them too tightly, which crushes the object, many robots struggle with these basic skills that humans have mastered.

Deep Think utilizes extended, parallel thinking and novel reinforcement learning techniques for significantly improved problem-solving.

Wheeled robots like ours are more efficient for the same reason cycling is more efficient than running, which includes less of a fight with gravity. The efficiency, as well as the sheer complexity of humanoid robots adds up to something that may be very much higher cost.

Wheeled robots like ours are more efficient for the same reason cycling is more efficient than running, which includes less of a fight with gravity. The efficiency, as well as the sheer complexity of humanoid robots adds up to something that may be very much higher cost.

A Los Angeles-area startup is using artificial intelligence and robotics in an unlikely way: making sashimi and other fish dishes taste better, last longer and be more humane.

Solo content creators often face the choice of either recording from a stationary camera or having to ask help from someone who needs to hold the camera. With this robotic tripod system called Roll Cam Robotic Cameraman, this problem seems to be solved to some extent. The system makes the tripod follow whatever needs to be recorded or live-streamed autonomously by using LIDAR and computer vision and can work on different tripods. In the video below it also mentions that the wheels were designed to absorb small vibrations for smooth recording. It comes with multiple recording modes as well. The kit comes with a maker SDK for C++ developers to customize its features further. The project is currently in the kickstarter phase.

Kickstarter Link:

https://www.kickstarter.com/projects/rollcam/roll-cam-camera-man/rewards

Video Link Here: https://www.youtube.com/watch?v=ybQoik3YIo8

Posted By: A. Tuter

Robotic Magazine’s general note for kickstarters: We occasionally publish about kickstarter projects on our site, but it does not mean that we test or endorse these projects. We publish at the request of project owners only, with whom we have no relationship, at no charge, to support development of robotics and to inform readers about new projects. You must do your own research before investing or purchasing anything. Also see our terms page.

——————————————————

Terms of use:

Copying or republishing of our content is not allowed without written permission from us. The content in this website may be incorrect or incomplete. User assumes all liability and risk as a result of using this website.

New AI model integrates petabytes of Earth observation data to generate a unified data representation that revolutionizes global mapping and monitoring

The robot, offered at a market-disruptive price of approximately $54,500, presents a cost-effective entry point into humanoid robotics for companies seeking automation solutions.

For the millions of Americans who live with a mobility issue, making a pizza can be a lot more challenging than just choosing between pepperoni or sausage. Now Virginia Tech researchers have developed a robotic arm with novel assistive grippers that can help those with disabilities accomplish complex everyday tasks, including building a pizza.

New research published in npj Robotics addresses the challenge of flying small quadrotors in air ducts as small as 35 cm (14 inches). This research, led by a team of researchers from Inria, CNRS, Université de Lorraine, and Aix-Marseille Université, opens a new way of accessing and inspecting highly-confined environments.

Many fulfillment and 3PL facilities struggle with the idea of automation, fearing downtime, technical headaches, and compatibility issues. But what if robotics could smoothly enhance your workflow instead of disrupting it?

Nanyang Technological University, Singapore (NTU Singapore) scientists have built the world's first automated cyborg insect "factory line." This new prototype robotic system automates the attachment of miniature electronic backpacks on the backs of Madagascar hissing cockroaches, turning them into insect-hybrid robots.

Future robots could soon have a lot more muscle power. Northwestern University engineers have developed a soft artificial muscle, paving the way for untethered animal- and human-scale robots. The new muscles, or actuators, provide the performance and mechanical properties required for building robotic musculoskeletal systems.

The integration of all-electric injection moulding machines and industrial robots offers a practical path, reducing energy consumption, cutting costs and boosting productivity.