Rough Terrain Robot with Computer Vision for Harsh Environment Mapping and Heavy Transportation

Hardware: reComputer J4012 with Jetson Orin NX 16GB module

Use Case Provider: CuboRex

Application: Rough Terrain Robot

Industry: Agriculture & Robotics Development

Deployment Location: Japan

As a pioneer in the field of rugged terrain, CuboRex launched the innovative tracked Robot for farm use, which is powered by NVIDIA Jetson Orin NX edge device to deal with the complex and difficult field working environment to reduce the labor of farmers based on the actual experience of working in the field. The robot kit also allows AI/CV engineers to start developing autonomous driving applications as soon as the robot arrives.


The hardships of the wasteland industry are predictable. There are about 4.37 million hectares of farmland and about 11,000 hectares of construction sites each year in Japan. In previous experience, we usually send human laborers to deal with complex unformed land conditions, such as fields, construction sites, disaster sites, etc. That’s quite an expensive cost, in the meanwhile, the working type and requirements are also diverse due to the weather and seasons changing.


CuboRex hoped to tackle the challenges of uneven terrain and heavy lifting concerns: human labor is expensive and time-consuming, and it’s not easy for them to carry heavy stuff while working on uneven paths and steps. At that point, a mobility unit could be very important to perform this kind of outdoor task. Furthermore, people want to advance the automation of robots based on AI/CV solutions but lack hardware technology. Especially when they got involved in the first beginning of ROS development, they required the necessary knowledge of know-how so it’s a time-wasting for them to learn all the stuff as a beginner. CuboRex launched the robot kit that allows AI/CV engineers to start developing autonomous driving applications as soon as the robot arrives.


The full potential of CuGo V3 crawlers is unleashed with the cutting-edge power of the Jetson Orin NX edge device. By seamlessly incorporating ROS/ROS 2, experience unmatched off-road capabilities and ruggedness. It’s getting easier to dive into the realm of autonomous driving applications backed by the strength of OpenCV, TensorFlow, PyTorch, or TAO Toolkit from NVIDIA with ROS/ROS 2 installed on Jetson’s Linux system. You can customize the NavigationStack, which is a sample autonomous driving application that comes with ROS/ROS 2, and craft outdoor robots tailored to your environment.

All necessary accessories and algorithms you need to get involved:

  • Enhance your robot by adding Jetson-powered AI/CV processing with object detection, semantic segmentation, and PoseEstimation models
  • along with a 2D LIDAR (RPLIDAR) for comprehensive environmental information
  • a GNSS (CLAS) for precise location data
  • an IMU for accurate acceleration measurement
  • top-notch sensors like Velodyne’s VLP-16 and Livox’s HAP for the Cubo development kit.
Workflow & equipment of the rough terrain robot

Now it’s ready to explore the future of robotics with CuGo V3 and Jetson Orin NX, bolstered by the versatility of ROS/ROS.

Business Impact/Result

CuboRex robot helps enhance productivity with the ability to work continuously and handle heavy loads can up to 70 kg, leading to increased output and potentially reducing labor costs. By utilizing robots in hazardous environments even with a 20° slope, you can also significantly reduce the risk to human life and avoid potential liabilities, which can contribute to long-term cost savings.

Meanwhile, when integrating AI/CV applications into robotic applications, it’s possible to skip all the knowledge related to hardware and rough terrain mobility, which leads to a significant reduction in development man-hours. Developers can also employ numerous sensors in autonomous driving algorithms with the abundant range of interfaces on reComputer J4012, which is indispensable not only for AI/CV applications but, while combined with autonomous driving applications, becomes crucial for quickly bringing outdoor mobility robots to life.

About CuboRex

CuboRex is a hardware company developing robots for the outdoor industry. They are developing robots that can work on rough terrain with large slopes and uneven ground, such as in agriculture and civil engineering construction sites. In rough terrain, it is difficult to mechanize the work, and much of the work is done by hand. By robotizing such work, they are approaching the challenges of these sites with technology.

Seeed NVIDIA Jetson Ecosystem

Seeed is an Elite partner for edge AI in the NVIDIA Partner Network. Explore more carrier boards, full system devices, customization services, use cases, and developer tools on Seeed’s NVIDIA Jetson ecosystem page.

Join the forefront of AI innovation with us! Harness the power of cutting-edge hardware and technology to revolutionize the deployment of machine learning in the real world across industries. Be a part of our mission to provide developers and enterprises with the best ML solutions available. Check out our successful case study catalog to discover more edge AI possibilities!

Take the first step and send us an email at [email protected] to become a part of this exciting journey! 

Download our latest Jetson Catalog to find one option that suits you well. If you can’t find the off-the-shelf Jetson hardware solution for your needs, please check out our customization services, and submit a new product inquiry to us at [email protected] for evaluation.

About Author


June 2023