
Robotic automation for smart agriculture and renewable energy


Challenge
Most autonomous vehicles designed for smart agriculture and renewable energy navigate use global positioning system (GPS) data. However, GPS navigation is not effective in structured environments, such as orchards and solar farms, where the GPS signals are often occluded and noisy.
Solution
The LCR autonomously navigates using Intel RealSense Depth Camera D455, in conjunction with Raspberry Pi microcontrollers. The robot perceives its surroundings in real time, allowing it to operate with centimeter accuracy in both structured and unstructured environments.
Results
Intel RealSense technology provides more features and more value for a lower price than Directed Machines could obtain from competing depth cameras, allowing the company to reduce costs, increase performance, and bring more value to its customers.
A Better Way to Navigate
Land Care Robots autonomously navigate using the Intel RealSense depth cameras in conjunction with programmable Raspberry Pi 4 RP2040 microcontrollers. There is no need for April tags or QR codes or any other type of localization symbols. The robot perceives its surroundings in real time and navigates accordingly.

Advanced vision technology for precision tasks
The LCR samples the depth image at 15 frames per second. The data is channeled through several layers of heavy filtering to remove artifacts and transform it into data representations that can be efficiently manipulated by the CPU: semantic filtering, 2D filtering, and 1D filtering. Since Intel RealSense technology processes the depth data within the camera, it takes much of the load off the robot’s CPU.
The heart of the solution.

The heart of the solution.
Directed Machine’s sensor suite is anchored by two Intel RealSense Depth Camera D455s, which include an inertial measurement unit (IMU) for refined depth awareness. There are two data streams for each camera: RGB data and depth perception data. In addition to navigation, the Intel RealSense depth cameras equip the Land Care Robots with dynamic obstacle avoidance. A compact form factor makes it easy to unobtrusively mount the cameras on the LCR’s solar panel.
What's next?
Learn how RightHand Robotics is using Intel® RealSense™ computer vision technology to revolutionize automated warehouse order fulfillment.
Robotics overview
See how Intel® RealSense™ cameras can revolutionize the robotics industry with the latest in depth‑sensing technology.