Research and Development in Agricultural Robotics
Farming is often thought as an ancient practice with conventional means, a practice in stark contrast with modernized urban practices and technologies like robotics, smart solutions, deep learning, uses of UAV’s and optimization of processes. Although plausible to some extent for some parts of the world, that is a large misconception.
Farming is being modernized at an accelerated pace and digital farming and smart farming are slowly becoming norms of farming practices in the developed world. Digital farming is the practice of modern technologies such as sensors, robotics, and data analysis for shifting from tedious operations to continuously automated processes.
A new research paper reviews some of the latest achievements in agricultural robotics, specifically those that are used for autonomous weed control, field scouting, and harvesting.”
The paper, titled “Research and development in agricultural robotics: a perspective of digital farming“, and authored by Redmond Ramin Shamshiri, Cornelia Weltzien, Ibrahim A. Hameed, Ian J. Yule, Tony E. Grift, Siva K. Balasundram, Lenka Pitonakov, Desa Ahmad, Girish Chowdhary, is published in the International J Agric & Biological Engineering Journal.
Robots, as obvious, are a useful replacement of labor work as they have fast and powerful processors, extreme resilience to periodic fatigue and obey commands without aberration (which could be a downside if the robots are not commanded with well enough expertise).
There have been several novel applications of robots in the agricultural sector:
- Automated harvesting with innovative grippers controlled by custom mobile platforms
- Autonomous targeted spraying in greenhouses with precision monitors
- De-leafing of cucumber plants at an optimized rate
- Simultaneous localization for trimming of plants
- Utilization of UAV’s for monitoring crops and spraying pesticides and medicine
These are just a few of the applications and successfully implemented or prototyped studies all of which are based on some very basic research fields in deep learning and robotics; object detection and image tracking, color and depth perception, texture analysis (sense of touch) and controlling components in 3d space.
A customized software platform called ForboMind was introduced to support field robots for precision agriculture task with the objective to promote reusability of robotic components. ForboMind is open-source, and support projects of varying size and complexity, facilitate collaboration for modularity, extensibility, and scalability. In order to experiment with vision sensors and agricultural robots, created a completely simulated environment in software’s like V-REP (Coppelia Robotics), ROS, and MATLAB (Mathworks, Natick, MA, USA) for improvement of plant/fruit scanning and visual scanning task through an easy testing and debugging of control algorithms with zero damage risk to the real robot and to the actual equipment.
Improvements in image tracking and image recognition systems have enabled several applications of robotic manipulators in effectively reducing labor fatigue and improving efficiency of agricultural practices.
Agricultural field robots contribute to increasing the reliability of operations, improved soil health, and improved crop yield. They are generally equipped with different sensors and cameras for navigation control, mapping, and path planning algorithms.
An example of one such robot is SWEEPER.
It is an assembly of an autonomous mobile platform with Fanuc LRMate 200iD robot holding an end-effector and catching device for fruit harvesting. The ultimate goal of the Sweeper is to put the first working sweet pepper harvesting robot on the market. Using the camera system mounted on the end-effector, the SWEEPER scans plants looking slightly upwards for detecting mature plants. The camera and sensors setup is completely independent of the surrounding light conditions and provide information about color images and distance maps that are used for fruit detection, localization, and maturity classification.
There are different robots used just for scouting the fields and monitoring crops:
- Trimbot2020: An outdoor robot based on a commercial Bosch Indigo lawn mower platform and Kinova robotic arm for automatic bush trimming and rose pruning.
- Wall-Ye: A prototype vineyard robot for mapping, pruning, and possibly harvesting the grapes
- Ladybird: An autonomous multipurpose farm robot for surveillance, mapping, classification and detection for different vegetables
- MARS: The mobile agricultural robot swarms are small and streamlined mobile robot units that have minimum soil compaction and energy consumption and aim at optimizing plant specific precision agriculture.
There are robots being developed for water spraying, harvesting, spraying etc as well and there is still a lot of room for development in the field. So it’s only a matter of time before robots take over the agriculture industry.
Reference: https://www.researchgate.net/publication/326929441_Research_and_development_in_agricultural_robotics_A_perspective_of_digital_farming | Research and development in agricultural robotics: A perspective of digital farming |Redmond Ramin Shamshiri, Cornelia Weltzien, Ibrahim A. Hameed, Ian J. Yule, Tony E. Grift, Siva K. Balasundram, Lenka Pitonakova, Desa Ahmad, Girish Chowdhary