Intelligent Grass Cutting Robot with Computer Vision

Author

Dr. G. Sasidhar, B. Niteesh Kumar, M. Vinod, K. Sanjay Kumar

Abstract

 Grass cutting is an essential maintenance task in gardens, parks, and lawns, but most existing grass-cutting machines operate continuously without distinguishing between grass and other green plants, which can lead to damage to flowers, shrubs, and ornamental vegetation. To overcome this limitation, this project proposes a Computer Vision-Based Autonomous Grass Cutting Robot that integrates computer vision with autonomous navigation to perform intelligent and selective grass cutting. The robot uses a camera to capture real-time images of its surroundings, and a trained deep learning model analyzes these images to identify grass while differentiating it from other green objects such as plants, flowers, shrubs, and obstacles. Based on the detection results, the system automatically activates the cutting blade only when grass is identified and keeps it turned off in all other situations, ensuring safe and precise operation. The robot is also capable of moving autonomously and avoiding obstacles, reducing the need for continuous human supervision. By combining artificial intelligence with an existing robotic platform, the proposed system aims to improve cutting accuracy, enhance safety, minimize damage to surrounding vegetation, and provide an efficient, eco-friendly, and intelligent solution for lawn maintenance in residential, commercial, and public green spaces.

Keywords

Autonomous grass cutter, Computer vision, Deep learning, Real-time object detection, Selective mowing, Autonomous navigation, Obstacle avoidance, Agricultural robotics.

Full Text:

Download Paper PDF

References

[1] Hameem, M., Mir, F. A., & Malik, M. (2020). Autonomous Grass Cutting Rover (Bachelor's project report). Department of Mechanical Engineering, Islamic University of Science & Technology, Awantipora, Jammu & Kashmir, India.

[2] Sakravarthy N, V., Guruprakash, A., Jeswin, J., & Logeshwaran, M. (2023). AI based grass cutting rover using image processing to move the obstacle. In S. Venkatesh et al. (Eds.), Emerging Trends in Mechanical Sciences for Sustainable Technologies (Advances in Intelligent Systems and Technologies, pp. 35–41).

[3] Bhanu Sri, Ch., Khaja Mohiddin, Sk., Naresh Kumar, S., Mohan Kalyan, V., Veer Raju, A., Nagendra Prasad, K., & Sai Mohan, U. (2023). IOT based solar grass cutting robot. International Journal for Multidisciplinary Research (IJFMR), 5(2), 1–9.

[4] Schepelmann, A. (2010). Identification & segmentation of lawn grass based on color & visual texture classifiers (Master's thesis). Department of Mechanical Engineering, Case Western Reserve University, Cleveland, OH.

[5] Zeng, Q., Ehmann, K. F., & Cao, J. (2020). Design of general kinematotropic mechanisms. Mechanism and Machine Theory, 154, Article 104033. https://doi.org/10.1016/j.mechmachtheory.2020.104033 

[6]  Einecke, N., Franzius, M., Dunn, M., & Dirnberger, R. (2017). Embedded robust visual obstacle detection on autonomous lawn mowers. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 361–369). IEEE. https://doi.org/10.1109/cvprw.2017.50 Cited by: 35

[7] Guo, Y., & Sun, F.-C. (2016). Vision-based lawn boundary recognition for mowing robot. In Proceedings of the 2016 International Conference on Computer Engineering and Information Systems (CEIS-16) (Advances in Computer Science Research, Vol. 52, pp. 79–83). Atlantis Press. https://doi.org/10.2991/ceis-16.2016.19 

[8] Matsuzaki, S., Masuzawa, H., & Miura, J. (2022). Image-based scene recognition for robot navigation considering traversable plants and its manual annotation-free training. IEEE Access, 10, 5115–5128. https://doi.org/10.1109/ACCESS.2022.3141594

[9] Safaldin, M., Zaghden, N., & Mejdoub, M. (2024). An improved YOLOv8 to detect moving objects. IEEE Access, 12, 59782–59806. https://doi.org/10.1109/ACCESS.2024.3393835 

[10] Nimma, D., Al-Omari, O., Pradhan, R., Ulmas, Z., Krishna, R. V. V., El-Ebiary, Y. A. B., & Rao, V. S. (2025). Object detection in real-time video surveillance using attention based transformer-YOLOv8 model. Alexandria Engineering Journal, 118, 482–495. https://doi.org/10.1016/j.aej.2025.01.032

Share your valuable work from Social Media Buttons