Object detection for a robotic lawn mower with neural network trained on automatically collected data

• Main Author: Sparr, Henrik
• Format: Others
• Language: English
• Published: Uppsala universitet, Datorteknik 2021
• Subjects: Robotic lawn mower; Computer Vision; CNN; Machine Learning; Neural Network; Depthwise Separable Convolution; Hierarchical Group Convolution; Computer Vision and Robotics (Autonomous Systems); Datorseende och robotik (autonoma system)
• Online Access: http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-444627

Machine vision is hot research topic with findings being published at a high pace and more and more companies currently developing automated vehicles. Robotic lawn mowers are also increasing in popularity but most mowers still use relatively simple methods for cutting the lawn. No previous work has been published on machine learning networks that improved between cutting sessions by automatically collecting data and then used it for training. A data acquisition pipeline and neural network architecture that could help the mower in avoiding collision was therefor developed. Nine neural networks were tested of which a convolutional one reached the highest accuracy. The performance of the data acquisition routine and the networks show that it is possible to design a object detection model that improves between runs.