Some aspects of road sweeping vehicle automation

Road sweeping vehicles that are commonly seen on the roads today, have been empirically developed over the years. As a result the operation of such machines has not undergone systems engineering development with respect to automating the sweeping performance so as to reduce the workload of the driver. This paper reports on work being undertaken to enhance the performance and safety of road sweeping vehicles. A forward looking debris detection system is being developed alongside research into brushes and the brushing process. This work is necessary to fully understand and automate the sweeping process. Vision processing techniques have been used to identify various road surfaces and debris. A two step approach is adopted to reduce the load on the processor, but still extract all the necessary information. Continuous flow of data is provided by laser striping, building up a 3D profile of the road ahead. Only when the scene cannot be fully identified with sizes and shapes alone, other, more advanced, image processing techniques are applied. Based on the data provided by laser striping, choices can be made on what specific techniques need to be used, and when, providing a flexible computer vision system without the need for fast processors. To gain an understanding of the brush characteristics a brush rig was constructed to test different brush types used on road sweeping vehicles. An extensive range of practical tests were undertaken on a variety of contact surfaces. Analysis of the results shows that the common brush types currently on the market have very different characteristics depending on the orientation of their tines.