On large construction sites, even a small deviation from the plan can cause big problems – money, and timewise. Hence, it is no surprise that modern technologies have been introduced actively to this field. Most of the activities are related to various types of mapping and modeling of the operation environment mainly to guide the operations and to monitor the results, but also to help autonomous machines or machines with assistive functionalities to perform their tasks. The research in this field is currently very active and we are participating in three related projects.
With our GIM-Mapper , we can create a precise 3D representation of the environment. Depending on the use case, the machine and especially the sensory setup, the accuracy of the map can be adjusted accordingly. In some high accuracy earth moving tasks, it is required to achieve maximum accuracy for acceptable performance. That kind of accuracy requires the best possible RTK-GNSS system, preferably with twin antennas, and top-of-the line LiDARs, IMUs and precise odometry information. With that kind of setup, we can produce 3D environmental modeling, mapping and even surface modeling. The progress of the construction can be followed in real-time, and the errors will be detected quickly.
GIM-Mapper needs our GIM-Locator to operate, because to map with a mobile machine, you obviously need to know how you have been moving and where you have been at any given time. And again, to make any machine capable of driving autonomously, you need to have a real-time situational awareness to provide the machine capability to understand what is going on around it, now and in near future. Our GIM-Observer will provide that for your machine and for the operator.
Although our brilliant trio (Locator, Mapper, Observer) will naturally absorb all the information, which is helping to fulfill the mission objectives, the situations where its value becomes extremely clear to everybody, are those cases when the GNSS signal will be denied for one reason or another. In those situations, without our feature-based localization capabilities or some other external infrastructure-based solution, expensive autonomous machines will be just big piles of metal.