Water scarcity is one of the biggest problems that humanity is currently facing. Unfortunately, the issue is only expected to worsen in the next years due to climate change and overpopulation, especially in the urban areas. This makes the task of water preservation and reduction in water networks leakages even more crucial for the water utility companies making it mandatory for them to make some crucial adjustments. Thankfully, modern technology with the use of robotics and AI algorithms can help in reducing the size of the problem and significantly lower the associated costs. Therefore, the TERRAPIN project acts on the development of a novel robotic solution for trenchless water pipe inspection that aims to automate the inspection process and lower the associated costs.
The TERAPPIN project provides the integration of a rover with a Ground Penetrating Radar (GPR) for autonomous mapping of subsurface utilities and leakages. Synchronized GPR data collection is applied during robot motion and the output of the pipes and leakages detection is interpreted as semantic representation to be coupled with the metric map. The proposed Al algorithm, based on Convolutional Neural Networks (CNNs), of TERRAPIN project can detect the location of each pipe and, additionally, to reveal whether there is leakage or no with 99% accuracy. For the detection of possible defects/degradations the proposed GAN (Generative Adversarial Network ) model of TERRAPIN project is able to efficiently capture the content of the GPR images and model their degradations (i.e. the level of their corrosion) in the future time, accordingly. The comparison results among the proposed model and the GAN-based baselines reveal the superiority of proposed method. Thus, the Al algorithms of TERRAPIN project contribute to reveal the pipe leakage (based on CNN model) and the severity of the evolving defect of pipeline (based on GAN model).
The TERRAPIN project provides a user-friendly interface that allows interaction with the surface rover and offers comprehensive visual representation of the extracted semantic information during the inspection process. Particularly, the TERRAPIN UI SW suite is a web-based interface to the backend algorithms and functions of the integrated TERRAPIN system. It allows the control of the TERRAPIN rover, the acquisition of data and the subsequent analysis and presentation of the results.
Also, from the TERRAPIN project pricing policies and strategies were developed while considering consumer and market demand, and the partners of TERRAPIN promote the TERRAPIN solutions which are ready for application in the water sector market.
The TERRAPIN project was implemented by a Consortium of three EU-based SMEs, namely HYPERTECH, Pragma-IoT and OZZIE Robotics. The project has started in October 2021 and ending in October 2022.