Robotic sensing for buried pipes with sound waves

The length of buried sewer and drainage network in Europe is several million kilometres. Autonomous robots are being developed to inspect this massive network of pipes pervasively. These inspection technologies traditionally rely on CCTV images. However, detection of the condition of buried pipes with autonomous robots is challenging computationally. Acoustic waves provide an efficient alternative to conventional CCTV methods to detect a range of artefacts that can lead to pipe failure and map these conditions. This paper presents an acoustic method for simultaneous condition detection, localization, and classification in air-filled pipes. A microphone array is used to estimate the reflection coefficient from a range of artefacts. This information is used together with a regularization method. A wavelet basis function is adapted to enhance the fidelity of collected acoustic data. It is shown that the wavelet components can also be used to train and to test a support vector machine (SVM) classifier for the condition identification. This work can also inform the route planning and low-level control algorithms for autonomous robots which are being developed for the inspection of buried pipes.