This paper presents a method for the real-time detection of pipeline leaks using flexible Acoustic Emission (AE) sensors. The signals gathered from the AE sensor are transformed into RGB images through the application of Mel-spectrogram and color coding. These converted images serve as input for a Convolutional Neural Network (CNN) based on ResNet18. With this approach, both the presence and intensity of leaks in a pipeline can be identified using the AE sensor. The effectiveness of the proposed method was validated through data collected from a testbed featuring a galvanized pipe.

This paper proposes an observation model for a particle filter-based localization using a sonar grid map. The proposed model estimates a predicted observation by considering the properties of a sonar sensor which has a large angular uncertainty. The proposed model searches a grid which has the highest probability to reflect a sonar beam using the following procedures; (1) the reliable area of a single sonar data is determined using the footprint association model; (2) the detection probability of each grid cell in a sonar beam coverage in estimated. The proposed model was applied to the particle filter based localization, and was verified by experiments in indoor environments.