Generating Ultrasonic Foliage Echoes with Variational Autoencoders

Navigation through dense foliage presents a fundamental challenge to autonomous systems, and achieving a performance level similar to echolocating bats could have important applications in areas such as forestry and farming. However, the clutter echoes originating from such environments have been difficult to analyze. To study the problem of sonar-based navigation in dense foliage in simulation, an artificial generation system for leaf impulse responses (IRs) based on variational auto-encoders is proposed. The system is to aid the construction of artificial foliage echo environments. A dataset of leaf echoes was collected in an anechoic chamber and convolved with the original signal to estimate the IR of each leaf. A modified version of the conditional variational autoencoder - generative adversarial network (cVAE-GAN) architecture was trained successfully on this dataset to produce a generative model that was conditional on leaf viewing angles, size, and species. The IRs generated by the model capture quantitative and qualitative similarity to the measured IRs. It surpasses the previous state of the art foliage echo model based on reflecting disks. The model's computational efficiency and its success suggest its potential use for simulating large environments of foliage to study bat biosonar and aid in engineering biomimetic sonar devices. In order to study bat biosonar and biomimetic engineering a generative deep learning based leaf impulse response generator is proposed. Trained on a dataset of single leaf echoes with an architecture based on conditional variational autoencoder - generative adversarial network (cVAE-GAN), a variety of realistic leaf impulse responses can be generated.image (c) 2024 WILEY-VCH GmbH