# Realistic Ultrasonic Environment Simulation Using Conditional Generative Adversarial Networks

## TL;DR

This paper introduces a novel conditional GAN-based method for realistic ultrasonic signal simulation, enabling flexible, accurate data augmentation for automotive sensors, surpassing traditional simulation techniques in efficiency and realism.

## Contribution

The paper presents the first realistic ultrasonic data augmentation method using conditional GANs, allowing flexible environment simulation conditioned on setup parameters.

## Key findings

- High realism and accuracy in simulated ultrasonic signals.
- Outperforms finite element method in efficiency and realism.
- Flexible simulation adaptable to environmental changes.

## Abstract

Recently, realistic data augmentation using neural networks especially generative neural networks (GAN) has achieved outstanding results. The communities main research focus is visual image processing. However, automotive cars and robots are equipped with a large suite of sensors to achieve a high redundancy. In addition to others, ultrasonic sensors are often used due to their low-costs and reliable near field distance measuring capabilities. Hence, Pattern recognition needs to be applied to ultrasonic signals as well. Machine Learning requires extensive data sets and those measurements are time-consuming, expensive and not flexible to hardware and environmental changes. On the other hand, there exists no method to simulate those signals deterministically. We present a novel approach for synthetic ultrasonic signal simulation using conditional GANs (cGANs). For the best of our knowledge, we present the first realistic data augmentation for automotive ultrasonics. The performance of cGANs allows us to bring the realistic environment simulation to a new level. By using setup and environmental parameters as condition, the proposed approach is flexible to external influences. Due to the low complexity and time effort for data generation, we outperform other simulation algorithms, such as finite element method. We verify the outstanding accuracy and realism of our method by applying a detailed statistical analysis and comparing the generated data to an extensive amount of measured signals.