Bayesian Data Augmentation and Training for Perception DNN in Autonomous Aerial Vehicles

TL;DR

This paper introduces a Bayesian data augmentation framework using photorealistic simulation and high-fidelity dynamics to improve perception DNNs for autonomous aerial vehicles, especially for safe landing in diverse conditions.

Contribution

It presents a novel data augmentation method combined with Bayesian optimization to enhance perception models for aerial vehicle landing tasks.

Findings

Landing success rate improved by at least 20% across various conditions.

Identified high-performing data augmentation parameters through Bayesian optimization.

Framework enables robust perception model development for autonomous air taxis.

Abstract

Learning-based solutions have enabled incredible capabilities for autonomous systems. Autonomous vehicles, both aerial and ground, rely on DNN for various integral tasks, including perception. The efficacy of supervised learning solutions hinges on the quality of the training data. Discrepancies between training data and operating conditions result in faults that can lead to catastrophic incidents. However, collecting vast amounts of context-sensitive data, with broad coverage of possible operating environments, is prohibitively difficult. Synthetic data generation techniques for DNN allow for the easy exploration of diverse scenarios. However, synthetic data generation solutions for aerial vehicles are still lacking. This work presents a data augmentation framework for aerial vehicle's perception training, leveraging photorealistic simulation integrated with high-fidelity vehicle dynamics. Safe landing is a crucial challenge in the development of autonomous air taxis, therefore, landing maneuver is chosen as the focus of this work. With repeated simulations of landing in varying scenarios we assess the landing performance of the VTOL type UAV and gather valuable data. The landing performance is used as the objective function to optimize the DNN through retraining. Given the high computational cost of DNN retraining, we incorporated Bayesian Optimization in our framework that systematically explores the data augmentation parameter space to retrain the best-performing models. The framework allowed us to identify high-performing data augmentation parameters that are consistently effective across different landing scenarios. Utilizing the capabilities of this data augmentation framework, we obtained a robust perception model. The model consistently improved the perception-based landing success rate by at least 20% under different lighting and weather conditions.