Search Results

Research interests in autonomous driving have increased significantly in recent years. Several methods are being suggested for performance optimization of autonomous vehicles. However, weather conditions such as rain, snow, and fog may hinder the performance of autonomous algorithms. It is therefore of great importance to study how the performance/efficiency of the underlying scene understanding algorithms vary with such adverse scenarios. Semantic segmentation is one of the most widely used scene-understanding techniques applied to autonomous driving. In this work, we study the performance degradation of several semantic segmentation algorithms caused by rain for off-road driving scenes. Given the limited availability of datasets for real-world off-road driving scenarios that include rain, we utilize two types of synthetic datasets.

While convolutional neural networks (CNNs) have revolutionized ground-vehicle autonomy in the last decade, this class of algorithms requires large, truth-labeled data sets to be trained. The process of collecting and labeling training data is tedious, time-consuming, expensive, and error-prone. In order to automate this process, an automated method for training CNNs with simulated data was developed. This method utilizes physics-based simulation of sensors, along with automated truth labeling, to improve the speed and accuracy of training data acquisition for both camera and LIDAR sensors. This framework is enabled by the MSU Autonomous Vehicle Simulator (MAVS), a physics-based sensor simulator for ground vehicle robotics that includes high-fidelity simulations of LIDAR, cameras, and other sensors.