Off-Road Autonomy Validation Using Scalable Digital Twin Simulations Within High-Performance Computing Clusters

Off-road autonomy validation presents unique challenges due to the unpredictable and dynamic nature of off-road environments. Traditional methods focusing on sequentially sweeping across the parameter space for variability analysis struggle to comprehensively assess the performance and safety of off-road autonomous systems within the imposed time constraints. This paper proposes leveraging scalable digital twin simulations within high-performance computing (HPC) clusters to address this challenge. By harnessing the computational power of HPC clusters, our approach aims to provide a scalable and efficient means to validate off-road autonomy algorithms, enabling rapid iteration and testing of autonomy algorithms under various conditions. We demonstrate the effectiveness of our framework through performance evaluations of the HPC cluster in terms of simulation parallelization and present the systematic variability analysis of a candidate off-road autonomy algorithm to identify potential vulnerabilities in the autonomy stack's perception, planning and control modules.

Using ROC and Unlabeled Data for Increasing Low-Shot Transfer Learning Classification Accuracy

One of the most important characteristics of human visual intelligence is the ability to identify unknown objects. The capability to distinguish between a substance which a human mind has no previous experience of and a familiar object, is innate to every human. In everyday life, within seconds of seeing an "unknown" object, we are able to categorize it as such without any substantial effort. Convolutional Neural Networks, regardless of how they are trained (i.e. in a conventional manner or through transfer learning) can recognize only the classes that they are trained for. When using them for classification, any candidate image will be placed in one of the available classes. We propose a low-shot classifier which can serve as the top layer to any existing CNN that the feature extractor was already trained. Using a limited amount of labeled data for the type of images which need to be specifically classified along with unlabeled data for all other images, a unique target matrix and a Receiver Operator Curve (ROC) criterion, we are able to increase identification accuracy by up to 30% for the images that do not belong to any specific classes, while retaining the ability to identify images that belong to the specific classes of interest.