We present SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments.

The post SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments appeared first on SRI.

We describe and demonstrate a novel approach for generating accurate and interpretable uncertainty estimation for outputs from a DNN in real time.

The post Machine Learning Aided GPS-Denied Navigation Using Uncertainty Estimation through Deep Neural Networks appeared first on SRI.

We propose an auxiliary pseudo-label refinement network (PRN) for online refining of the pseudo labels and also localizing the pixels whose predicted labels are likely to be noisy.

The post Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement appeared first on SRI.

We propose C-SFDA, a curriculum learning aided self-training framework for SFDA that adapts efficiently and reliably to changes across domains based on selective pseudo-labeling. Specifically, we employ a curriculum learning scheme to promote learning from a restricted amount of pseudo labels selected based on their reliabilities.

The post C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation appeared first on SRI.

In this presentation, we describe and demonstrate a novel vision-enhanced low-light imager system to provide GPS-denied navigation and ML-based visual scene understanding capabilities for both day and night operations.

The post Night-Time GPS-Denied Navigation and Situational Understanding Using Vision-Enhanced Low-Light Imager appeared first on SRI.

In this work, we present a new vision-based cross-view geo-localization solution matching camera images to a 2D satellite/ overhead reference image database. We present solutions for both coarse search for cold start and fine alignment for continuous refinement.

The post Vision based Navigation using Cross-View Geo-registration for Outdoor Augmented Reality and Navigation Applications appeared first on SRI.

We address the problem of geo-pose estimation by cross-view matching of query ground images to a geo-referenced aerial satellite image database. Recently, neural network-based methods have shown state-of-the-art performance in cross-view matching.

The post Cross-View Visual Geo-Localization for Outdoor Augmented Reality appeared first on SRI.