Visual Perception for Decision Making

This research opportunity is focused on the development of visual perception models to extract the relevant visual information from a scene needed for an autonomous or human agent to understand their surrounding environment and make an appropriately informed decision. Decision-making may require understanding the surrounding environment using a combination of low, mid, or high-level visual concepts. Research opportunities exist at ARL to develop computer vision models focused on object recognition, instance segmentation, panoptic segmentation, scene graph generation, amodal perception, pose estimation, open-set recognition, zero-shot learning, high dynamic range processing for visual perception, and visual saliency modeling. This opportunity is part of the Army Research Laboratory Research Associateship Program (ARL-RAP), which is designed to significantly increase the involvement of creative and highly trained scientists and engineers from academia and industry in scientific and technical areas of interest and relevance to the Army. The program supports research in diverse fields including applied mathematics, atmospheric characterization, simulation and human modeling, digital/optical signal processing, nanotechnology, material science and technology, and computational and information sciences.