This $596,285 Project Grant awarded by the National Science Foundation (NSF) under the Engineering program (CFDA 47.041) to Arizona State University's Division, doing business as Orspa, aims to develop an end-to-end framework for automating manufacturing tasks in extreme environments. The key products and services to be delivered under this 3-year grant include:
- Interpreting manufacturing data (e.g., text, drawings, 3D layouts) using vision-language models to generate high-level task sequences. 2) Automated sub-goal planning and task assignment for single or multi-robot manufacturing scenarios through a language-integrated task planner. 3) Validating and correcting manufacturing plans using a digital twin system with sensor feedback and trajectory evaluation.
This project seeks to address the challenge of transitioning from engineering requirements to robotic control by integrating computer vision, natural language processing, and task planning capabilities. The goal is to enable more scalable, generalized data-driven automation, especially in extreme environments like outer space, underwater, and radioactive settings.
Generated 1/28/25, 7:59 AM