Vision-Guided Robotic Automation and Digital Twin Framework for Autonomous Experiments

The Brookhaven National Laboratory (BNL) is seeking a vendor to develop a vision-guided automation platform integrated with a digital twin and robotic simulation framework for autonomous experiments. The project aims to create a foundational subsystem for an autonomous beamline framework, enabling perception-driven decision-making, predictive safety assessment, and validated robotic workflows for spectroscopy experiments. The scope of work includes deploying stereo camera systems, developing 3D perception pipelines, and creating a digital twin representing robotic kinematics and workspace geometry. The project is expected to last 12 months, with a base year and optional years. The student will work 20 hours per week with BNL and a weekly project meeting is expected. Some key points of this opportunity include: • Deploying stereo camera systems in laboratory and beamline environments • Developing 3D perception pipelines for reconstructing workspace geometry and detecting experimental components • Creating a digital twin representing robotic kinematics and workspace geometry • Developing a robotic simulation environment mirroring the laboratory and beamline setups • Implementing pre-execution evaluation of robotic trajectories, including reachability analysis, collision prediction, clearance margin estimation, and joint limit and singularity detection