Construction

We developed a specialized construction algorithm and robotic system that can autonomously build motion support structures with previously unseen stones. A physics-based planner explicitly considers the uncertainty produced by incomplete in-situ sensing and imprecision during pickup and placement.

We present a construction model that allows robots with different construction capabilities, using materials of different physical properties and sizes, to modify unstructured environments in a distributed system.

We present and validate a property-driven autonomous system that modifies its environment to achieve and maintain navigability over a highly irregular 3-dimensional terrain. We demonstrate the approach by running the system on a variety of terrains and with mixed materials, including both deformable and rigid components.

We propose a ”next best step” planning method that autonomously chooses assembly actions to allow construction with objects that contain a significant amount of variation.