RoboGrammar Creates Terrain-Optimized Robot Designs Automatically Using Graph Grammar Rules

Roboticists at the Massachusetts Institute of Technology (MIT) have developed a "graph grammar" framework designed to optimize the design of robots to particular terrain layouts by mixing and matching modular components: RoboGrammar.

"We present RoboGrammar, a fully automated approach for generating optimized robot structures to traverse given terrains," the team explains in the abstract to its paper. "In this framework, we represent each robot design as a graph, and use a graph grammar to express possible arrangements of physical robot assemblies. Each robot design can then be expressed as a sequence of grammar rules. Using only a small set of rules our grammar can describe hundreds of thousands of possible robot designs. The construction of the grammar limits the design space to designs that can be fabricated.'

"For a given input terrain, the design space is searched to find the top performing robots and their corresponding controllers. We introduce Graph Heuristic Search — a novel method for efficient search of combinatorial design spaces. In Graph Heuristic Search, we explore the design space while simultaneously learning a function that maps incomplete designs (e.g., nodes in the combinatorial search tree) to the best performance values that can be achieved by expanding these incomplete designs. Graph Heuristic Search prioritizes exploration of the most promising branches of the design space."

"This work is a crowning achievement in the a 25-year quest to automatically design the morphology and control of robots," claims Hod Lipson, a mechanical engineer and computer scientist at Columbia University, asked his unbiased opinion on the project by MIT News. "The idea of using shape-grammars has been around for a while, but nowhere has this idea been executed as beautifully as in this work. Once we can get machines to design, make and program robots automatically, all bets are off."

The key feature of the team's approach, when compared to rival automated robot design systems, is the designs it produces are not only optimized by producible — guaranteed to be physically fabricable, in fact, meaning that it's easy to take the output of the program and turn it into a functioning robot complete with control system. That's not to say the system couldn't have virtual use cases, though: "Let’s say in a video game you wanted to generate lots of kinds of robots, without an artist having to create each one," lead author Allan Zhao explains in an interview. "RoboGrammar would work for that almost immediately."

More details, and a link to the team's paper under open access terms, can be found on MIT News.