Robots Building Together: Learning to Collaborate

Thesis Prize
SMArchS Computation
Advisors: Skylar Tibbits and Patrick Winston
Reader: Terry Knight

Since robots were first invented, robotic assembly has been an important area of research in both academic institutions and industry settings. The standard approach in robotic assembly lines utilizes fixed industrial-sized robotic arms and prioritizes speed and precision over customization and flexibility. With a recent shift towards mobile multi-robot teams, researchers have developed a variety of approaches ranging from planning to swarm robotics. However, existing approaches are either too rigid with a deterministic planning approach or do not take advantage of the opportunities available with multiple robots. Rather, if we are to push the boundaries of robotic assembly, then we need to make collaborative robots that can work together, without human intervention, to plan and build large structures that they could not complete alone.

By taking a collaborative approach to robotic assembly, I define a strategy wherein the result will consistently be much greater than sum of its parts. In this thesis, I take a first step towards this vision by developing collaborative agents that learn how to work together to move blocks. This aspect of collaboration is the key difference from current methods in robotic assembly. In the context of this research, I define collaboration as an emergent process that evolves as multiple agents learn to work together to achieve a common goal. Rather than taking an explicit planning approach, I employ an area of research in artificial intelligence called reinforcement learning. Drawn from behavioral psychology, reinforcement learning is a subset of machine learning where agents learn an optimal behavior to achieve a specific goal by receiving rewards or penalties for good and bad behavior, respectively. By developing teams of robots that can collaboratively work together to plan and build large structures, we could aid in disaster relief, enable construction in remote locations, and support the health of construction workers in hazardous environments.