Stackelberg Strategic Guidance for Heterogeneous Robots Collaboration

Abstract-- In this study, we explore the application of game theory, in particular Stackelberg games, to address the issue of effective coordination strategy generation for heterogeneous robots with one-way communication. To that end, focusing on the task of multi-object rearrangement, we develop a theoretical and algorithmic framework that provides strategic guidance for a pair of robot arms, a leader and a follower where the leader has a model of the follower's decision-making process, through the computation of a feedback Stackelberg equilibrium. With robotic technology research and development rapidly have knowledge of the follower's decision-making model, accelerating, one can expect an explosion in the number whereas the follower only makes decisions based on the and type of robots to be deployed in the coming years. SGCM is shown to deliver more efficient With this trend, there is an increasing need to have robots solutions as compared with a greedy baseline and avoids with different capabilities effectively collaborative to solve potential pitfalls, e.g., chattering where the robots nullify tasks, e.g., packing products at factories or in autonomous each other's actions, with limited communication. For example, it can be that different batches words, SGCM provides a more resilient architecture. of robots have different specifications and, as a result, This work's key contribution is a theoretical and algorithmic have complementary capabilities, which can happen when framework that applies Stackelberg games to robot a company purchases the batches years apart.