Coordination of Bounded Rational Drones Through Informed Prior Policy

Biological agents, such as humans and animals, are capable of making decisions out of a very large number of choices in a limited time. They can do so because they use their prior knowledge to find a solution that is not necessarily optimal but good enough for the given task. In this work, we study the motion coordination of multiple drones under the above-mentioned paradigm, Bounded Rationality (BR), to achieve cooperative motion planning tasks. Specifically, we design a prior policy that provides useful goal-directed navigation heuristics in familiar environments and is adaptive in unfamiliar ones via Reinforcement Learning augmented with an environment-dependent exploration noise. Integrating this prior policy in the game-theoretic bounded rationality framework allows agents to quickly make decisions in a group considering other agents' computational constraints. Our investigation assures that agents with a well-informed prior policy increase the efficiency of the collective decision-making capability of the group. We have conducted rigorous experiments in simulation and in the real world to demonstrate that the ability of informed agents to navigate to the goal safely can guide the group to coordinate efficiently under the BR framework.

I. Introduction

Efficient decision-making algorithms that can operate under computational constraints are essential in developing robotic systems. These systems need to select reasonable decisions from an extensive range of options within a limited time frame while constrained by finite computational resources. In multi-agent scenarios, such as generating motion trajectories that coordinate multiple agents, the challenge is further amplified, as the trajectories of different agents are interdependent, and the decisions made by one agent can impact the decisions of others. Moreover, when agents have different goals, balancing individual and collective decision-making objectives while considering each agent's computational limitations can make the problem even more complex.