Agent-Based Emulation for Deploying Robot Swarm Behaviors

TL;DR

An Agent-Based Embodiment and Emulation process that balances the importance of running physical swarming experiments and the prohibitively time-consuming process of even setting up and running a single experiment by leveraging low-fidelity lightweight simulations to enable hypothesis-formation to guide physical experiments is presented.

Abstract

Despite significant research, robotic swarms have yet to be useful in solving real-world problems, largely due to the difficulty of creating and controlling swarming behaviors in multi-agent systems. Traditional top-down approaches in which a desired emergent behavior is produced often require complex, resource-heavy robots, limiting their practicality. This paper introduces a bottom-up approach by employing an Embodied Agent-Based Modeling and Simulation approach, emphasizing the use of simple robots and identifying conditions that naturally lead to self-organized collective behaviors. Using the Reality-to-Simulation-to-Reality for Swarms (RSRS) process, we tightly integrate real-world experiments with simulations to reproduce known swarm behaviors as well as discovering a novel emergent behavior without aiming to eliminate or even reduce the sim2real gap. This paper presents the development of an Agent-Based Embodiment and Emulation process that balances the importance of running physical swarming experiments and the prohibitively time-consuming process of even setting up and running a single experiment with 20+ robots by leveraging low-fidelity lightweight simulations to enable hypothesis-formation to guide physical experiments. We demonstrate the usefulness of our methods by emulating two known behaviors from the literature and show a third behavior `discovered' by accident.

Figures (6)

• Figure 1: Diminishing return of model value relative to development cost RGS:10.
• Figure 2: Different local interaction rules leading to different emergent group behaviors (under certain conditions).
• Figure 3: Flow Chart of Reality-to-Simulation-to-Reality for Swarms (RSRS) Process
• Figure 4: Examples of different values of (a) $\overline{c}$ and (b) $\overline{\delta}$.
• Figure 5: A 2D slice of a phase diagram produced using simulated results for the milling behavior demonstrating the value of even a low-fidelity phase diagram as a guide to physical experiments. The 9 colored shapes in the phase diagram show that only 5 of 9 physical experiments matched the simulator results, but the usefulness in the insights gained from the 56 simulations with only 50% model confidence still has clear value to humans and enables forming hypotheses that can be physically tested.