Classifying Environmental Features From Local Observations of Emergent Swarm Behavior Megan Emmons, Student Member, IEEE, Anthony A. Maciejewski, Fellow, IEEE, Charles Anderson, Senior Member, IEEE, and Edwin K. P. Chong, Fellow, IEEE Abstract—Robots in a swarm are programmed with individual behaviors but then interactions with the environment and other robots produce more complex, emergent swarm behaviors. One discriminating feature of the emergent behavior is the local distri- bution of robots in any given region. In this work, we show how local observations of the robot distribution can be correlated to the environment being explored and hence the location of open- ings or obstructions can be inferred. The correlation is achieved here with a simple, single-layer neural network that generates physically intuitive weights and provides a degree of robustness by allowing for variation in the environment and number of ro- bots in the swarm. The robots are simulated assuming random motion with no communication, a minimalist model in robot sophistication, to explore the viability of cooperative sensing. We culminate our work with a demonstration of how the local distri- bution of robots in an unknown, office-like environment can be used to locate unobstructed exits. Index Terms—Biologically inspired robotics, environment explora- tion, multi-agent systems, swarm robotics. I. Introduction W HILE individual or small teams of robots have been used for exploration in relatively controlled settings, harsh environments like partially collapsed buildings and un- derground mines remain an important challenge. Our goal is to leverage the domain of swarm robotics to expand the type of environments which can be reliably explored. In this work we provide a base level for what information can be obtained about features in an unknown environment from a minimalist swarm, i.e., one comprised of very simple, inexpensive robots that contain no sensing or direct communication abilities. Inspired by cooperative biological systems like ants and bees, robotic swarms are a relatively new area of robotics research that extend multi-robot systems by incorporating significantly more robots. The increase in robot numbers is frequently countered by a decrease in the individual robot complexity to ensure the entire system is scalable [1] and more easily managed by a human. Like multi-robot systems, swarms can accomplish complex tasks that exceed the capabilities of the individual robots but swarms have additional benefits in exploration applications. The swarm can cover an area more efficiently than an individual robot or small team, and, as we demonstrate in this paper, environmental features can be inferred without requiring robots to explicitly store or relay information, further increasing system robustness and decreasing exploration time. Feature inference is achieved using local observations of the swarm distribution. Each individual robot is programmed with a set of known behaviors. Frequent robot-robot and robot- environment interactions naturally lead to more complex but often difficult to predict emergent behaviors. The emergent behavior can be quantified by different properties (see, e.g., [2]) but in this work we focus on how the robots are distributed. Hence, there is a correlation between three key factors: individual robot behaviors, environment features, and the observable distribution of robots. If two factors are known, the third can be inferred. If the robot behaviors are independent and the environment is known, a partial differential equation (PDE) can be derived to exactly model the robot distribution [3]. With a finite number of environments, a least-squared error comparison between each derived PDE model and an observed robot distribution can be used to identify in which environment the robots are moving. As individual robot behaviors become more sophisticated and environments become more varied, there is no plausible deterministic approach for predicting the robot distribution, but there is still a correlation. In this paper, we exploit the correlation by using a simple, single-layer neural network to demonstrate how known individual robot behaviors and locally observed robot distributions can accurately predict environmental features. We focus on a minimum sensing scenario where the robots are limited to random motion and have no communication abilities. A simple, single-layer neural network is then trained to correlate the number of robots in a central region of the environment with the environment type itself. Despite the limited robot capabilities and local observations, this work shows the distribution of a swarm can be used to quickly and accurately infer environmental features. The primary contribution of this work is providing a baseline feasibility study to affirm that environmental information can Manuscript received January 29, 2020; revised February 19, 2020; accep- ted March 6, 2020. Recommended by Associate Editor MengChu Zhou. (Cor- responding author: Megan Emmons.) Citation: M. Emmons, A. A. Maciejewski, C. Anderson, and E. K. P. Chong, “Classifying environmental features from local observations of emer- gent swarm behavior,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 3, pp. 674–682, May 2020. M. Emmons, A. A. Maciejewski, and E. K. P. Chong are with the Depart- ment of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO 80523 USA (e-mail: memmons14k@gmail.com; aam@colostate.edu; edwin.chong@colostate.edu). C. Anderson is with the Department of Computer Science, Colorado State University, Fort Collins, CO 80523 USA (e-mail: chuck.anderson@colostate. edu). Color versions of one or more of the figures in this paper are available on- line at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/JAS.2020.1003129 674 IEEE/CAA JOURNAL OF AUTOMATICA SINICA, VOL. 7, NO. 3, MAY 2020