Ergodic Specifications for Flexible Swarm Control: From User Commands to\n Persistent Adaptation

Abstract

This paper presents a formulation for swarm control and high-level task\nplanning that is dynamically responsive to user commands and adaptable to\nenvironmental changes. We design an end-to-end pipeline from a tactile tablet\ninterface for user commands to onboard control of robotic agents based on\ndecentralized ergodic coverage. Our approach demonstrates reliable and dynamic\ncontrol of a swarm collective through the use of ergodic specifications for\nplanning and executing agent trajectories as well as responding to user and\nexternal inputs. We validate our approach in a virtual reality simulation\nenvironment and in real-world experiments at the DARPA OFFSET Urban Swarm\nChallenge FX3 field tests with a robotic swarm where user-based control of the\nswarm and mission-based tasks require a dynamic and flexible response to\nchanging conditions and objectives in real-time.\n