Table of Contents
Fetching ...

Can A Single Human Supervise A Swarm of 100 Heterogeneous Robots?

Julie A. Adams, Joshua Hamell, Phillip Walker

TL;DR

This study addresses whether a single swarm commander can supervise a true heterogeneous swarm of 100 robots in real-world urban environments. Using the DARPA OFFSET FX-6 field exercises and the CCAST Immersive Interaction Interface, the authors deploy a large multi-fleet swarm and monitor the human operator with a multi-dimensional workload algorithm that estimates cognitive, auditory, physical, speech, and visual workload components from wearable sensors. The results show that, although overload episodes occur, the overall workload remains largely within a normal range and the missions are successfully completed, demonstrating the feasibility of single-human supervision for large heterogeneous swarms and validating the workload estimation approach in a complex, uncontrolled setting. These findings have practical implications for disaster response and logistics applications, and inform design considerations for scalable human-swarm interfaces and workload management in real-world deployments.

Abstract

An open research question has been whether a single human can supervise a true heterogeneous swarm of robots completing tasks in real world environments. A general concern is whether or not the human's workload will be taxed to the breaking point. The Defense Advanced Research Projects Agency's OFFsensive Swarm-Enabled Tactics program's field exercises that occurred at U.S. Army urban training sites provided the opportunity to understand the impact of achieving such swarm deployments. The Command and Control of Aggregate Swarm Tactics integrator team's swarm commander users the heterogeneous robot swarm to conduct relevant missions. During the final OFFSET program field exercise, the team collected objective and subjective metrics related to teh swarm commander's human performance. A multi-dimensional workload algorithm that estimates overall workload based on five components of workload was used to analyze the results. While the swarm commander's workload estimate did cross the overload threshold frequently, the swarm commander was able to successfully complete the missions, often under challenging operational conditions. The presented results demonstrate that a single human can deploy a swarm of 100 heterogeneous robots to conduct real-world missions.

Can A Single Human Supervise A Swarm of 100 Heterogeneous Robots?

TL;DR

This study addresses whether a single swarm commander can supervise a true heterogeneous swarm of 100 robots in real-world urban environments. Using the DARPA OFFSET FX-6 field exercises and the CCAST Immersive Interaction Interface, the authors deploy a large multi-fleet swarm and monitor the human operator with a multi-dimensional workload algorithm that estimates cognitive, auditory, physical, speech, and visual workload components from wearable sensors. The results show that, although overload episodes occur, the overall workload remains largely within a normal range and the missions are successfully completed, demonstrating the feasibility of single-human supervision for large heterogeneous swarms and validating the workload estimation approach in a complex, uncontrolled setting. These findings have practical implications for disaster response and logistics applications, and inform design considerations for scalable human-swarm interfaces and workload management in real-world deployments.

Abstract

An open research question has been whether a single human can supervise a true heterogeneous swarm of robots completing tasks in real world environments. A general concern is whether or not the human's workload will be taxed to the breaking point. The Defense Advanced Research Projects Agency's OFFsensive Swarm-Enabled Tactics program's field exercises that occurred at U.S. Army urban training sites provided the opportunity to understand the impact of achieving such swarm deployments. The Command and Control of Aggregate Swarm Tactics integrator team's swarm commander users the heterogeneous robot swarm to conduct relevant missions. During the final OFFSET program field exercise, the team collected objective and subjective metrics related to teh swarm commander's human performance. A multi-dimensional workload algorithm that estimates overall workload based on five components of workload was used to analyze the results. While the swarm commander's workload estimate did cross the overload threshold frequently, the swarm commander was able to successfully complete the missions, often under challenging operational conditions. The presented results demonstrate that a single human can deploy a swarm of 100 heterogeneous robots to conduct real-world missions.
Paper Structure (37 sections, 1 equation, 19 figures, 15 tables)

This paper contains 37 sections, 1 equation, 19 figures, 15 tables.

Figures (19)

  • Figure 1: (a) The FX-4 Joint Base Lewis-McChord CACTF. (b) A UAV conducting a building Surveil. Photos courtesy of DARPA.
  • Figure 2: (a) A sand table representation, including a neutralized UGV's glyph. (b) A UAV glyph (indicated by the propeller), where the top bars indicate communication connectivity (blue) and battery level (multi-colored), the lightning bolt indicates an electronic warfare payload, the forward facing camera, the central icon indicates the task currently being executed, and the gray dashed box indicates the UAV is virtual.
  • Figure 3: Example of (a) an improvised explosive device artifact and associated threat ring, and (b) swarm visualizations, where six sub-swarms are beginning to execute a mission. Note, the fuchsia ring represents the spatial area the SC sees within the head mounted display.
  • Figure 4: The FX-6 tactics menu.
  • Figure 5: (a) Example tactic and (b) mission plan visualizations, where the mission plan contains several nodes (white disks) gated by a single signal (red button with raised cover).
  • ...and 14 more figures