To maximize the advantages of unmanned systems, technologies enabling the cooperation, coordination, and interoperability through heterogeneous multi-robotic systems (MRS) are vital in providing the significantly diversified intrinsic and/or extrinsic characteristics necessary to adapt to unknown environmental and/or dynamic operational tasking, thereby expanding the operational envelope to better manage real world conditions. In order to achieve a cohesive solution for addressing these challenges, Heron Systems delivers Generalized Logistics for Unstructured Environments (GLUE); a mature software framework enabling an explicit decentralized coordination mechanism wherein the cumulative utility of each system is maximized through simultaneous recursive evaluation of multi-objective optimization functions.

GLUE preserves opportunities to optimize construction, planning, and execution phases for specific missions, environments, and/or behaviors. This has been demonstrated in a variety of swarm systems architectures and vehicle platforms; inclusive of both MACE and 3rd party solutions. This enabled Heron Systems to quantitatively demonstrate an inherent ability for System of Systems (SoS) to exhibit significantly adaptable complex behaviors where the situational awareness of the environmental state is evolving and potentially disparate.


  • Provides the necessary algorithmic rigor required to achieve a system-agnostic solution capable of assessing resources and subsequently coordinate collaborating agents to elicit complex behaviors.

  • Decomposition of human perceivable behaviors into machine interpretable robotic motion primitives through online task generation.

  •  Agents’ action policies advocate self-interests while guaranteeing a monotonically increasing global utility; preserving the benefits of heterogeneous agent independence.

  • Tractable performance with finite time execution produces quantifiable and deterministic results.

  • Significant reduction in operator burden through autonomous task generation and subsequent coordination per instantiated human-perceivable behavior.

  • Integration within the MACE ecosystem allows Heron Systems to rapidly innovate collaborative autonomy research with an immediate ability to demonstrate behaviors within a swarm system.

Ongoing Research

  • Heron Systems defines a collaborative subset of SoS consisting of heterogeneous agents with significantly diversified skills used to address the decomposition of a complex task in an optimal (as defined by an objective function) way a coalition. Coalitions are formulated to provide the SoS a capability to robustly respond to spontaneous opportunities resulting from adaptation of the situational awareness when executing over-the-horizon and reduce overall system coordination/communication burden.
  • GLUE facilitates adapting agent action policies in dynamic response to vulnerabilities of the swarm. Foundational methods (e.g. describing the diversity of a coalition) can be leveraged to generate further abstract methods that are beneficial in assessing the effectiveness of the composition to achieve minimum readiness, redundancy, and diversity.

Demonstrated Programs

  • JHU SKYBORG Autonomy Incubator
  • MACE


Collaborative multi-agent systems achieved by naively increasing the number of systems is practically a nonstarter due to the compounding management workload. Effective swarms need to implement a high-degree of AI that can be trusted to autonomously execute their own observe-orient-decide-act (OODA) loop, providing a means to address dynamic conditions and reduce operator workload. Task-able swarms capable of generating actionable information without direct operator management yields trust in the technology, creating a valuable tool.


A resource and task allocation software framework was developed that provides the robotics capabilities, agent-based behaviors, and collaborative autonomy to field trusted autonomous assets.


Complex collaborative autonomous behaviors can be achieved with a single high-level initial condition.