Level 2 (Self)
TECHNOLOGY AREAS
Air Platform
MODERNIZATION PRIORITIES
Trusted AI and Autonomy
KEYWORDS
Humanoid Robots; Human-Robot Interaction; Multi-Robot Coordination; Fleet Management; Supervisory Control; Task Allocation; Autonomy; Resource Optimization
OBJECTIVE
The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.
To Effectively and Efficiently Coordinate Multiple Humanoid and Industrial Robots for Complex Tasks in Dynamic Industrial Environments
ITAR
The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.
DESCRIPTION
Within Air Force depots for aircraft maintenance and sustainment, there are many workloads that present significant challenges for human personnel due to reasons including high physical demand, repetitive tasks, and unfriendly environmental conditions. In the endeavor of optimizing manufacturing and sustainment operations, robots have increasingly been integrated, serving to separate human personnel from potentially hazardous activities and creating opportunities for process improvement. The robots that have been determined to be most versatile in industrial settings as support to human personnel are those designed to operate similarly, in a humanoid manner.As the potential of humanoid robots for widespread deployment in various applications is growing in accordance with their increasing sophistication and capability, so is the cruciality of managing and coordinating large fleets of these robots effectively for the maximization of their utility and the assurance to complete tasks successfully. While implementing a fleet management system allows for the dynamic allocation of robots to specific maintenance tasks based on real-time demand and priority, resource utilization optimization, and aircraft downtime minimization, current robot management systems often lack the scalability, flexibility, and robustness required for complex, real-world deployments involving humanoid robots beyond material handling operational scenarios. Current research emphasizes the integration of advanced sensing capabilities, such as computer vision and tactile feedback, into humanoid robots to enable them to perform intricate maintenance tasks, such as component inspection and repair, with increasing autonomy and precision to support a shift in robot fleet management towards decentralized control architectures that allow humanoid robots to adapt to changing task priorities and collaborate more effectively with human personnel. This project seeks to develop a humanoid fleet management system that provides a centralized platform for monitoring, controlling, and coordinating the activities of multiple robots across a variety of manufacturing and sustainment operations. The system should enable autonomous task allocation based on robot capabilities and availability, optimize resource utilization, allow real-time monitoring and control, facilitate seamless communication between robots and human operators, and adapt to dynamic changes in the operational environment. The system should be scalable to fleets of varying sizes and adaptable to different humanoids, other robot platforms, and operational scenarios.
PHASE I
This is a Direct-to-Phase II initiative. Companies must demonstrate, from the outset, (1) a prototype system capable of basic fleet monitoring for mobile and non-mobile platforms, task assignment, and adaptive autonomous robot control in a simulated environment. (2) An understanding of the challenges associated with managing and coordinating humanoid robot fleets and propose innovative solutions for addressing these challenges. (3) Proven experience deploying autonomous systems performing manufacturing and sustainment activities beyond material handling. Provide a clear plan for scaling the system to larger fleets and more complex operational scenarios.
PHASE II
Develop a functional prototype of the humanoid fleet management system and demonstrate its performance on a physical fleet of robots including humanoid, non-humanoid mobile, and non-mobile industrial robotics platforms. Evaluate the system's effectiveness in coordinating the robots to perform a range of collaborative tasks in a real-world environment, showcasing its ability to adapt to dynamic conditions and optimize resource utilization. Quantify the performance improvements achieved through fleet management compared to individual robot operation. Refine the system based on experimental results, focusing on scalability, robustness, and user-friendliness. The expected TRL from Phase II is TRL 7 or 8.
PHASE III DUAL USE APPLICATIONS
If Phase II is successful, Phase III will focus on transitioning the fleet management system to a commercially viable product. This includes further development and refinement of the system, rigorous testing and validation in diverse operational environments, and integration with existing robotic platforms and control systems. Explore potential applications in various sectors, including manufacturing, logistics, and inspection. Develop partnerships with robotics manufacturers to integrate the fleet management system into their product offerings, paving the way for widespread adoption of humanoid robot fleets across a range of industries.
REFERENCES
Dai, Yanyan, et al. Development of a Fleet Management System for Multiple Robots' Task Allocation Using Deep Reinforcement Learning. Processes, vol. 12, no. 12, 20 Dec. 2024, p. 2921, https://doi.org/10.3390/pr12122921. Accessed 1 August 2025.
Hazik, Jakub, et al. Fleet Management System for an Industry Environment. Journal of Robotics and Control/Journal of Robotics and Control (JRC), vol. 3, no. 6, 23 Dec. 2022, pp. 779 789, https://doi.org/10.18196/jrc.v3i6.16298. Accessed 1 August 2025.3. Morais, Paulo, et al. A Review of Robot Fleet Management. IEEE Access, vol. 13, 7 July 2025, pp. 118975-119003, ieeexplore.ieee.org/abstract/document/11072173, https://doi.org/10.1109/access.2025.3586564. Accessed 1 Aug. 2025.
