Search NASA⌕ Search

SEARCH · Search NASA

Results for “multi-agent system”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

204 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning

The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.

Ruixuan Han↗
NASA NTRSDate not supplied

Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning

The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.

Ruixuan Han↗
NASA NTRSDate not supplied

Autonomous In-space Construction, Maintenance, and Reconfiguration Using Programmable Meta-Material

NASA ARC's Coded Structures Laboratory (CSL) is developing autonomous construction, maintenance, and reconfiguration technologies to meet long-duration and deep space infrastructure needs, in accordance with long-term NASA goals of "in-space reliance" and "mass-less exploration." We seek to achieve these capabilities by utilizing a "programmable meta-material" approach that integrates emerging advances in materials (mechanical meta-materials), manufacturing (cooperative mobile robotics), and autonomy (multi-agent planning algorithms). Through the ARMADAS project, we have shown assembly of high-performance engineered cellular materials using multiple cooperating mobile robotic assemblers. In this paper, we describe how such a programmable meta-material architecture may shift the paradigm of how we design, build, manufacture, and operate future space infrastructure and assets. The core of a programmable meta-material architecture consists of 3 main technology sub-areas: the structure, the assembly agents, and the assembly algorithms. We co-design these systems to ensure an adaptable system that can create and reconfigure structures from a base set of building block components. From this core technology, we can branch out and expand the capability of the system through additional secondary component types and robotic agents to perform activities such as inspections, maintenance, repair, payload installation, or perform power and communications interconnect. As these technologies mature, future designers will be able to utilize the system to rapidly integrate and operate assets in space or on planetary surfaces from a set of well-tested part library, or create their own modules to integrate into the system. A core trait to the development of this system is the automation approach. Because of the modular and functional discrete (pixel-like) nature of the structural system, a diverse set of powerful algorithms for analysis, planning, and simulation can be adapted and leveraged to optimize construction, maintenance, and dynamic reorganization (as hardware with programmable form and function). With an ability to free the design space from launch vehicle constraints and fundamentally shift how a mission is designed and conducted, we discuss the influence of a programmable meta-material architecture on mission design, build, and operations. For the "design phase", we discuss project lifecycle effects, costs, time, and performance. For the "build phase", we discuss reusability, ISRU, manufacturing, material logistics, and scalability. And for "operations", we discuss autonomy, maintenance and upgrades, reliability, and reconfiguration. Autonomy and modularity are the primary enabling traits of this system. Engineering systems that utilize a modular and reconfiguration building block approach such as digital communication and computation systems, currently lead all other areas of technology in size and complexity scalability. NASA is extending the benefits and flexibility of digital systems to hardware systems, to optimize materials lifecycle management and expand our space exploration mission capabilities.

in space assembly↗
NASA NTRS2023

An Overview of Distributed Spacecraft Autonomy at NASA Ames

Autonomous decision-making significantly increases mission effectiveness by mitigating the effects of communication constraints, like latency and bandwidth, and mission complexity on multi-spacecraft operations. To advance the state of the art in autonomous Distributed Space Systems (DSS), the Distributed Spacecraft Autonomy (DSA) team at NASA's Ames Research Center is developing within five relevant technical areas: distributed resource and task management, reactive operations, system modeling and simulation, human-swarm interaction, and ad hoc network communications. DSA is maturing these technologies - critical for future large autonomous DSS - from concept to launch via simulation studies and orbital deployments. A 100-node heterogenous Processor-in-the-Loop (PiL) testbed aids distributed autonomy capability development and verification of multi-spacecraft missions. The DSA software payload deployed to the D-Orbit SCV-004 spacecraft demonstrates multi-agent reconfigurability and reliability as part of an ESA-sponsored in-orbit technology demonstration. Finally, DSA's primary flight mission showcases collaborative resource allocation for multipoint science data collection with four small spacecraft as a payload on NASA's Starling 1.0 satellites.

Caleb Ashmore Adams↗
DOE OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗