Intelligent, autonomous communications systems working together to optimize the exploration of our solar system.
Cognitive Communications Project
Cognitive communications research aims to mitigate the increasing communication complexity for mission users by increasing the autonomy of links, networks, and service scheduling. NASA has traditionally launched single spacecraft missions, typically scheduled weeks in advance, with each asset serving a single user spacecraft at a time. Recently, NASA science missions have found benefit in an alternate approach, launching swarms of spacecraft allowing coordinated simultaneous observations from different perspectives. As more complex swarm missions launch, a challenge will be coordinating communications within the swarm. The Cognitive Communications project at NASA Glenn Research Center (GRC) aims to develop decentralized space networks with artificial intelligence (AI) agents optimizing communication link throughput, data routing, and system-wide asset management as a way to mitigate this challenge.
What is Cognitive Communication?
NASA’s Cognitive Communications project defines “cognitive” as any system, or part of a system, that is able to overcome obstacles, respond to and learn from its environment, and achieve beneficial goals to the completion of its primary mission with minimal to no human interaction. Effectively, the cognitive system must have the ability to adapt to changing conditions by producing reasonable outcomes in scenarios that extend beyond the pre-programmed knowledge of its original inception. These systems utilize cognitive engines (CE), or decision-making algorithms that enable part of a cognitive system. A cognitive engine learns from past allocations to improve mission communications performance over time. The growing complexity of NASA’s spacecraft constellations, communication relay offerings, and mission architectures, drive the need for the development of autonomous communication systems.
The Cognitive Communications project at NASA GRC performs research in four distinct but intertwined areas:
- Cognitive Links – concerning point-to-point connections between two devices
- Cognitive Networks – concerning multiple devices routing information among multiple links
- Cognitive Systems – concerning the interaction among devices and supporting ground-and space-based infrastructure
- Enabling Technology – concerning the on-board processing, sensing, and adaptation capability of a device that allows it to participate in cognitive links, networks, or systems
A space communication link is a wireless connection between two radios over distance with at least one of the radios in space. Currently, NASA missions determine the exact communication system configuration of the radio prior to launch. While this approach is proven and robust, it is also inflexible to real-time mission changes that can occur after launch. Benefits to using a cognitive link approach opposed to the traditional link approach currently used by NASA include diminishing data loss from radio frequency (RF) interference, optimizing throughput, and reduced operator burden.
Space communication networks are used to route information between multiple communication links. The goal of a cognitive network is to have the autonomous aspects not only understand the interfaces between the systems, but also optimize to fulfill specific objectives. NASA has a demonstrated need for networks that are tolerant to delay and disruption, known as Delay-Tolerant Networking (DTN). Engineers at NASA GRC are currently researching methods of integrating cognitive aspects into DTN protocol.
Cognitive systems aim to optimize performance across entire space communication systems, improving the interaction between mission spacecraft and ground service provider infrastructure. Currently, network operators manage access to the highest performance services based on requests from each mission’s operations staff. Mission operators must anticipate spacecraft commanding and data transfer needs potentially weeks in advance. By increasing system autonomy, the mission spacecraft can negotiate access to communication services based on its current data transfer needs without user interference.
Enabling technologies are used to adapt modern equipment such as neuromorphic processors to allow for cognitive capabilities. The hardware necessary to implement cognitive communications capabilities on-board spacecraft typically mimics the hardware that enables artificial intelligence and machine learning on the ground. While each of these four focus areas can mature independently, the end goal is to transition towards integration into a decentralized cognitive space communications system.