Autonomous Agents Networks Blueprint Family

This blueprint family aims to present Autonomous Agents Networks (AAN), where agents can be robots, vehicles, drones, sensors, and devices exhibiting autonomous behavior based on AI models and rules-based reasoning. Models may be multi-modal, either large models maintained in the cloud or on-device.

Emphasis is placed on (1) human safety related directives, self-healing features, adaptivity, auto-sensing, and (2) combining AI and required telecom standards necessary for fully autonomous and intelligent operation in remote and cloud-unavailable environments.

A layered approach is taken for defining actions concerning each type of expected functionalities.

Attributes	Description	Informational
Type	New
Industry Sector	AI, Telco, IoT/IIoT, Carrier Networks, Driving Networks, Federated Networks
Business driver	More and more adaptive and autonomous machines, such as robots, drones, self-driving vehicles, etc. are being deployed in different contexts and in close proximity to human activities. With this, there is a need for not only architectural reference but also standards on how machines (or “agents”) will interact with each other and with humans in a safe, reliable, stable and coordinated way. Agents will utilize communications technologies and network standards based on P2P (peer-to-peer) cellular and satellite to notify each other and humans of important safety related events they detect and observe during their operation, regardless of whether they have a cloud connection available. In the future, we can expect mobile drones and robots to act as machine level first-responders, as they will be prevalent, widespread, and likely to discover human danger and property damage first.
Business use cases	Industrial Machine Communications On-device multimodal small models and P2P communications allow machines in manufacturing, construction, agriculture, and other machine-intensive industrial sectors to communicate directly, regardless of cloud connectivity issues or WiFi impediments such as metal or other interference, distance, landscape obstructions, etc. Direct device-to-device communications, both multicast and bi-directional, are supported by cellular and satcom networks Flood Prediction, Detection, and Rescue Cameras, water level sensors, drones, meteorological stations and dam leak systems exchange data, send alerts, monitor overall systems and feed different datasets concerning rain level, floods (local and regional flow) etc. First Responder Machine Assistants Mobile robots, drones, and vehicles detect, identify, and report incidents to 1) other machines within a 1 to 5 mile radius, and 2) First Responders depending on incident priority level. Machines from different providers and vendors must pay attention to their surroundings, interact with humans if necessary, and share information about safety - human safety as well as property and other machines. P2P call and satcom network protocols are used to eliminate dependencies on cloud communications subject to vendor incompatibility / lack of cooperation and unreliable connectivity depending on environmental conditions Proximate Machine Safety On-device multimodal small model apps for human safety in close proximity to robots and automated vehicles. Personal apps can utilize visual and audio input to monitor users' surroundings for dangerous machine conditions and behavior, for example when riding as a passenger in a robotaxi, users can attach a smartphone USB camera to a headrest or other elevated location and warn on dangerous conditions such as imminent pedestrians or pets. As another example factory workers can wear their phone as a body camera to monitor automated machines (eg. a forklift) for dangerous proximity or behavior
Business Cost - Initial Build Cost Target Objective	At least one Edge Site should be deployable at nearby sensors and actuators network, being able to collect, analyze and send over it’s findings as well telemetry. All the setup is low cost as much as possible.
Github page	https://github.com/signalogic/Autonomous-Agents-Networks
Business Cost – Target Operational Objective	For Example: 1.Edge Cloud deployable at Central offices with 7 servers in a single rack should incur low operational costs per year 2. In-place upgrade of the Edge cloud should be supported without impacting the availability of the edge applications 3. Edge Solution should have role based access controls, Single Pane of Glass control, administrative and User Based GUIs to manage all deployments. 4. The automation should also support zero touch provisioning and management tools to keep operational cost lower
Security need	For Example: The solution should have granular access control and should support periodic scanning
Regulations	For Example: The Edge cloud solution should meet all the industry regulations of data privacy, telco standards (NEBS), etc.,
Other restrictions	Physical restrictions: Power restrictions: Connectivity restrictions: Precision restrictions: Accessbility restrictions:
Additional details	For Example: The Edge Cloud Solution should be deployable across the globe and should be able to support more than 10,000 locations	Use case submitters can include files (PPT, DOC, etc…) that explain the use case in more detail.

Case Attributes	Description	Informational
Type	New
Blueprint Family - Proposed Name	Autonomous Agents Network
Use Case	Network Cloud
Blueprint proposed	Central Office deployments • Unicycle • Tricycle • Cruzer Customer Premise deployments • Rover
Initial POD Cost (capex)	• Rover less than $20k • Unicycle less than $150k • Tricycle less than $300k • Cruzer less than $800k
Scale	• Rover - 1 server • Unicycle - 1 rack • Tricycle - 3 racks • Cruzer - 6 racks
Applications	Any type of Edge Virtual Network Functions
Power Restrictions	Example Only: • Cruzer - less than 50k watts
Preferred Infrastructure orchestration	Examples Only: OpenStack - VM orchestration Docker/K8 - Container Orchestration OS - Linux VNF Orchestration - ONAP Under Cloud Orchestration – Airship
Additional Details	Submitter to provide additional use case details

Case Attributes	Description	Informational
Type	New or Modification to an existing submission
Blueprint Family - Proposed Name	Autonomous Agents Networks Blueprint Family
Use Case	Examples Only: Network Cloud
Blueprint proposed Name	Autonomous Agents Networks Blueprint Family
Initial POD Cost (capex)	Water leak and level detector: Metereological station: Cameras: Drones:
Scale & Type	• Up to 7 servers - Site Edges • x86/ARM server or deep edge class Up to 25 servers/nodes: Regional Edge
Applications	Examples Only: 5G Core or vRAN (RIC)
Power Restrictions	Example Only: • Less than 10Kw
Infrastructure orchestration	Examples Only: OpenStack Pike or above/OpenNebula One - VM orchestration and container Docker 1.13.1 or above / K8 1.27 or above- Container Orchestration (k3s and KubeEdge) OS - Ubuntu 16.x VNF Orchestration - ONAP Beijing Under Cloud Orchestration - Airship v1.0
SDN	Examples Only: SR-IOV & OVS-DPDK or VPP-DPDK OpenDayLight
Workload Type	Examples Only: VMs (microVMs preferable) and Containers
Additional Details	Submitter to provide additional use case details