Collaborative Agent Control Using Shared Models Under Low Bandwidth

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for controlling heterogeneous unmanned systems face challenges in maintaining effective communication and localization in environments with limited bandwidth and degraded GPS, which hinders their ability to perform collaborative tasks efficiently.

Innovation Solution

The TEAM Estimation (TE) system, which involves each agent simulating numeric models of other agents to reduce communication bandwidth and improve localization accuracy by sharing only significant data, enabling collaborative target identification and automated task generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If uninterrupted high bandwidth wireless communications are assumed, then control capability is provided, but communication bandwidth consumption increases

Engineering Contradiction:

Improvecontrol capabilityVSAvoidcommunication bandwidth

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system extracts and transmits only the most critical data elements needed for control decisions, filtering out redundant information. This selective data extraction maintains control reliability while significantly reducing bandwidth consumption compared to transmitting all available sensor data.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Different data streams are transmitted with different quality levels based on their importance to control decisions. Critical control parameters are transmitted with high fidelity, while less important data is transmitted at lower quality or aggregated, optimizing the trade-off between control capability and bandwidth usage.

Inventive Principle:

Principle #3Local quality

2Reliability

If high-quality real-time localization data is assumed, then control capability is provided, but dependency on external infrastructure increases

Engineering Contradiction:

Improvecontrol capabilityVSAvoidenvironmental adaptability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system pre-processes and caches localization data before it becomes critical, building up buffers of position information during periods when GPS is available. This preliminary action allows the system to maintain control capability during GPS-denied periods without real-time infrastructure dependency.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-localization capabilities using onboard sensors and relative positioning algorithms, reducing dependency on external GPS infrastructure. Agents can determine their positions through self-contained methods such as inertial navigation and relative measurements from other agents.

Inventive Principle:

Principle #25Self-service

3Loss of information

If all agents continuously share complete state data, then situational awareness is improved, but communication bandwidth consumption increases

Engineering Contradiction:

Improvesituational awarenessVSAvoidcommunication bandwidth

Core Design Contradiction:

Loss of informationVSQuantity of substance

Solution Approach 1:

Multiple agents share a common world model that is continuously updated with incremental data exchanges. Instead of each agent transmitting its complete state, agents merge their partial observations and model updates, achieving comprehensive situational awareness through combination rather than duplication of data transmission.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

Agents transmit only the partial data necessary to maintain situational awareness thresholds, rather than complete state information. The system uses predictive models to estimate missing data, allowing agents to function with partial information exchanges that are sufficient for collaborative operation.

Inventive Principle:

Principle #16Partial or excessive action

4Adaptability or versatility

If agents operate in GPS-denied environments, then environmental adaptability is improved, but localization accuracy deteriorates

Engineering Contradiction:

Improveenvironmental adaptabilityVSAvoidlocalization accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system implements feedback loops where agents continuously exchange relative position measurements and use this feedback to correct drift in their self-localization estimates. This collaborative feedback mechanism maintains localization accuracy in GPS-denied environments by constantly refining position estimates based on inter-agent measurements.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The shared world model acts as an intermediary that integrates and reconciles localization data from multiple agents. This intermediary model synthesizes partial observations from different perspectives to produce more accurate collective localization estimates than any single agent could achieve alone.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11334069B1Systems, methods and computer program products for collaborative agent control

Publication Date: 2022.05.17 NATIONAL TECHNOLOGY & ENGINEERING SOLUTIONS OF SANDIA LLC

AI summary

Systems, methods and unmanned agents for collaboratively controlling agents in a collaborative network by one or more agents continuously simulating numeric models of one or more other agents in the network to dramatically reduce the computational bandwidth required between agents, and improve the quality of shared estimates of the agent locations as well as the locations and characteristics of other objects of interest, e.g. targets. Bandwidth is reduced by using the models to intelligently filter data before communicating.