Autonomous Agent Formation Control With Delayed Self-Reinforcement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems for automated vehicles, such as driverless trucks and unmanned aerial vehicles, face challenges in maintaining formation and responding quickly to changes, especially when interacting with both machine and human-piloted vehicles, due to slow response times and deficient vehicle behavior.
Innovation Solution
The implementation of a control system that uses delayed self-reinforcement to generate course correction data based on the average movement of adjacent automated vehicles and time-delayed movement data, allowing for faster convergence and improved cohesion in vehicle formations without requiring additional signal transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If existing control schemes are used for automated vehicles, then basic navigation is achieved, but response time is slow and vehicle behavior is deficient
Solution Approach 1:
The patent applies preliminary action by using delayed self-reinforcement that incorporates historical movement data into the control decision-making process. The controller uses past movement patterns of the automated vehicle to anticipate and prepare for future maneuvers, enabling faster response times while maintaining reliable vehicle behavior through proactive adjustment of navigation commands.
2Stability of the object's composition
If automated vehicles maintain formation using traditional control methods, then basic formation keeping is achieved, but convergence is slow and cohesion is poor
Solution Approach 1:
The patent implements feedback mechanisms where each automated vehicle continuously monitors the movement of adjacent vehicles and adjusts its own navigation commands accordingly. The delayed self-reinforcement component enhances this feedback by incorporating historical movement data, creating a more responsive and cohesive formation that converges faster while maintaining stability through iterative adjustment of course correction commands.
3Reliability
If more signal transfer is used to improve formation control, then better coordination is achieved, but system complexity increases
Solution Approach 1:
The patent applies self-service by enabling each automated vehicle to independently generate its own navigation commands using local sensors and onboard processing. The delayed self-reinforcement mechanism allows each vehicle to use its own historical movement data alongside observations of adjacent vehicles, eliminating the need for complex centralized signal transfer while maintaining reliable formation control through decentralized autonomous decision-making.
Data Source
AI summary
The behavior of automated agents, such as autonomous vehicles, drones, and the like, can be improved by control systems and methods that implement a combination of neighbor following behavior, or neighbor-averaged information transfer, with delayed self-reinforcement by utilizing time-delayed movement data to modify course corrections of each automated agent. Disclosed herein are systems and methods by which a follower agent, or a multiple follower agents in formation with a plurality of automated agents, can be controlled by generating course correction data for each follower agent based on the movement of neighboring agents in formation, and augmenting the course correction data based on time-delayed movement data of the follower agent. The delayed self-reinforcement behavior can (i) increase the information-transfer rate between autonomous agents without requiring an increased, individual update-rate; and (ii) cause superfluid-like information transfer between the autonomous agents, resulting in improvements in formation-keeping performance of the autonomous agents.