Consensus learning for distributed coverage control

A decentralized controller is presented that causes a network of robots to converge to a near optimal sensing configuration, while simultaneously learning the distribution of sensory information in the environment. A consensus (or flocking) term is introduced in the learning law to allow sharing of parameters among neighbors, greatly increasing learning convergence rates. Convergence and consensus is proven using a Lyapunov-type proof. The controller with parameter consensus is shown to perform better than the basic controller in numerical simulations.

Authors

• Mac Schwager
• Jean-Jacques E. Slotine
• Daniela Rus

Keywords

• Distributed control
• Robot sensing systems
• Automatic control
• Convergence
• Optimal control
• Robotics and automation
• Control systems
• Numerical simulation
• Q measurement
• Learning
• Coverage Control
• Numerical Simulations
• Distribution Information
• Basic Control
• Decentralized Control
• Centroid
• Bimodal
• Final Value
• Sensory Function
• Parameter Vector
• Adaptive Control
• Function Approximation
• Sensor Measurements
• Error Parameters
• Voronoi Diagram
• Graph Laplacian
• Adaptive Law
• Intuitive Interpretation
• Parameter Convergence
• Consensus Control
• Robotic Group
• Unit Square
• Position Of The Robot
• Spatial Integration