Implicit adaptive multi-robot coordination in dynamic environments

Multi-robot teams offer key advantages over single robots in exploration missions by increasing efficiency (explore larger areas), reducing risk (partial mission failure with robot failures), and enabling new data collection modes (multi-modal observations). However, coordinating multiple robots to achieve a system-level task is difficult, particularly if the task may change during the mission. In this work, we demonstrate how multiagent cooperative coevolutionary algorithms can develop successful control policies for dynamic and stochastic multi-robot exploration missions. We find that agents using difference evaluation functions (a technique that quantifies each individual agent's contribution to the team) provides superior system performance (up to 15%) compared to global evaluation functions and a hand-coded algorithm.

Authors

• Mitchell K. Colby
• Jen Jen Chung
• Kagan Tumer

Keywords

• Robot kinematics
• Approximation methods
• Sociology
• Statistics
• Robot sensing systems
• Neural networks
• Dynamic Environment
• System Performance
• Superior Performance
• Evaluation Of Function
• Multi-agent
• Global Rate
• Exploration Missions
• Neural Network
• Learning Algorithms
• Local Actors
• Performance Variables
• Evolutionary Algorithms
• Fitness Function
• Local State
• Unmanned Aerial Vehicles
• Feedback Signal
• Multi-agent Systems
• Team Performance
• Policy Learning
• External Feedback
• Swarm Robotics
• Neural Network Control
• Mission Requirements
• Team Behavior
• State-action Pair
• External Operations
• Unknown Regions
• Human Operator
• Range Of Sensors
• Global Teams