Acquiring Conflict Avoidance Behaviors with Multi-Objective Reinforcement Learning in Multi-Agent Systems

2018 ◽  
Vol 2018 (0) ◽  
pp. 2P2-F15
Author(s):  
Kazuaki YAMADA
Keyword(s):  
Reinforcement Learning ◽  
Conflict Avoidance ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Multi Objective ◽  
Avoidance Behaviors ◽  
Multi Agent

scholarly journals Velocity Obstacles and Emergent Rules-of-the-Air for Autonomous Drone Traffic Management

2021 ◽  
Author(s):  
William Bonnell ◽  
R. Eddie Wilson
Keyword(s):  
Traffic Management ◽  
Swarm Robotics ◽  
Mean Transit Time ◽  
Conflict Avoidance ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Avoidance Behaviors ◽  
Multi Agent ◽  
The Mean ◽  
The Impact

As the use of unmanned aerial vehicles (UAVs) becomes ever more widespread there is a growing need to develop traffic management and flight rules, in particular for autonomous UAVs or where the predicted traffic densities far exceed those of traditional manned aviation. Inspired by the current rules of the air and multi-agent systems (e.g., pedestrians and swarm robotics) we outline a set of flight rules for autonomous UAVs that consist of waypoint following and conflict avoidance schemes. These flight rules are then explored in small,pairwise simulations and thus refined to allow a UAV to choose from three potential avoidance behaviors based on it and its neighbors velocities and positions. Finally we compare the original and modified flight rules in larger scale simulations modelling two streams of UAV traffic crossing at a point. We show that the modified rules significantly reduce the mean transit time by reducing the impact of UAVs avoiding other UAVs from the same stream.

scholarly journals Velocity Obstacles and Emergent Rules-of-the-Air for Autonomous Drone Traffic Management

2021 ◽  
Author(s):  
William Bonnell ◽  
R. Eddie Wilson
Keyword(s):  
Traffic Management ◽  
Swarm Robotics ◽  
Mean Transit Time ◽  
Conflict Avoidance ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Avoidance Behaviors ◽  
Multi Agent ◽  
The Mean ◽  
The Impact

As the use of unmanned aerial vehicles (UAVs) becomes ever more widespread there is a growing need to develop traffic management and flight rules, in particular for autonomous UAVs or where the predicted traffic densities far exceed those of traditional manned aviation. Inspired by the current rules of the air and multi-agent systems (e.g., pedestrians and swarm robotics) we outline a set of flight rules for autonomous UAVs that consist of waypoint following and conflict avoidance schemes. These flight rules are then explored in small,pairwise simulations and thus refined to allow a UAV to choose from three potential avoidance behaviors based on it and its neighbors velocities and positions. Finally we compare the original and modified flight rules in larger scale simulations modelling two streams of UAV traffic crossing at a point. We show that the modified rules significantly reduce the mean transit time by reducing the impact of UAVs avoiding other UAVs from the same stream.

Sign in / Sign up

Export Citation Format

Share Document