A Testing Method for Multi-UAV Conflict Resolution Using Agent-Based Simulation and Multi-Objective Search
نویسندگان
چکیده
We present a new approach to testing multi-UAV conflict resolution algorithms. We have formulated the problem as a multi-objective search problem, with two objectives: finding air traffic encounters that (1) are able to reveal faults in conflict resolution algorithms, and (2) are likely to happen in the real world. Our method uses agent-based simulation and multiobjective search to automatically find encounters satisfying these objectives. It describes pairwise encounters in 3D space using a parameterized geometry representation, which allows encounters involving multiple UAVs to be generated by combining several pairwise encounters. The consequences of the encounters, given the conflict resolution algorithm, are explored using a fast-time agent-based simulator. To find encounters meeting the two objectives, we use a genetic algorithm approach. We have applied our method to test ORCA3D, a widely-cited open source multi-UAV conflict resolution algorithm, and compared our method’s performance against a plausible random testing approach. Our results show that our method can find the required encounters more efficiently than the random search. The identified safety incidents are then the starting points for understanding limitations of the conflict resolution algorithm.
منابع مشابه
Testing Method for Multi-UAV Conflict Resolution Using Agent-Based Simulation and Multi-Objective Search
متن کامل
A multi Agent System Based on Modified Shifting Bottleneck and Search Techniques for Job Shop Scheduling Problems
This paper presents a multi agent system for the job shop scheduling problems. The proposed system consists of initial scheduling agent, search agents, and schedule management agent. In initial scheduling agent, a modified Shifting Bottleneck is proposed. That is, an effective heuristic approach and can generate a good solution in a low computational effort. In search agents, a hybrid search ap...
متن کاملA Reinforcement Learning Based Uavs Air Collision Avoidance
In this paper, we propose to deal with the UAV airspace conflict resolution problem. We propose to search near optimal conflict free policies in virtue of the model-based reinforcement learning. We first analyze the UAV airspace conflict problem and the basic conditions in ensuring collision-free planning, and then discuss the features that effect the optimal action. We then propose the reinfor...
متن کاملImprovement of Frequency Fluctuations in Microgrids Using an Optimized Fuzzy P-PID Controller by Modified Multi Objective Gravitational Search Algorithm
Microgrids is an new opportunity to reduce the total costs of power generation and supply the energy demands through small-scale power plants such as wind sources, photo voltaic panels, battery banks, fuel cells, etc. Like any power system in micro grid (MG), an unexpected faults or load shifting leads to frequency oscillations. Hence, this paper employs an adaptive fuzzy P-PID controller for f...
متن کاملOptimal Operation Management of Grid-connected Microgrid Using Multi-Objective Group Search Optimization Algorithm
Utilizing distributed generations (DGs) near load points has introduced the concept of microgrid. However, stochastic nature of wind and solar power generation as well as electricity load makes it necessary to utilize an energy management system (EMS) to manage hourly power of microgrid and optimally supply the demand. As a result, this paper utilizes demand response program (DRP) and battery t...
متن کامل