KEYWORD |
Multi-Application Task Allocation for Drone Networks
keywords DRONE, MULTI AGENT SYSTEM, UAV
Reference persons STEFANO PRIMATESTA
External reference persons Marco Rinaldi (marco_rinaldi@polito.it)
Research Groups 08- Dinamica, controllo e simulazione del volo
Description Unmanned Aerial Vehicles (UAVs), commonly known as drones, are being seen as the most promising type of autonomous vehicles in the context of Intelligent Transportation System (ITS) technology. A key enabling factor for the current development of ITS technology based on autonomous vehicles is the task allocation architecture. This approach allows tasks to be efficiently assigned to robots of a Multi-Agent System (MAS), taking into account both the robots’ capabilities and service requirements. There are different types of algorithms that are employed in state-of-the-art drone-based ITSs, including auction (market)-based approaches, game-theory-based algorithms, optimization-based algorithms, and Machine Learning (ML) techniques. One of the key aspects of task allocation algorithms is that, because of their different features, they must be carefully designed depending on both the application’s characteristics and the goal of the task allocation itself. The objective of this thesis is to propose a generalized task allocation framework applicable to the problem of allocating different tasks (with different requirements) to different UAVs (with different capabilities).
The expected outcome of the thesis is defined as follows:
- Design of a generalized (multi-goal) task allocation architecture (possibly merging different types of algorithms) that can efficiently allocate different tasks to a heterogeneous fleet of UAVs.
- Validation of the proposed approach by means of simulation results with a well-defined use case that includes a set of drones that has to carry out different tasks (e.g., parcel delivery, inspection, traffic monitoring, etc.) within a certain time frame.
See also multi-application task allocation.pdf
Required skills Matlab, Python (optional), C++ (optional) Programming Skills
Deadline 20/12/2025
PROPONI LA TUA CANDIDATURA