Tesi etd-09242024-151609
Link copiato negli appunti
Tipo di tesi
Dottorato
Autore
MUGNAI, MICHAEL
URN
etd-09242024-151609
Titolo
Goal-directed interactive trajectory planning for Autonomous Mobile Robots
Settore scientifico disciplinare
ING-INF/04
Corso di studi
Istituto di Tecnologie della Comunicazione, dell'Informazione e della Percezione - PHD IN EMERGING DIGITAL TECHNOLOGIES
Commissione
relatore Prof. AVIZZANO, CARLO ALBERTO
Presidente Prof. GABICCINI, MARCO
Membro Prof.ssa DONZELLA, VALENTINA
Presidente Prof. GABICCINI, MARCO
Membro Prof.ssa DONZELLA, VALENTINA
Parole chiave
- Autonomous Racing
- Autonomous Vehicles
- Coverage Planning
- GNSS-denied Environments
- Multi-stage Trajectory Planner
- Nonlinear Model Predictive Control (NMPC)
- Precision Agriculture
- Receding Horizon Planner
- Trajectory Planning
- Unmanned Aerial Vehicles (UAVs)
Data inizio appello
31/01/2025;
Disponibilità
parziale
Riassunto analitico
This thesis presents a comprehensive exploration of autonomous vehicle technologies across three distinct domains: racing vehicles, unmanned aerial vehicles (UAVs), and agricultural machinery. It emphasizes the development and application of advanced control systems and planning algorithms to achieve optimal performance in complex, real-time environments.
In the context of racing, the work addresses the challenges of high-speed control and optimization, leveraging Nonlinear Model Predictive Control (NMPC) to enhance lap times while accounting for disturbances and dynamic constraints. In UAV applications, the focus shifts to autonomous navigation in environments without Global Navigation Satellite Systems (GNSS), where trajectory planning and robust localization are critical for mission success. Finally, the work delves into precision agriculture, introducing innovative coverage planning techniques that allow autonomous agents to efficiently navigate with bulky vehicles and perform tasks in constrained environments like vineyards.
Overall, the work demonstrates the versatility of autonomous systems in solving diverse real-world challenges by integrating model-based control, optimization, and planning approaches, pushing the boundaries of what autonomous agents can achieve in terms of performance, adaptability, and robustness across various industries.
In the context of racing, the work addresses the challenges of high-speed control and optimization, leveraging Nonlinear Model Predictive Control (NMPC) to enhance lap times while accounting for disturbances and dynamic constraints. In UAV applications, the focus shifts to autonomous navigation in environments without Global Navigation Satellite Systems (GNSS), where trajectory planning and robust localization are critical for mission success. Finally, the work delves into precision agriculture, introducing innovative coverage planning techniques that allow autonomous agents to efficiently navigate with bulky vehicles and perform tasks in constrained environments like vineyards.
Overall, the work demonstrates the versatility of autonomous systems in solving diverse real-world challenges by integrating model-based control, optimization, and planning approaches, pushing the boundaries of what autonomous agents can achieve in terms of performance, adaptability, and robustness across various industries.
File
| Nome file | Dimensione |
|---|---|
Ci sono 1 file riservati su richiesta dell'autore. |
|