Politecnico di Torino (logo)

Autonomous Vehicle Integration: Pedestrian Behaviour Prediction

Francesca Mangone

Autonomous Vehicle Integration: Pedestrian Behaviour Prediction.

Rel. Andrea Bottino. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2024


In the realm of automotive safety and innovation, Advanced Driver Assistance Systems (ADAS) play a pivotal role in enhancing vehicle operation and road safety. This thesis explores the development and evaluation of ADAS, with a specific emphasis on Automatic Emergency Braking (AEB) systems. The thesis delves into the challenges faced by autonomous vehicles in navigating complex urban environments designed for human drivers. Unlike humans, autonomous vehicles perceive the environment differently and rely on various sensors for perception, localization, prediction, planning, and control. Each aspect is crucial for safe and efficient autonomous driving. The focus of this work is on perfecting the Prediction task, by tackling questions related to predicting human behavior, distinguishing between normal and abnormal situations, and ethical decision-making in emergency scenarios, the research aims to enhance the predictive capabilities of autonomous vehicles. The thesis proposes a strategic foundational approach, initially focusing on a 2D environment for analyzing and understanding critical variables in pedestrian movement. The transition to the three-dimensional setting entails a thoughtful adaptation of core algorithms, all within the framework of an iterative strategy. This systematic progression not only ensures a solid foundation for algorithmic advancements but also emphasizes the commitment to enhancing accuracy and reliability incrementally. Through this approach, the thesis contributes to the ongoing evolution of autonomous vehicle development, paving the way for systems that navigate real-world scenarios with increased competence and safety.

Relators: Andrea Bottino
Academic year: 2023/24
Publication type: Electronic
Number of Pages: 70
Additional Information: Tesi secretata. Fulltext non presente
Corso di laurea: Corso di laurea magistrale in Data Science And Engineering
Classe di laurea: New organization > Master science > LM-32 - COMPUTER SYSTEMS ENGINEERING
Aziende collaboratrici: UNSPECIFIED
URI: http://webthesis.biblio.polito.it/id/eprint/31109
Modify record (reserved for operators) Modify record (reserved for operators)