Maria Acciavatti
Multi-camera Perception and Control for Human-aware Robot Navigation.
Rel. Marcello Chiaberge, Mauro Martini. Politecnico di Torino, Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica), 2026
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (20MB) | Preview |
Abstract
Socially aware navigation has become a key requirement for autonomous service robots operating in human-populated environments, as they are increasingly expected to navigate naturally and safely among people. Achieving this objective requires the integration of local motion planning strategies with reliable human perception. Navigation and perception are often investigated independently, although they are intrinsically connected. Indeed, the robot’s socially compliant behavior depends on the robustness of the perception system capable of providing accurate and temporally consistent information about surrounding people. In particular, accurate human perception is essential for computing the social costs used by local planners to evaluate robot-human interactions and select the optimal trajectory for human-aware navigation.
Motivated by this close interdependence, this thesis jointly addresses, within a robotic platform based on the Robot Operating System 2 (ROS 2), two complementary contributions: the improvement of social navigation capabilities and the development of a global perception system
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
