PORTALE DELLA DIDATTICA

Ricerca CERCA
  KEYWORD

Automated Valet Parking policies: from telecontrol to ego-based approach.

keywords AUTOMATED DRIVING SYSTEMS, AUTONOMOUS VEHICLES, MODEL PREDICTIVE CONTROL

Reference persons MASSIMO CANALE

External reference persons Ing. P. Borodani (Centro Ricerche Fiat / Stellantis)

Description Any vehicle can be partially or fully remote-controlled or can drive quasi autonomously with minimal information by the infrastructure, or even without it (autonomously).
The main topic of this thesis is concerned with SAE Level 4 Automated Driving control in reserved parking areas.
Operational Design Domain (ODD) is limited on: low speed maneuver (< 15 km/h), structured environment (vehicle reserved area), I2V communication with specialized infrastructure.
The vehicle considered is provided with full sensor configuration (camera, radar, lidar, …) to cover the “worst” case, the ego-based approach, i.e., minimal information by the infrastructure.
In a previous PoliTo-CRF collaboration, a complete control system based on Model Predictive Control (MPC) and Artificial Potential Field (APF) techniques was developed for the ego-approach in some reserved parking areas. APF approach, where the environment is represented by the combination of different fields, enables the MPC design to generate an optimal and safe path, given by the minimum energy trajectory over time.
In this thesis, the focus will be mainly on the flexibility: different degrees of responsibility / autonomy & different configurations of vehicle sensors, actuators, infrastructure, utilizing the incapsulated control architecture above mentioned, that offers great adaptability for such scenarios and configurations.

Required skills Solid background in the field of Automatic Control including advanced methodology such as Model Predictive Control. Furthermore, deep expertise of MatLab programming and Simulink environment is required. Finally, basics of mechanical modeling of ground vehicles and automated driving tasks are needed as additional specific knowledge.

Notes Candidates having at most two exams left are selected based on CV and interview.


Deadline 31/12/2023      PROPONI LA TUA CANDIDATURA