Pre doctoral Fellowship linked to the project “Heterogeneous Advances in Machine Imitation Learning for Training Orchestrated Navigation (Hamilton)”

CALL FPI93-CVC 

The CVC offers one pre-doctoral fellowship linked to the project “Heterogeneous Advances in Machine Imitation Learning for Training Orchestrated Navigation (Hamilton)” with reference PID2024-162555OB-I00 funded by MICIU/AEI /10.13039/501100011033 and by FEDER, UE. 

This call is funded by the AEI and the ESF+ and the definitive award of predoctoral contracts for the training of doctors, following the indications of article 12 of the call “Proyectos de Generación de Conocimiento 2024.  

• Duration of the fellowship: 4 years 
• Expected start date: Between 1 December 2025 to 1 May 2026. 
• Selected fellows will receive a gross annual salary of €24,348.77, as established in the official terms of the public call. 

This amount includes the employee’s income tax (IRPF) and social security contributions, but excludes the employer’s contribution to social security.

In Spain, the net salary is obtained by deducting from the gross amount the corresponding income tax (IRPF) and employee social security contributions, both of which may vary annually depending on government regulations, income level, personal circumstances, and region. The resulting amount after these deductions constitutes the net salary received by the fellow.

To cover both the employee’s gross salary and the employer’s social security contributions, the host institution will receive an annual grant of €31,000, as specified in the official call.

The indicated gross salary may be updated annually in accordance with the provisions of the Collective agreement (“Estatuto del Personal Investigador Predoctoral en Formación”, Royal Decree 103/2019), and the host institution will apply any such updates as established by that regulation.

There is also an additional compensation for the end of the contract. Finally, there is a fund of 7.000 euros to pay PhD enrolment fees and for doing research stays during the fellowship.

• Specific requirements: 
  • MSc degree in: computer vision, artificial intelligence, computer science, computer engineering or related subject. 
  • We will positively consider previous background in computer vision, deep learning and/or ADAS research, as well as previous experience in research activities. 
  • Applicants are expected to be fluent in both oral and written communication in English.  
  • They should work well in a team while demonstrating initiative and autonomy. 

• To apply, please submit the following documents as a single PDF file through the online form, clearly indicating the job reference(CALL FPI93-CVC):
  • Cover letter stating accomplishments you would like to highlight 
  • Complete CV 
  • Academic transcript for the bachelor’s and master’s degrees (they should include the grade obtained in each subject).  

• Deadline: 14 December 2025.  
• On 19 December 2025 we will post in our website the resolution of this fellowship.  

Please read the complete call to know all the details of the fellowship and the evaluation process. 

Job Description
Job title	PhD fellow position linked to the project “Heterogeneous Advances in Machine Imitation Learning for Training Orchestrated Navigation (Hamilton)” with reference PID2024-162555OB-I00
Dedication	Full time, 4-year grant (annual evaluation)
Supervisors	Gabriel Villalonga Pineda and Antonio López Peña
Background	The selected candidate will work in the Computer Vision Centre (CVC), Barcelona, a research institute comprising more than 130 researchers and support staff, dedicated to computer vision research and knowledge transfer, with an excellent research production. With a strong international projection and links to the industry, the Computer Vision Centre offers an exciting environment for scientific career development. The Computer Vision Centre has a plan for expansion of its permanent research staff base and has received the “HR Excellence in Research” award as a provider and supporter of a stimulating and favourable working environment.  The successful candidate will become part of the ADAS Group, a team with over 20 years of leadership in computer vision and autonomous driving. Founded in 2002, the group pioneered research on domain adaptation, contributing major assets such as the SYNTHIA dataset and the CARLA simulator, both now international references in the field. Since 2017, the group has driven advances in end-to-end (sensorimotor) autonomous driving, developing the CIL and CIL++ models that learn directly from human driving. These models have been successfully deployed in a real VW eGolf vehicle, demonstrating robust, camera-based autonomous navigation in both the Catalan Pyrenees and on the UAB campus, where ongoing research continues. Through collaborations with major partners such as Volkswagen, Intel, and NVIDIA, the ADAS Group is internationally recognized for its contributions to AI-driven mobility and autonomous systems.
Summary of the project	HAMILTON proposal focuses on advancing vision-based sensorimotor autonomous driving (AD) models trained through driver imitation learning. The project builds upon the success of the CIL++ model, which has shown promising results in real-world AD applications. Key objectives of HAMILTON include: 1. Enhancing model training scalability through federated domain generalization and synth-to-real unsupervised domain adaptation techniques. 2. Developing automated failure analysis procedures using Large Language Models (LLMs) to identify critical scenarios and improve AD performance. 3. Creating introspective analysis methods to explain the decision-making process of sensorimotor AD models, increasing their trustworthiness. 4. Improving model architectures to incorporate learnable context-memory, prior knowledge integration, and cooperative driving capabilities while maintaining efficiency.  HAMILTON addresses major challenges in autonomous driving research, including data sharing limitations, explainability, and vehicle cooperation. It emphasizes camera-based approaches for their cost-effectiveness, reliability, and rapid technological progress, leveraging the team’s two decades of expertise in vision-based driving systems. Beyond autonomous vehicles, the project’s advances in sensorimotor imitation learning are expected to benefit a wide range of robotic applications, promoting more natural, human-like, and scalable robotic behavior.
Description of the job	The selected candidate will carry out a doctoral thesis within the framework of the HAMILTON project, contributing to research on vision-based, sensorimotor autonomous driving and imitation learning. The specific topic of the thesis will be defined according to the candidate’s background, interests, and the project’s research priorities. Possible directions include areas such as training efficiency, explainability, cooperative driving and advancements in sensorimotor model architectures. The candidate will participate in the scientific activities of the ADAS group, contributing to ongoing research and development tasks aligned with the project. They are expected to disseminate research results through publications in top-tier conferences and journals and to actively engage in the international research community in computer vision and autonomous driving.
Specific requirements	The candidate should possess a MSc degree in computer vision, artificial intelligence, computer science, computer engineering or related subject. We will positively consider previous background in computer vision, deep learning and/or ADAS research, as well as previous experience in research activities. Applicants are expected to be fluent in both oral and written communication in English. They should work well in a team while demonstrating initiative and autonomy.
Selection Committee	Gabriel Villalonga Pineda Antonio López Peña