Master Thesis: Semi-Automated Annotation for Object Detection in Confined Industrial Environments

Job description

Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future. If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match. 

 

At Volvo Autonomous Solutions (V.A.S.) we work together to realize autonomous solutions that defy conventions and push us into the future. With new business models and advanced technology, we meet and exceed customer expectations while contributing to a society we want to live in. Diversity, great ideas, and inclusiveness unify us. Every team member matter and plays a critical role in our journey.

 

Thesis Scope & Problem Statement

Volvo Autonomous Solutions develops systems for automated hauling operations in quarries and open pit mines using Volvo trucks. The safe deployment of autonomous vehicles in confined industrial environments requires robust perception systems capable of identifying and localizing diverse objects, including rocks, trucks, cones, poles, boxes, and operating machinery. A key prerequisite for training and validating such perception systems is the availability of high-quality annotated datasets that accurately represent these complex environments.

However, manual annotation of video and image data in such contexts is prohibitively time-consuming and costly, and traditional supervised detection models struggle to generalize novel object categories without extensive retraining.

The central focus of this master's thesis is to investigate the development of a semi-automated data annotation tool tailored for object detection in mining and quarrying environments. The proposed approach will explore zero-shot object detection as a foundation, leveraging vision–language models (e.g.,OWL-ViT, CLIP) to localize and label objects without requiring large amounts of task-specific annotated data.

 

Research Objectives & Tasks

 

The work may include:

·  Develop a semi-automated annotation framework that combines zero-shot detection and supervised models for industrial datasets.
·  Evaluate the detection performance of zero-shot models (e.g., OWL-ViT, CLIP) against supervised baselines ( like YOLOv8/YOLO11).
·  Implement a proof-of-concept pipeline for generating training datasets using zero-shot methods, followed by refinement via human-in-the-loop (HITL) annotation.
·  Investigate the contribution of semi-automated annotations to the V&V of perception systems for autonomous vehicles (scope permitting).

 

Who Are We?

You will join the Verification & Validation (V&V) Virtual Driver team at V.A.S., focused on ensuring the integrity of the software stack for autonomous decision-making and control. We are 9 developers with varied backgrounds and seniority, all centered around robust V&V practices. The environment is friendly and helpful, with both in‑office development and in‑vehicle testing.

 

Who Are You?

You are a final-year student with a strong background in Computer Vision and Machine Learning and comfortable programming in Python. You should be familiar with common deep learning frameworks (e.g., PyTorch or TensorFlow) and model architectures for object detection (e.g., YOLO, R-CNN). Experience with vision-language models (e.g., CLIP, OWL-ViT) is a strong plus. Familiarity with data annotation tools and techniques is advantageous.

 

Why Join Us?

This thesis project is a unique opportunity to work at the critical intersection of autonomous perception systems and Verification & Validation (V&V) processes for autonomous vehicles.

 

You will:

·  Pioneer novel methods by combining Zero-Shot Detection (Vision-Language Models) with high-performance Supervised Models (YOLO).
·  Contribute directly to enhancing the Validation & Verification (V&V) pipeline for autonomous perception systems in challenging industrial environments.

 

You'll gain valuable, market-ready experience and collaborate with experts in the field. We look forward to receiving your application letter, academic transcript, and CV (in English).

 

Last application date: 7th November

We value your data privacy and therefore do not accept applications via mail. 

 

Who we are and what we believe in 
We are committed to shaping the future landscape of efficient, safe, and sustainable transport solutions. Fulfilling our mission creates countless career opportunities for talents across the group’s leading brands and entities.

 

Applying to this job offers you the opportunity to join Volvo Group . Every day, you will be working with some of the sharpest and most creative brains in our field to be able to leave our society in better shape for the next generation. ​We are passionate about what we do, and we thrive on teamwork. ​We are almost 100,000 people united around the world by a culture of care, inclusiveness, and empowerment. 

 

Part of Volvo Group, Volvo Autonomous Solutions accelerates the development, commercialization and sales of autonomous transport solutions, focusing on defined segments for the on- and off-road space. The combination of strong tech expertise and skilled customer solutions creates innovative transport offers never seen before. We are constantly pushing our own skills and ability to drive change in a traditional industry to meet a growing customer demand. We are now looking for innovative, committed individuals to join us in our endeavor to create customer solutions that enhance safety, flexibility and productivity.

Job Category:  Engineering

Organization:  Volvo Autonomous Solutions

Travel Required:  Occasional Travel

Requisition ID:  25929