Master Thesis within Computer Vision for Perception and Localization in Autonomous Navigation

Last date to apply:

22 October 2026

Master’s Thesis: Computer Vision for Perception and Localization in Autonomous Floor Grinding 

 

We are looking for one or two master’s students with an interest in robotics and computer vision to conduct their thesis project with the Floor Grinding team at Husqvarna Construction in Jonsered, Sweden. 

Background 

Autonomous floor grinders must operate reliably in large and challenging indoor environments. To follow planned grinding paths, achieve consistent surface coverage, and interact safely with their surroundings, the machines require accurate information about their own motion and the surrounding environment. 

Existing systems may use sensors such as LiDAR, wheel odometry, and inertial measurement units. However, industrial environments can present difficult conditions, including large open areas, uniform concrete floors, plain walls, changing surroundings, moving equipment, dust, vibration, limited visual texture, and varying illumination. Under these conditions, individual sensors may provide incomplete or uncertain information. 

Computer vision could provide additional information that complements the existing sensor system. One possible direction is visual SLAM, or vision-based simultaneous localization and mapping, in which camera data is used to estimate the machine’s motion while simultaneously building or updating a representation of its surroundings. Visual SLAM could be used independently or combined with LiDAR, IMU, and wheel odometry in a multi-sensor fusion solution. 

Other possible applications of computer vision include: 

• Visual odometry and motion estimation 

• Detection of moving, temporary, or unsuitable reference objects 

• Recognition of environmental features and landmarks 

• Estimation of sensor alignment and machine parameters 

• Detection of floor boundaries, obstacles, and relevant work-area characteristics 

• Improved sensor fusion and confidence estimation 

The central question is how camera-based perception can complement the machine’s existing sensors and improve its ability to localize itself and understand its operating environment. 

. 

 

The objective 

The objective of this thesis is to investigate how computer vision can improve the perception, localization, and autonomous capabilities of floor-grinding machines. 

 

Based on a review of the application, available sensors, and relevant computer-vision methods, the students will identify and select a promising use case. Possible directions include visual SLAM, visual odometry, vision-assisted localization, environmental understanding, object detection, sensor calibration, and multi-sensor fusion. 

 

The selected approach will be implemented and evaluated using suitable data, experiments and a prototype system installed in a floor grinding machine. The goal is to assess both its potential benefits and its practical limitations in realistic floor-grinding environments. 

 

The solution should account for application-specific constraints such as dust, vibration, motion blur, changing illumination, limited visual texture, available computing resources, and the need to operate across different indoor environments. 

  

Your skills and background   

• Currently studying towards a master’s degree in Automation and Mechatronics, Robotics, Computer Science, Engineering Physics, Electrical Engineering, or a related field 

• Interest in computer vision, autonomous systems, localization, SLAM, or sensor fusion 

• The thesis is suitable for one or two students 
   

The thesis will include work such as 

• Study the autonomous floor-grinding application and identify challenges where visual information could provide value. 

• Review relevant computer-vision methods, including visual SLAM, visual odometry, perception, and multi-sensor fusion. 

• Analyse available sensors, computing resources, data, and practical environmental constraints. 

• Investigate whether visual SLAM or another vision-based approach could complement LiDAR, IMU, and wheel odometry. 

• Define evaluation criteria and select a feasible computer-vision use case in dialogue with Husqvarna. 

• Develop and implement a prototype based on the selected approach. 

• Test and evaluate the solution under representative conditions. 

• Compare the proposed approach with existing sensor information or suitable baseline methods. 

• Document the results, identified limitations, and recommendations for further development. 

 
 

How to apply

 
Please submit your application, including your CV, cover letter, and transcript of grades, as soon as possible. Due to GDPR, we do not accept applications by email.  

 

The thesis project is expected to start in early 2027 and continue throughout the spring semester of 2027. 

 

For questions regarding the thesis project please contact:   

Antonio Bogdanovic, +46 706 475 012, Antonio.Bogdanovic@husqvarnagroup.com 

 

Read about Husqvarna Group here:   
https://www.husqvarnagroup.com/    

 

Husqvarna Group is a world-leading producer of outdoor power products for garden, park and forest care. Products include chainsaws, trimmers, robotic lawn mowers and ride-on lawn mowers. The Group is also the European leader in garden watering products and a world leader in cutting equipment and diamond tools for the construction and stone industries.