We are Zeekr Technology Europe. Powered by engineers and creative minds from all over the world. Located in Gothenburg, Sweden, one of the leading mobility innovation grounds worldwide. Established in 2013 as CEVT and began with the mission to create a revolutionary modular vehicle architecture, CMA. As of 2024, CEVT is now Zeekr Technology Europe, signaling our belonging within Zeekr. Delivering intelligent, sustainable, and user centric technology and software for tomorrow's electric mobility today.

Project Description: 

Reversing with a trailer is a well-known pain point for drivers and a frequent cause of minor collisions and jackknife incidents. Trailer Reverse Assistance (TRA) features depend critically on accurate real-time estimation of the trailer–vehicle articulation (hitch) angle. Current solutions vary widely, from direct sensing at the hitch to camera-based or kinematics-based estimators, each with trade-offs in accuracy, compute cost, user setup burden, and robustness to weather and trailer variability.

Winter conditions (snow, slush, salt, low sun angle) challenge vision systems. Diverse trailer shapes (boat, caravan, box) test model assumptions. Cost and power limits on edge ECUs restrict compute options. A rigorous comparative evaluation and practical recommendation can speed deployment of reliable TRA and related safety functions (jackknife avoidance, trailer stability support, etc.).

Scope

This thesis surveys, implements, and benchmarks methods for estimating the trailer–vehicle articulation angle, including kinematic sensor fusion using standard vehicle signals, camera-based approaches (marker-based and marker less with lightweight vision models), short-range ultrasonic sensors, trailer-mounted IMUs, and direct hitch sensing as a reference. The work shall define qualitative performance expectations for accuracy, robustness, responsiveness, and edge feasibility, and evaluate methods across diverse trailer types and environmental conditions. A practical ground-truth and evaluation protocol shall be established, and a proof-of-concept shall be realized to demonstrate real-time operation on a representative in-vehicle platform. Methods shall be compared using a multi-criteria decision framework that balances accuracy, computational footprint, ease of deployment, and user experience, leading to a recommended solution and integration guidelines.

Objectives

• Define qualitative requirements, use cases, and constraints for hitch angle estimation to support trailer reverse assistance.
• Implement representative estimation methods (kinematic fusion, camera-based, and combined fusion) with minimal calibration and assumptions.
• Establish ground truth and evaluation protocols covering diverse trailers, environments, and maneuvers typical in Nordic conditions.

• Benchmark methods for accuracy, robustness, responsiveness, computational load, and user burden.
• Select the optimal approach using a transparent multi-criteria decision framework and provide sensitivity analysis.

Expected Outcomes

• A comparative review and taxonomy of trailer hitch angle estimation methods with practical deployment considerations.
• A curated, multi-condition dataset with synchronized vehicle signals, perception data, and reliable ground truth for benchmarking.
• A reproducible evaluation toolkit covering core metrics for accuracy, robustness, responsiveness, and resource use on edge platforms.
• Implementations of representative estimators (kinematic, camera-based, fusion) packaged for fair comparison and reuse.
• A transparent multi-criteria decision analysis recommending an approach with clear trade-offs and sensitivities.
• An edge-ready reference design and integration guidelines, including calibration, diagnostics, and user experience.
• Documented limitations, key failure modes, and prioritized recommendations for future development and validation.

Your skills and background

• Master’s degree in Automotive Engineering, Control Systems, Computer Science, or Electrical Engineering.
• Strong background in Machine Learning (ML) and classical Computer Vision (CV) for perception tasks.
• Knowledge about Vehicle dynamics, Trailer Kinematics, and State Estimation.
• Shows strong programming skills in C++ and Python for both real-time systems and research prototypes.
• Strong analytical and problem-solving skills, including statistical evaluation and error analysis.

This thesis project is for 2 students who together need to have the required skills and background. Applicants may specify a preferred partner in their cover letter.

Why you should join Zeekr Tech Eu

We are engineers, developers, and innovators from around the world. Joined together by entrepreneurship, our unique blend of global culture, and a belief in a smarter more sustainable future. At Zeekr Tech Eu we fast-track innovation and transform ideas into pioneering technology solutions, doing your master thesis here is no different. We are convinced that a thesis project is a major contribution to our innovation capabilities and long-term development. You'll have a great opportunity to use your skills and creativity to push the boundaries of what´s possible.

What happens when you apply
If this sounds interesting and you match the requirements, please don't hesitate to submit your application with a CV and cover letter. Shortlisted candidates will be contacted for an interview to further discuss the project's details and expectations. 

Supervisor:  Karthik Prasad, Expert Motion Systems, karthik.prasad@zeekrtech.eu, please contact for more information about the project

Starting date: January 2026

Last application date:  2025-11-04

Apply today. We will perform ongoing selection during the application period. We look forward to hearing from you!

Please note that due to GDPR regulations, we can only accept applications sent through the recruitment system, not via email or other channels.