High Level Description

Unmanned surface vessels must navigate safely and predictably in inshore/coastal waters where encounters, crossing traffic, and narrow channels are common. To avoid collisions, the International Regulations for Preventing Collisions at Sea (COLREGs)—the maritime “rules of the road”—are applied; however, translating these rules into robust decision strategies under varying traffic and sensor conditions is challenging. By generating synthetic training data in simulated scenarios, a model can learn COLREG-compliant behaviors from inputs such as vessel type, position, course, speed, and size, enabling path planning that balances safety and efficiency.

Project Description
The work focuses on:

• Scoping a subset of COLREGs and operationalizing them into measurable
  requirements and cost functions.
• Identifying a suitable model with clearly defined inputs—vessel type, position, course,
  speed, dimensions, and relevant environmental variables—that generates a route
  represented as a series of waypoints for a limited segment.
• Specifying and implementing simulations of diverse traffic situations to generate
  synthetic training and test data.
• Training the model and verifying it in a simulated environment against high-level
  metrics for safety, efficiency, and rule compliance.
• Evaluating performance in a real or semi-real environment, where feasible.

Depending on progress, the work may be extended to cover additional COLREG cases,
include handling of sensor uncertainty, and analyse transferability from simulation to reality.

Who are we looking for?

Master’s-level engineering students in areas such as computer science, engineering physics, robotics, or similar, with an interest in AI, machine learning, control engineering, and autonomous systems.

An Exciting Journey with Knightec Group
Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe’s leading strategic partner in product and digital service development. With a unique combination of cross-functional expertise and a holistic business understanding, we help our clients realize their strategies – from idea to complete solution.

Practical Information
This is a Thesis position, located at our office in Umeå or Örnsköldsvik. Start date is in January 2026.

Please submit your application as soon as possible, but no later than 2025-11-14. If you have any questions, you are welcome to contact Robert Nazaretyan. Note that due to GDPR, we only accept applications through our careers page.