Master Thesis Project 30hp - Deterministic principles for sampling-based motion planning

Introduction
Thesis work is an excellent way to get closer to Scania and build relationships for the future. Many of today's employees began their Scania career with their degree project.

Background
Scania is now undergoing a transformation from being a supplier of trucks, buses, and engines to a supplier of complete and sustainable transport solutions. One of the target products is autonomous trucks for the mining industry.

An autonomous truck consists of several hardware and software modules. One of the backbone software is path planning, which determines where and how a truck should move to reach its destination. Path planning has been extensively researched and developed in Scania. In robotics literature, path planning is a well-known topic. Nonetheless, developing a suitable solution for a specific system is a non-trivial problem. Your task is to perform development, examination, and verification of a path planning problem for Scania’s autonomous trucks.

Job description
Scania's sampling-based path planner is designed for mining environments and should account for interactions with other autonomous and manual agents. Being an adaptable, predictable and reliable planner poses several challenges. The optimal path provided does not contain restrictions necessary to enforce well defined behaviour in interactions.

Adding planning principles to a sampling-based path planner has been explored previously using adaptations of the sampling strategy. However, a sampling strategy will not guarantee that the principles are followed. Analysing how well the principles are followed is not a trivial problem especially when considering a dynamic, semi-defined environment, where the optimal path is not known and differs depending on the situation.

Planning principles can be viewed as a form of traffic rules on an open area. Common planning principles in a mining environment are:

• Which side to approach a manually equipped mining vehicle, e.g., loader.
• Always finishing a maneuver by reversing a set distance.
• Give way instead of crossing path with another vehicle even if crossing is the optimal solution.

Objective
The purpose of this thesis is to derive, prove and apply suitable planning principles on RRT* for Scania autonomous trucks. The final solution should include methods for enforcing planning strategies and verifying the performance of a sampling-based motion planner towards the planning strategies. There will be opportunities for real-word verification during the thesis.

Education

• Master student in Computer Science, Engineering Physics, or similar.
• Knowledge in Motion Planning, Motion Control, and Search Algorithms.
• Basic knowledge in C++.
• Good communication skills in English.

Number of students: 1

Time: 20 weeks (VT25) full time 40 hours per week

Start date: Jan 2025 or according to agreement

Credits: 30hp

Contact persons and supervisors
Ofa Ismail, Development Engineer, EEADM, Scania CV AB +46700898778  ofa.ismail@scania.com

Application:
Your application must include a CV, personal letter and transcript of grades

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.