Scania genomgår nu en transformation från att vara en leverantör av lastbilar, bussar och motorer till en leverantör av kompletta och hållbara transportlösningar.
A thesis project at Scania is an excellent way of making contacts for your future working life. Many of our current employees started their career with a thesis project.
Autonomous driving is a widely studied topic that has gained a lot of traction lately: there are more and more advanced driver assistance functions on the market and we will see fully autonomous vehicles on the road in the near future.
Safe navigation in urban areas is a challenging problem for self-driving vehicles.
One of the reasons why human drivers can safely navigate even under occlusions is that they augment their sensing capabilities and anticipate the need to slow down due to the potential risk of collision that arises due to unseen regions. Occlusions and limited sensor range are unavoidable limitations of self-driving vehicles, and they pose significant challenges to safely navigate among vulnerable road users.
Situational awareness is crucial for autonomous driving in urban environments. Decision problems in the real world are affected by incomplete and noisy perception and uncertain knowledge about how the world evolves over time. The goal of this thesis is to model the task of choosing safe, efficient, and goal-directed behavior for self-driving vehicles operating in uncertain and partially-known environments. The framework will enable the possibility of selecting the most effective and reliable actions while navigating in occluded environments, minimizing the collision risk with other vehicles and maximizing the sensor coverage.
The assignment is divided into the following sub-tasks: 1. Evaluate current state of the art; 2. Provide an estimation and representation of the occluded areas in the environment; 3. Propose and implement a method to track objects passing through occluded areas; 4. Propose and implement a method to represent objects passing through occluded areas without previous observations; 5. Propose and implement an association method to handle the re-observation of the tracked object; 6. Test the work in simulation and/or in real experiments using research vehicles;
Master (civilingenjör) in computer science, engineering physics, electrical engineering, or applied mathematics, preferably with specialization in artificial intelligence algorithms, control theory, optimal control or optimization. Knowledge of programming, predictive modeling, and reinforcement learning are a plus.
Number of students: 1-2
Start date: January 2019
Estimated time needed: 20 weeks
Contact persons and supervisors:
Laura Dal Col, Development Engineer in Autonomous Motion, email@example.com, 08 - 553 851 20
Christoffer Norén, Senior Engineer in Autonomous Motion, Christoffer.firstname.lastname@example.org, 08 - 553 811 48
Enclose CV, cover letter and transcript of records