Thesis work - AI-supported stand-alone Dead Reckoning
- Application Deadline: Jan. 14, 2024
- Linköping
- Hybrid
Background
Dead Reckoning (DR) is a technology to determine a unit's absolute position from an outdated absolute position and recent sensor data. A common automotive use case is to determine the position of a vehicle while driving in a tunnel where there is no GNSS (e.g. GPS) reception. Typically this has been done using a Kalman filter, wheel tick data, steering angle data, accelerometer and gyro This works well but requires a substantial integration and tuning work for each vehicle model.
Recent research ( GitHub - mbrossar/ai-imu-dr: AI-IMU Dead-Reckoning ) has shown an opportunity to remove the dependency on vehicle specific data and models by combining the Kalman filter with a neural network.
Goal
A dead reckoning solution for ACTIA's ACU6 platform which requires minimal integration and tuning, therefore applicable also for low volume applications.
This thesis will be a first step towards that goal.
Scope:
Note that the later steps below are depending on previous steps and may not be possible at all. Therefore a first project should aim only for step 1.
Step 1 - Apply the research algorithms to ACTIA hardware
Investigate whether the referenced algorithms can produce sufficient quality output also with the sensors of a mass produced telematics unit (ACTIA's ACU6 unit). The work will include
- Writing data collection software in the ACU6 and/or a connected PC
- Connecting a reference GNSS receiver (RTK supported) for collecting "true position"
- Collecting real drive data
- Applying (off-line) the proposed algorithms
- If needed, investigate adaptations of the algorithms to improve the output.
Repeat the analysis with a high quality automotive GNSS receiver using RTK technology (already available in some vehicles)
Needed skills: Good understanding of Kalman filtering and neural networks. Basic programming (Python, shell scripting). Systematic and scientific mindset.
Work with great people
Skills & Requirements
Who are you?
You are an engineering student with good understand of Kalman filtering and neural networks. You have at least basic programming skills in Python and shell scripting. Further more, in order to really ace this thesis, you will need a systematic and scientific mindset.
Great Place to Work
Full-spectrum development. From SW to HW
In-house production. Full insight and control
Workplace flexibility. Hybrid work set-up
High-profile clients – global well-known brands
Company health care and health insurance
Flat organization. Collaborate and innovate freely
About the company
Welcome to the technology leader in connectivity
ACTIA’s products are used in millions of applications worldwide, mainly in the automotive industry. We are a part of the global ACTIA Group, but our workplace culture is characterized by the closeness, innovativeness and flexibility of a smaller company. As an employee at ACTIA, you have the opportunity to work with world-leading technology in the entire chain from software, to hardware, production and ancillary services. It provides a valuable and exciting overall perspective where you can see every technical detail develop together with your colleagues. We are looking for everybody who is attracted by challenging, forefront technology, and who have high expectations for both your own and your workplace's development.
Our Core ValuesHidden section
CareThe wellbeing of people and environment is important to us and we make long-term sustainable choices.
CourageWe empower each other and seek opportunities to develop both individuals and as a company.
DedicationWe take a genuine interest in our client’s business and strive for excellence together.
TrustWe create safe and efficient technology that both our customers and society can rely on.
Oscar Bentevik Holm | Contact Person
Powered by
