Research: completed projects

This is a list of selected project which Dr Hendeby has been PI for.

The Map to Everywhere: Building HD Maps for Autonomous Driving Using Crowdsourcing

In collaboration with Zenseact.

Crowdsourced mapping, facilitated by low-cost sensors installed on vehicles that frequently travel on the roads, has emerged as an economically efficient and highly scalable solution for creating high-definition (HD) maps, which enable self-driving vehicles to perform precise localization and make informed decisions. This project aims to develop efficient and accurate crowdsourced mapping algorithms for autonomous driving through the collaboration of academia and industry.

This project contains three main work packages. First, we will develop mathematical frameworks for multi-robot simultaneous localization and mapping (SLAM) based on finite set statistics. Second, we will tailor the developed multi-robot SLAM algorithms to crowdsourced mapping. Lastly, we will verify the effectiveness of the developed crowdsourced mapping algorithms using both synthetic and real-world data. Throughout the project, the crowdsourced data collected by Zenseact’s production vehicles will guide the algorithm development. In addition, by leveraging the real-world data, we will also explore how to best combine model-based and data-driven methods.

This project will contribute to the academic research on crowdsourced mapping (and multi-robot SLAM in general) by providing new theories and algorithms, advancing the state-of-the-art. This project will also benefit Zenseact (and the Swedish automotive industry in general) by offering an economically efficient solution for creating its own up-to-date HD maps, giving it a competitive edge in the market.

Funding from WASP for one PostDoc (two years), Yuxuan Xia, Zenseact.

Multi-Sensor Image-Based Navigation

Aerial navigation in GNSS contested environments is a challenge for both manned and unmanned aircraft. This research project aims to study and develop technologies and algorithms to address the problem of aerial navigation without relying on GNSS, focusing in image-based navigation with multi-sensor fusion in order to get a precise localization of the aircraft. The proposed application to be used in this research project is related to an aerial transport of goods in a remote area (challenging environment and low risk area), using real time image processing and another embedded sensor processing to improve the aircraft localization, without using GNSS data. This application has a dual use (both military and civil).

Funding from Vinnova for one PostDoc, Jeong Min Kang.

Learning To Time Update

Classical methods for filtering are married with machine learning methodology to provide better tracking and navigation solutions. Focus is on addressing the time update bottle neck in filtering, due to poor signal- to-noise (SNR), which has appeared as a result of the high requirements of situational awareness posed by autonomous systems. The goal is to be able to provide high quality filtering solutions, for tracking and navigation, as a result of being able to learn more accurate motion models.

Funding from WASP for one PhD student, Anton Kullberg.

Applied Research Platform for Sensor Fusion (CENIIT Project 17.2)

The aim of this project is to create a research group that using probabilistic learning methods addresses the needs introduced by the surge of less expensive sensors, and in the process to complement the existing group with competence in computer science and more knowledge of hardware. The goal of the proposal is to perform agile development of theory for emerging applications with early demonstrators and active involvement of students.

Funding from ZENITH.