diff --git a/README.md b/README.md index e566740..957a6c8 100644 --- a/README.md +++ b/README.md @@ -44,7 +44,7 @@ You can preview your changes by running the site locally. To do this, simply run docker compose build docker compose up ``` -Note that you only have to build the docker image once. After that, you can simply run `docker compose up` to serve the site locally. You can then preview the site at [http://http://0.0.0.0:8080/\](http://http://0.0.0.0:8080/). +Note that you only have to build the docker image once. After that, you can simply run `docker compose up` to serve the site locally. You can then preview the site at [http://0.0.0.0:8080/\](http://0.0.0.0:8080/). ### Step 5 Make a pull-request to this repository. Once the pull-request is merged, the blog post will be automatically published at [research.zenseact.com](https://research.zenseact.com). diff --git a/_data/authors.yml b/_data/authors.yml index 464aed9..9bc6493 100644 --- a/_data/authors.yml +++ b/_data/authors.yml @@ -332,3 +332,18 @@ Ohlsson: Persson: firstname: ["Daniel", "D.", "D. P.", "Daniel Persson"] org: Chalmers University of Technology +Yuchuan: + firstname: ["Yuchuan", "Y.", "Y. J.", "Yuchuan Jin"] + org: Zenseact +Theodor: + firstname: ["Theodor", "T.", "T. S.", "Theodor Stenhammar"] + org: Zenseact +David: + firstname: ["David", "D.", "D. B.", "David Bejmer"] + org: Zenseact +Axel: + firstname: ["Axel", "A.", "A. B.", "Axel Beauvisage"] + org: Zenseact +Yuxuan: + firstname: ["Yuxuan", "Y.", "Y. X.", "Yuxuan Xia"] + org: Zenseact \ No newline at end of file diff --git a/_publications/towards-accurate-ego-lane/towards-accurate-ego-lane.md b/_publications/towards-accurate-ego-lane/towards-accurate-ego-lane.md new file mode 100644 index 0000000..4c158c6 --- /dev/null +++ b/_publications/towards-accurate-ego-lane/towards-accurate-ego-lane.md @@ -0,0 +1,30 @@ +--- +layout: publication +permalink: /publications/towards-accurate-ego-lane/ +title: "Towards Accurate Ego-lane Identification with Early Time Series Classification" +venue: ARXIV +authors: + - Yuchuan + - Theodor + - David + - Axel + - Yuxuan + - Fu +arxiv: https://arxiv.org/abs/2405.17270 +date: 2024-05-27 00:00:00 +0000 +--- + +# Abstract +Accurate and timely determination of a vehicle's current lane within a map is a critical task in autonomous driving systems. This paper utilizes an Early Time Series Classification (ETSC) method to achieve precise and rapid ego-lane identification in real-world driving data. The method begins by assessing the similarities between map and lane markings perceived by the vehicle's camera using measurement model quality metrics. These metrics are then fed into a selected ETSC method, comprising a probabilistic classifier and a tailored trigger function, optimized via multi-objective optimization to strike a balance between early prediction and accuracy. Our solution has been evaluated on a comprehensive dataset consisting of 114 hours of real-world traffic data, collected across 5 different countries by our test vehicles. Results show that by leveraging road lane-marking geometry and lane-marking type derived solely from a camera, our solution achieves an impressive accuracy of 99.6%, with an average prediction time of only 0.84 seconds. + +# BibTeX +```bibtex +@misc{jin2024accurate, + title={Towards Accurate Ego-lane Identification with Early Time Series Classification}, + author={Yuchuan Jin and Theodor Stenhammar and David Bejmer and Axel Beauvisage and Yuxuan Xia and Junsheng Fu}, + year={2024}, + eprint={2405.17270}, + archivePrefix={arXiv}, + primaryClass={eess.SP} +} +``` \ No newline at end of file