Skip to content

Commit

Permalink
Deployed 173d9b2 to main with MkDocs 1.4.3 and mike 2.2.0.dev0
Browse files Browse the repository at this point in the history
  • Loading branch information
github-actions committed Jan 11, 2025
1 parent 0e0f2e8 commit 6736828
Show file tree
Hide file tree
Showing 8 changed files with 320 additions and 320 deletions.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

620 changes: 310 additions & 310 deletions main/sitemap.xml

Large diffs are not rendered by default.

Binary file modified main/sitemap.xml.gz
Binary file not shown.
Original file line number Diff line number Diff line change
Expand Up @@ -7662,7 +7662,7 @@ <h4 id="test-dataset-map">Test Dataset &amp; Map<a class="headerlink" href="#tes
<p><span style="color:green"><strong>NOTE !</strong></span> <br>
Since there was no velocity source coming from the vehicle during all these tests, the twist message coming from <abbr title="Global Navigation Satellite System">GNSS</abbr>/INS was given to ekf_localizer as the linear&amp;angular velocity source.
In order to understand whether this increases the error in cases where the <abbr title="Global Navigation Satellite System">GNSS</abbr>/INS error increases in the tunnel and how it affects the system, localization in the tunnel was tested by giving only the pose from the NDT, without giving this velocity to ekf_localizer. <br>
The video of this test is <a href="https://www.youtube.com/watch?v=ajgedIwwuaM">here</a>.
The video of this test is <a href="https://youtu.be/6On130bjQUY?si=vumtij7a66WBIV3z">here</a>.
As seen in the video, when velocity is not given, localization in the tunnel deteriorates more quickly.
It is also predicted that if the <abbr title="Inertial Measurement Unit">IMU</abbr> Twist message combined (/localization/twist_estimator/twist_with_covariance) with the linear velocity from the vehicle is given instead of the <abbr title="Global Navigation Satellite System">GNSS</abbr>/INS Twist message, the performance in the tunnel will increase. However, this test cannot be done with the current data.</p>
</blockquote>
Expand Down Expand Up @@ -7767,7 +7767,7 @@ <h5 id="run-rosbag_1">Run Rosbag<a class="headerlink" href="#run-rosbag_1" title
<h3 id="test-results">Test Results<a class="headerlink" href="#test-results" title="Permanent link">#</a></h3>
<h4 id="test-1-simple-test-of-localization">Test 1: Simple Test of Localization<a class="headerlink" href="#test-1-simple-test-of-localization" title="Permanent link">#</a></h4>
<p>Simply put, how localization works in an urban environment was tested and the results were recorded on video.
Here is the <a href="https://youtu.be/Bk4Oyk6FOg0?t=6">test video</a>.
Here is the <a href="https://youtu.be/DQsk3rY7NjY?si=NkJYIZoPd6HqLIHp">test video</a>.
<a href='https://youtu.be/Bk4Oyk6FOg0?t=6"'><img src="https://github.com/user-attachments/assets/e0f7edbf-0596-4806-8dcd-b4156584e4c0" width="60%"></a></p>
<p>We can see from video that there is a localization error in the longitudinal axis along the Eurasia tunnel. As expected, NDT based localization does not work properly here. However, since the NDT score cannot detect the distortion here, localization is not completely broken until the end of the tunnel. Localization is completely broken at the exit of the tunnel. I re-initialized the localization after vehicle exit the tunnel.</p>
<p>From this point on, we move on to the bridge scenario. This is one of the bridges connecting the Bosphorus and was the longest bridge on our route. Here too, we thought that NDT-based localization might be disrupted. However, I did not observe any disruption.</p>
Expand All @@ -7781,7 +7781,7 @@ <h4 id="test-2-comparing-results-with-ground-truth">Test 2: Comparing Results wi
<p>NDT Score (Nearest Voxel Transformation Likelihood) Threshold = 2.3</p>
<p>2.) Compare with Ground Truth</p>
<p>Ground Truth : In these tests, the post-processed <abbr title="Global Navigation Satellite System">GNSS</abbr> / INS data was used as ground truth. Since the error of this ground truth data also decreases in the tunnel environment, it is necessary to evaluate these regions by taking into account the Ground Truth error.</p>
<p>During these tests, I compared the NDT and EKF exposures with Ground Truth and presented the results. I am sharing the test results below as png. However, if you want to examine this data in more detail, I have created an executable file for you to visualize and take a closer look at. You can access this executable file from <a href="https://drive.google.com/drive/folders/145QXl6wfV7IB9NS-PzFQtsNnxnAn6a9o?usp=sharing">here</a>. Currently there is only a version that works on Ubuntu at this link, but I plan to add it for Windows as well.
<p>During these tests, I compared the NDT and EKF exposures with Ground Truth and presented the results. I am sharing the test results below as png. However, if you want to examine this data in more detail, I have created an executable file for you to visualize and take a closer look at. You can access this executable file from <a href="https://drive.google.com/drive/folders/1ges_2q8qljgLfwjZbv2Bn35Rv5awhd_U?usp=sharing">here</a>. Currently there is only a version that works on Ubuntu at this link, but I plan to add it for Windows as well.
You need to follow these steps:</p>
<div class="highlight"><pre><span></span><code><span class="nb">cd</span><span class="w"> </span>/your/path/show_evaluation_ubuntu
./pose_main
Expand Down

0 comments on commit 6736828

Please sign in to comment.