Blog: update urls to public
This commit is contained in:
parent
fa5928c178
commit
78cc506cf8
GPG key ID:
8DE0764E1809E9FC
|
|
@ -2,7 +2,7 @@
|
|||
title: 'DuckieTown - Lab 1'
|
||||
description: "Let's get rolling!"
|
||||
pubDate: 'Jan 22 2023'
|
||||
heroImage: '../../../src/assets/duckietown/sleeping_duckies.avif'
|
||||
heroImage: '/images/duckietown/sleeping_duckies.avif'
|
||||
---
|
||||
|
||||
<p style="font-size: max(2vh, 10px); margin-top: 0; text-align: right">
|
||||
|
|
@ -132,7 +132,7 @@ in a browser. It has a live camera feed and sensor signals. Here's a dashboard
|
|||
with my bot driving forward in a straight line
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/dashboard_motors_forward.avif"
|
||||
src="/images/duckietown/dashboard_motors_forward.avif"
|
||||
alt="Motors of duckiebot driving forward, as seen from the dashboard"
|
||||
/>
|
||||
|
||||
|
|
@ -140,7 +140,7 @@ Notice how the angular speed is 0. That's since it's not turning. Below is a
|
|||
picture of it spinning in a circle, now with no forward velocity
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/dashboard_motors_spin.avif"
|
||||
src="/images/duckietown/dashboard_motors_spin.avif"
|
||||
alt="Motors of duckiebot spinning in a circle, as seen form the dashboard"
|
||||
/>
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
title: 'DuckieTown - Lab 2'
|
||||
description: "Camera and kinematics"
|
||||
pubDate: 'Feb 13 2023'
|
||||
heroImage: '../../../src/assets/duckietown/lab2/quiver_plot_sparse.avif'
|
||||
heroImage: '/images/duckietown/lab2/quiver_plot_sparse.avif'
|
||||
---
|
||||
|
||||
<!-- THIS IS THE OUTLINE, NOT VISIBLE THO KEEP IT FOR REFERENCE
|
||||
|
|
@ -136,7 +136,7 @@ instead of having to constantly modify source code.
|
|||
Here's a screenshot of the node in `rqt_graph`:
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab2/custom_publisher_and_subscriber_allinone.avif"
|
||||
src="/images/duckietown/lab2/custom_publisher_and_subscriber_allinone.avif"
|
||||
alt="Custom camera node in rqt_graph. It publishes two outgoing topics"
|
||||
/>
|
||||
|
||||
|
|
@ -152,7 +152,7 @@ Here's a screenshot of our modified topic being published (this one isn't black
|
|||
and white):
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab2/custom_published_image.avif"
|
||||
src="/images/duckietown/lab2/custom_published_image.avif"
|
||||
alt="Picture of screen with rqt_image_view streaming our topic"
|
||||
/>
|
||||
|
||||
|
|
@ -162,7 +162,7 @@ though the assignment asks for a picture of the source code... so here's a
|
|||
picture of where the link leads:
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab2/lab2_camera_node_code_screenshot.avif"
|
||||
src="/images/duckietown/lab2/lab2_camera_node_code_screenshot.avif"
|
||||
alt="Screenshot of 2 Chromium windows displaying source code"
|
||||
/>
|
||||
|
||||
|
|
@ -175,43 +175,43 @@ initial robot frame to the world frame?**
|
|||
The robot frame is always centered on the robot, so it is given by
|
||||
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math1.avif" />
|
||||
<img src="/images/duckietown/lab2/math1.avif" />
|
||||
|
||||
The initial world frame is given by
|
||||
<img src="../../../src/assets/duckietown/lab2/math2.avif" />
|
||||
<img src="/images/duckietown/lab2/math2.avif" />
|
||||
|
||||
To transform the initial world frame to the robot frame is trivial, keep the
|
||||
angle theta the same, and `x_R = 0` and `y_R = 0`. This is equivalent to this
|
||||
matrix multiplication:
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math11.avif" />
|
||||
<img src="/images/duckietown/lab2/math11.avif" />
|
||||
|
||||
To get the initial world frame from the initial robot frame,
|
||||
we keep the angle theta the same, and set `x_I = 0.32` and `y_I = 0.32`.
|
||||
This is equivalent to this matrix multiplication:
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math3.avif" />
|
||||
<img src="/images/duckietown/lab2/math3.avif" />
|
||||
|
||||
|
||||
We used the following matrix multiplication to transform between the two:
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math4.avif" />
|
||||
<img src="/images/duckietown/lab2/math4.avif" />
|
||||
|
||||
with
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math5.avif" />
|
||||
<img src="/images/duckietown/lab2/math5.avif" />
|
||||
|
||||
Then we can update the world frame by integrating the above changes in world
|
||||
frame
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math6.avif" />
|
||||
<img src="/images/duckietown/lab2/math6.avif" />
|
||||
|
||||
We also must apply the modulo of `2 * pi` to the angle theta to keep it between
|
||||
0 and `2 * pi`.
|
||||
|
||||
We note that the equation for getting the change in robot frame is given by
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math7.avif" />
|
||||
<img src="/images/duckietown/lab2/math7.avif" />
|
||||
|
||||
where `d_r` and `d_l` are the integrated displacement traveled by the right and
|
||||
left wheels and `l` is the distance between the wheels and the center of the
|
||||
|
|
@ -220,7 +220,7 @@ rotation.
|
|||
To get the integrated displacements `d_r` and `d_l`, we use the wheel encoder
|
||||
ticks formula:
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math8.avif" />
|
||||
<img src="/images/duckietown/lab2/math8.avif" />
|
||||
|
||||
where `r = 0.025` is the radius of the Duckiebot wheel and `resolution = 135`
|
||||
is the number of ticks in one rotation of the wheel.
|
||||
|
|
@ -230,11 +230,11 @@ is the number of ticks in one rotation of the wheel.
|
|||
To update the angle theta that our DuckieBot has traveled, we used the matrix
|
||||
multiplication above, which breaks down to the following equations for angle:
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math9.avif" />
|
||||
<img src="/images/duckietown/lab2/math9.avif" />
|
||||
|
||||
where
|
||||
|
||||
<img src="../../../src/assets/duckietown/lab2/math10.avif" />
|
||||
<img src="/images/duckietown/lab2/math10.avif" />
|
||||
|
||||
**Can you explain why there is a difference between actual and desired
|
||||
location?**
|
||||
|
|
@ -464,13 +464,13 @@ one from the start of this section. The final distance was 64cm when measured by
|
|||
AR-ruler. About 62cm when measured by a prehistoric 90cm-stick:
|
||||
|
||||
<div><img
|
||||
src="../../../src/assets/duckietown/lab2/lab2_final_position.avif"
|
||||
src="/images/duckietown/lab2/lab2_final_position.avif"
|
||||
alt="64cm measured distance in an AR-ruler screenshot of an iPhone"
|
||||
style="width: 100%; height: 100%"
|
||||
/></div>
|
||||
|
||||
<div><img
|
||||
src="../../../src/assets/duckietown/lab2/lab2_final_dist_ar.avif"
|
||||
src="/images/duckietown/lab2/lab2_final_dist_ar.avif"
|
||||
alt="64cm measured distance in an AR-ruler screenshot of an iPhone"
|
||||
/></div>
|
||||
|
||||
|
|
@ -485,7 +485,7 @@ ipython-notebook](https://codeberg.org/akemi/duckietown/src/branch/main/lab2/bag
|
|||
with the resulting image here:
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab2/quiver_plot_sparse.avif"
|
||||
src="/images/duckietown/lab2/quiver_plot_sparse.avif"
|
||||
alt="A quiver plot (end-to-end arrows) of the robot traveling in a square"
|
||||
/>
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
title: 'DuckieTown - Lab 3'
|
||||
description: "Localization through Sensor Fusion"
|
||||
pubDate: 'March 05 2023'
|
||||
heroImage: '../../../src/assets/duckietown/lab3/ar-ducks.avif'
|
||||
heroImage: '/images/duckietown/lab3/ar-ducks.avif'
|
||||
---
|
||||
|
||||
A screenshot of our [Unit A-4 Advanced Augmented Reality
|
||||
|
|
@ -60,7 +60,7 @@ This is nicely visualized in this diagram from Figure 4.4 of [Unit B-4 Exercises
|
|||
Duckmentation](https://docs.duckietown.org/daffy/duckietown-classical-robotics/out/exercise_sensor_fusion.html#fig:at-lib-frame-convention-wrap).
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab3/at-frame-convention.jpg"
|
||||
src="/images/duckietown/lab3/at-frame-convention.jpg"
|
||||
alt="Frame convention used by april tag library when returning pose"
|
||||
/>
|
||||
|
||||
|
|
@ -223,12 +223,12 @@ the bot is an entire intersection ahead of where Rviz seems to show it.
|
|||
<iframe
|
||||
width="100%"
|
||||
height="325"
|
||||
src="../../../src/assets/duckietown/lab3/footprint_as_root_tf.pdf"
|
||||
src="/images/duckietown/lab3/footprint_as_root_tf.pdf"
|
||||
frameborder="0">
|
||||
</iframe>
|
||||
|
||||
It is quite the big graph, if you need to zoom in, click
|
||||
[here](../../../src/assets/duckietown/lab3/footprint_as_root_tf.pdf) to open the generated
|
||||
[here](/images/duckietown/lab3/footprint_as_root_tf.pdf) to open the generated
|
||||
transform tree graph. The root of this tree is
|
||||
`csc22927/footprint`.
|
||||
|
||||
|
|
@ -293,12 +293,12 @@ remove the ability to transform between frames in two different trees.
|
|||
<iframe
|
||||
width="100%"
|
||||
height="260"
|
||||
src="../../../src/assets/duckietown/lab3/footprint_as_child_tf.pdf"
|
||||
src="/images/duckietown/lab3/footprint_as_child_tf.pdf"
|
||||
frameborder="0">
|
||||
</iframe>
|
||||
|
||||
It is quite the big graph, if you need to zoom in, click
|
||||
[here](../../../src/assets/duckietown/lab3/footprint_as_child_tf.pdf) to open the newly generated
|
||||
[here](/images/duckietown/lab3/footprint_as_child_tf.pdf) to open the newly generated
|
||||
transform tree graph.
|
||||
|
||||
The new root/parent is the `world` frame.
|
||||
|
|
@ -338,7 +338,7 @@ already.
|
|||
Our solution to this was pure genius:
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab3/bottle_bots.avif"
|
||||
src="/images/duckietown/lab3/bottle_bots.avif"
|
||||
alt="Big waterbottle on top of duckiebot"
|
||||
/>
|
||||
|
||||
|
|
@ -411,7 +411,7 @@ We could have tried using multiple april tags (when visible) to improve our
|
|||
localization estimate.
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab3/birds_eye_view.avif"
|
||||
src="/images/duckietown/lab3/birds_eye_view.avif"
|
||||
alt="Bird's eye view from camera"
|
||||
/>
|
||||
Bird's eye view obtained using a projective transformation of the image.
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
title: 'DuckieTown - Lab 4'
|
||||
description: "Robots Following Robots"
|
||||
pubDate: 'March 19 2023'
|
||||
heroImage: '../../../src/assets/duckietown/lab4/state_machine_flowchart.avif'
|
||||
heroImage: '/images/duckietown/lab4/state_machine_flowchart.avif'
|
||||
---
|
||||
|
||||
# Don't crash! Tailing behaviour - Fourth lab
|
||||
|
|
@ -56,7 +56,7 @@ by seeing the red line from the other line.
|
|||
Check out the diagram below!
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab4/state_machine_flowchart.avif"
|
||||
src="/images/duckietown/lab4/state_machine_flowchart.avif"
|
||||
alt="Flow chart of internal state machine"
|
||||
/>
|
||||
|
||||
|
|
@ -76,7 +76,7 @@ detection node is intermittent, we had to use the TOF to fill in the gaps,
|
|||
however, we noticed that the two measurements did not perfectly correspond.
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab4/camera_vs_tof.avif"
|
||||
src="/images/duckietown/lab4/camera_vs_tof.avif"
|
||||
alt="Camera readings against TOF distance readings on a chart"
|
||||
/>
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
title: 'DuckieTown - Lab 5'
|
||||
description: "Machine Learning Robotics - Vision"
|
||||
pubDate: 'March 26 2023'
|
||||
heroImage: '../../../src/assets/duckietown/lab5/test-contour.avif'
|
||||
heroImage: '/images/duckietown/lab5/test-contour.avif'
|
||||
---
|
||||
|
||||
# MNIST Dataset and ML basic terminologies
|
||||
|
|
@ -12,7 +12,7 @@ heroImage: '../../../src/assets/duckietown/lab5/test-contour.avif'
|
|||
<iframe
|
||||
width="100%"
|
||||
height="600"
|
||||
src="../../../src/assets/duckietown/lab5/deliverable-1-backprop.pdf"
|
||||
src="/images/duckietown/lab5/deliverable-1-backprop.pdf"
|
||||
frameborder="0">
|
||||
</iframe>
|
||||
|
||||
|
|
@ -53,13 +53,13 @@ that is unable to separate the classes well.
|
|||
|
||||
t-SNE before changing the activation function:
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/t-SNE.avif"
|
||||
src="/images/duckietown/lab5/t-SNE.avif"
|
||||
alt="Clusters without changing activation function"
|
||||
/>
|
||||
|
||||
t-SNE after changing the activation function:
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/t-SNE-linear.avif"
|
||||
src="/images/duckietown/lab5/t-SNE-linear.avif"
|
||||
alt="Clusters after changing activation function"
|
||||
/>
|
||||
|
||||
|
|
@ -144,7 +144,7 @@ Our model architecture diagram created with
|
|||
[NN-SVG](https://github.com/alexlenail/NN-SVG) is shown below:
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/model.avif"
|
||||
src="/images/duckietown/lab5/model.avif"
|
||||
alt="Model architecture"
|
||||
/>
|
||||
|
||||
|
|
@ -152,7 +152,7 @@ We collected 270 train images and 68 test images of the numbers by saving
|
|||
images from the bot like below:
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-raw.avif"
|
||||
src="/images/duckietown/lab5/test-raw.avif"
|
||||
alt="Example raw image"
|
||||
/>
|
||||
|
||||
|
|
@ -161,21 +161,21 @@ extract the blue sticky note.
|
|||
(`cv.inRange`).
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-mask1.avif"
|
||||
src="/images/duckietown/lab5/test-mask1.avif"
|
||||
alt="Example mask image"
|
||||
/>
|
||||
|
||||
Then, we find the contour (`cv.findContours`) of the blue sticky note.
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-contour.avif"
|
||||
src="/images/duckietown/lab5/test-contour.avif"
|
||||
alt="Example contour image"
|
||||
/>
|
||||
|
||||
Then, we use OpenCV to get the convex hull of the contour (`cv.convexHull`).
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-convex_hull.avif"
|
||||
src="/images/duckietown/lab5/test-convex_hull.avif"
|
||||
alt="Example convex hull image"
|
||||
/>
|
||||
|
||||
|
|
@ -187,7 +187,7 @@ came up with the same idea as this [Stack Overflow
|
|||
answer](https://stackoverflow.com/a/55339684).
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-corners.avif"
|
||||
src="/images/duckietown/lab5/test-corners.avif"
|
||||
alt="Example corners image"
|
||||
/>
|
||||
|
||||
|
|
@ -195,7 +195,7 @@ Using OpenCV we calculate a perspective transform matrix to transform the
|
|||
image to 28 x 28 pixels.
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-warp.avif"
|
||||
src="/images/duckietown/lab5/test-warp.avif"
|
||||
alt="Example warp image"
|
||||
width="30%"
|
||||
/>
|
||||
|
|
@ -204,7 +204,7 @@ We get the black HSV colour mask of the warped image (`cv.inRange`) to extract
|
|||
the number.
|
||||
|
||||
<img
|
||||
src="../../../src/assets/duckietown/lab5/test-mask2.avif"
|
||||
src="/images/duckietown/lab5/test-mask2.avif"
|
||||
alt="Example mask image"
|
||||
width="30%"
|
||||
/>
|
||||
|
|
|
|||
|
|
@ -2,12 +2,12 @@
|
|||
title: 'DuckieTown - Lab 6'
|
||||
description: "Final Assignment - Obstacle Course"
|
||||
pubDate: 'April 16 2023'
|
||||
heroImage: '../../../src/assets/duckietown/final/three_ducks_on_a_windowsill.avif'
|
||||
heroImage: '/images/duckietown/final/three_ducks_on_a_windowsill.avif'
|
||||
---
|
||||
|
||||
<img src="../../../src/assets/duckietown/final/nine_ducks_on_two_dividers.avif" alt="Nine ducks on two dividers" style="height: 900px; margin: 0, padding: 0">
|
||||
<img src="../../../src/assets/duckietown/final/six_ducks_on_two_windowsills.avif" alt="Six ducks on two windowsills">
|
||||
<img src="../../../src/assets/duckietown/final/bam.avif" alt="Bam!">
|
||||
<img src="/images/duckietown/final/nine_ducks_on_two_dividers.avif" alt="Nine ducks on two dividers" style="height: 900px; margin: 0, padding: 0">
|
||||
<img src="/images/duckietown/final/six_ducks_on_two_windowsills.avif" alt="Six ducks on two windowsills">
|
||||
<img src="/images/duckietown/final/bam.avif" alt="Bam!">
|
||||
|
||||
## Round 1
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
title: 'DuckieTown - Pre-Lab 1'
|
||||
description: 'Getting ready for CMPUT 412'
|
||||
pubDate: 'Jan 11 2023'
|
||||
heroImage: '../../../src/assets/duckietown/dashboard_motors_spin.avif'
|
||||
heroImage: '/images/duckietown/dashboard_motors_spin.avif'
|
||||
---
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue