You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The new README now contains the PX4 dev summit video presentation and the thesis report. furthermore, I moved the instructions to run the simulation down because the user can only run the custom model once he/she has estimated the model parameters.
Copy file name to clipboardExpand all lines: README.md
+28-11Lines changed: 28 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,6 +6,13 @@
6
6
7
7
This repository allows a data-driven dynamics model for PX4 SITL(Software-In-The-Loop) simulations.
8
8
9
+
You can get an overview of the pipeline and its functionalities in the following video presentation:
10
+
11
+
[](https://www.youtube.com/watch?v=kAsfptZU4uk)
12
+
13
+
14
+
More detailed information can be found in the student paper [Data-Driven Dynamics Modelling Using Flight Logs](https://www.research-collection.ethz.ch/handle/20.500.11850/507495).
15
+
9
16
## Setting up the environment
10
17
11
18
This plugin depends on [PX4 SITL](https://github.com/PX4/PX4-SITL_gazebo). Therefore custom messages of PX4 SITL needs to be linked. Therefore, prior to building this package, PX4 and corresponding SITL package needs to be built.
@@ -30,7 +37,7 @@ source ~/.bashrc
30
37
31
38
The use the parametric model structure you need to install python 3.8 and the needed python libraries. It is strongly advised to install the pip packages in a [virtual enviroment](https://docs.python.org/3/tutorial/venv.html) setup for this project.
32
39
33
-
Update submodules:
40
+
Update and initialize submodules:
34
41
35
42
```
36
43
make submodulesupdate
@@ -42,6 +49,14 @@ Install the dependencies from the project folder:
42
49
make install-dependencies
43
50
```
44
51
52
+
Or install the dependencies including submodule dependencies:
53
+
54
+
```
55
+
install-full-depdencies
56
+
```
57
+
58
+
59
+
45
60
## Build
46
61
47
62
After the environment has been setup as described in the previous section, build the package as the following.
@@ -53,15 +68,6 @@ cmake ..
53
68
make
54
69
```
55
70
56
-
## Running the Simulation
57
-
58
-
To run the simulation,
59
-
60
-
```
61
-
source setup.bash
62
-
Tools/sitl_run.sh -m iris -s iris_aerodynamics
63
-
```
64
-
65
71
## Generating a Parametric Model from Log File
66
72
67
73
Link the latest log files to your local logs folder using:
@@ -109,10 +115,21 @@ As an example to get started you estimate the parameters of a quadrotor model wi
109
115
make estimate-model model=quadrotor_model log=resources/quadrotor_model.ulg
110
116
```
111
117
112
-
## Testing the functionality of Parametric model
118
+
###Testing the functionality of Parametric model
113
119
114
120
To ensure that the parametric model works as expected you can perform a set of pytests, which are stored in `Tools/parametric_model/tests`. To start the tests you have to run the shell script:
115
121
116
122
`Tools/parametric_model/test_parametric_model.sh`
117
123
118
124
Currently only the transformation from body to intertial frame and vise versa are checked. This should be expanded in the future.
125
+
126
+
## Running the Simulation
127
+
128
+
To run the simulation,
129
+
130
+
```
131
+
source setup.bash
132
+
Tools/sitl_run.sh -m iris -s iris_aerodynamics
133
+
```
134
+
135
+
The custom Gazebo quadrotor model will always read the model parameters from the file `model_results/quadrotor_model.yaml`. You can simply rename your desired model results file to fly your estimated model in Gazebo.
0 commit comments