Donkeycar

Latest version: v5.1.0

Safety actively analyzes 714860 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 2 of 4

4.3.6.2

This is a bugfix release for Donkey Car 4.3.6

This release contains PR 1011, 1009, 1007 which fix issues in recording and training.

4.3.6.1

_Note_
This release still has issues with recording data correctly, please install 4.3.6.2 instead.

This is a bugfix release for Donkey Car 4.3.6. It fixes an issue where the Raspberry Pi and Jetson Nano installations are currently depending on `pytorch` when driving with auto pilot. The release includes PR 1004.

4.3.6

_Note_
There is a bug when running this version on Raspberry Pi or Jetson Nano while driving with auto-pilot. Please install version 4.3.6.2 instead.

What's Changed

* Remove docs from dev by DocGarbanzo in https://github.com/autorope/donkeycar/pull/875
* Revert to passing full path to model in training by DocGarbanzo in https://github.com/autorope/donkeycar/pull/873
* Refactored RC control for GPIO pins by zlite in https://github.com/autorope/donkeycar/pull/860
* Add OLED resolution option by zlite in https://github.com/autorope/donkeycar/pull/879
* fix saliency map bugs by BillyCheung10botics in https://github.com/autorope/donkeycar/pull/886
* Add support for all models by DocGarbanzo in https://github.com/autorope/donkeycar/pull/884
* Fix moviepy installation on OSX by DocGarbanzo in https://github.com/autorope/donkeycar/pull/888
* Fixed RC control by zlite in https://github.com/autorope/donkeycar/pull/889
* Fix version in setup and align with module. by DocGarbanzo in https://github.com/autorope/donkeycar/pull/902
* Fix bugs and Improve the approach of makemovie by BillyCheung10botics in https://github.com/autorope/donkeycar/pull/900
* Fix issue 912: Cannot start 2D lidar if using a RealSense D435 by Ezward in https://github.com/autorope/donkeycar/pull/913
* Support cropping and trapezoidal mask by DocGarbanzo in https://github.com/autorope/donkeycar/pull/903
* Fix for memory model inferencing by DocGarbanzo in https://github.com/autorope/donkeycar/pull/922
* fix-encoder-pipeline by Ezward in https://github.com/autorope/donkeycar/pull/929
* Added an image buffer to fix the artificial latency in sim by Maximellerbach in https://github.com/autorope/donkeycar/pull/919
* Support for sixad ps3controller on Nano(2nd try) by fengye in https://github.com/autorope/donkeycar/pull/931
* now donkey gets version from setup.py by Ezward in https://github.com/autorope/donkeycar/pull/935
* 937-import-imageaugmentation-causes-error by Ezward in https://github.com/autorope/donkeycar/pull/939
* Updated stop sign detector part to allow reversing for few iterations by JoeSiu in https://github.com/autorope/donkeycar/pull/899
* Added fps counter part by JoeSiu in https://github.com/autorope/donkeycar/pull/897
* 954-fix-csic-camera-capture by Ezward in https://github.com/autorope/donkeycar/pull/955
* Add back support for tubhist by DocGarbanzo in https://github.com/autorope/donkeycar/pull/958
* 963 Install Jetson.GPIO on [nano] by Ezward in https://github.com/autorope/donkeycar/pull/964
* Improvements to donkey UI and donkey command by DocGarbanzo in https://github.com/autorope/donkeycar/pull/962
* Eliminate unnecessary spaces messing up OLED display by zlite in https://github.com/autorope/donkeycar/pull/971
* 961 protect from empty camera image by Ezward in https://github.com/autorope/donkeycar/pull/967
* Fix missing import for UI and added windows support where tensorrt is not available by DocGarbanzo in https://github.com/autorope/donkeycar/pull/975
* 945 refactor motor drivers by Ezward in https://github.com/autorope/donkeycar/pull/951
* 970 imgaug workaround mock augmentations by Ezward in https://github.com/autorope/donkeycar/pull/978
* Add argument parser to realsense435i.py main by Ezward in https://github.com/autorope/donkeycar/pull/979
* Install imgaug also on the robot and not only the pc, so the donkey c… by DocGarbanzo in https://github.com/autorope/donkeycar/pull/965
* Improve CI times by switching from conda to mamba by DocGarbanzo in https://github.com/autorope/donkeycar/pull/981
* clamp differential drive throttle and steering by Ezward in https://github.com/autorope/donkeycar/pull/983
* 970 enable rc controller in webui by Ezward in https://github.com/autorope/donkeycar/pull/985
* Adding FastAI(pytorch) as a first class citizen to the pipeline by adricl in https://github.com/autorope/donkeycar/pull/982
* fix syntax error in the joystick creator by Ezward in https://github.com/autorope/donkeycar/pull/995



New Contributors
* JoeSiu made their first contribution in https://github.com/autorope/donkeycar/pull/899

4.2.1

There was a regression in 4.2 where the `--model` argument only expected the model name but not the full path. This gets reverted to the previous behaviour

4.2

* The Donkey Gym simulator, which is both super useful for training at home as well as what we use for our virtual races, has been significantly improved. Along with new tracks, it now supports virtual Lidar.

* Speaking of which, lidar is now supported on real Donkey Cars, too. RPLidar and YPLidar (in beta) 2-D lidars now have parts in Donkey Car - so you can do effective obstacle avoidance, slam, drive in the dark or have a donkey F1/10.
* Instructions (with pictures!!) how to setup the car to drive with the RC controller that is usually shipped with any car - this provides the ‘classic’ RC driving feel.
* A new Donkey UI app:
- You can edit your tub using the app, this replaces donkey tubclean
- There is also support for training the model
- You can run and compare two pilots
- On OSX/Linux you can transfer data between the car and the PC
* Support for L298 motor controller in the car app
* Support for both simple and quadrature encoders to add odometry learning and driving
* Enabling storage of position, gyro, acceleration, velocity in the tub when using the Donkey Gym!
* MQTT logging
* donkey findcar now working on RPi 4

Contributors: zlite, showsep93, sctse999, Maximellerbach, Meir Tseilin, fengye, Heavy02011, BillyCheung10botics, EricWiener, DocGarbanzo.

4.1

New 4.1 Release Highlights

* New Datastore
* New Training Pipeline
* PyTorch Support (Resnet 18)

Page 2 of 4

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.