Michał Antoszkiewicz

I have similar problem on ROS noetic. On ROS melodic it works fine.

Hi @Lindsay284 Did you manage to build use the planner in galactic?

Your robot position drifts a lot, which you can see base on the that laser scans move. Robot position drifting causes planner to change plane after every position estimation jump....

@SteveMacenski Is real-time BT graph visualization still possible with ZMQ ports depreciated? Edit: Found my answer. The whole future of live graph visualisation is depreciated: https://github.com/ros-planning/navigation2/issues/3770

@azhurkevich are you planning to work on the pure ONNX converter in the nearest future?

@azhurkevich I am trying to create TensorRT version of the detectron2 maskRCNN model. I understand that your conversion script (create_onnx.py) will not work with the newest detectron2. So I decided...

@zhuimeng2080 and @Photoheyler I had exactly the same problems with converting the model to TensorRT. In the end I used [MMDeploy](https://github.com/open-mmlab/mmdeploy) to convert and run the model on TensorRT backend....

Just follow the instructions from the [README.md](https://github.com/open-mmlab/mmdeploy/blob/master/README.md) of their repository. You probably interested in sections [getting_started](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/get_started.md), [Build for Linux](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/01-how-to-build/linux-x86_64.md), [How to convert model](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md).