Martin Günther

A couple of comments: * You have mixed up the training and testing datasets, so you've only been training on 2k images: > training data: 311 batches > testing data:...

Oh, and one more thing regarding the amount of training data: Did you specify `--nb_objects 1`? Your images look like it. If you regenerate the dataset, consider cranking that number...

I believe what @xiu-ccc means is that only part of the background HDRI map is visible in the generated images. @xiu-ccc , is that what you mean? If yes, I...

I can confirm that this works and is necessary to make VINS work with a Realsense T265 tracking camera. I had to remove the following assertion though: https://github.com/HKUST-Aerial-Robotics/VINS-Fusion/blob/0c3206941410723b8c62b7b0c6a6189b38ae7d99/vins_estimator/src/estimator/feature_manager.cpp#L65

I can't reproduce the problem. If you run these commands: ```bash roslaunch sbpl_lattice_planner move_base_sbpl_fake_localization_2.5cm.launch rostopic echo move_base_node/SBPLLatticePlanner/plan ``` ... and then send a navigation goal via RViz, you'll see that...

That's not the full modified portion of the script. Please post your full modified script.

You can also have a look at this file: https://github.com/sbpl/sbpl/blob/4d654845aa3b92aa1b4282a342e9011bac95aeb9/matlab/mprim/genmprim_unicycleplussidewaysplusbackturn.m That file generates backwards turns.

Yes, Navfn only produces a sequence of points, not poses (it doesn't fill out the orientation component of the pose). Simply limiting the twist like you proposed won't help: If...

Sorry, I don't have any idea either. I haven't seen this bug yet, and since as you said it's not reproducible this doesn't sound like a fun bug to fix......

Yes, the string includes the firmware version: `V2.45-12.03.15`.