Gerardo Puga

- [Hilti Challenge 2022 dataset](https://hilti-challenge.com/dataset-2022.html) - MARS??? - [Malaga 2009](https://www.mrpt.org/malaga_dataset_2009) - [NCTL](https://robots.engin.umich.edu/nclt/), through [nclt2ros](https://github.com/bierschi/nclt2ros) ? - [OpenLORIS](https://lifelong-robotic-vision.github.io/dataset/scene.html) - [Rawseeds dataset](http://www.rawseeds.org/home/category/benchmarking-toolkit/datasets/) - ["TUM"](https://www.mrpt.org/Collection_of_Kinect_RGBD_datasets_with_ground_truth_CVPR_TUM_2011) (only a subset) - [Willow Garage](https://google-cartographer-ros.readthedocs.io/en/latest/data.html#pr2-willow-garage)

This is ok by me, but we should first test the hyphotesis about what the problem is before looking for performant solutions for it. I would definitely not want spend...

@glpuga

:thinking:

It's great that we have the benchmarks already. I think when deciding if it's worth to pursue further optimization we need to evaluate the execution time in the context of...

Thanks a lot for the prompt response!

> Hello, can you help me with how to transform the velocity_control/odom topic into an odometry message type? Hi! In my case I simply processed the bagfile with a python...

@hidmic should we should reactivate or drop this. I tend lean on the second option, since as long as we publish results, and replicability is possible through the lambkin repository,...

> Ideally, neither. I meant, having a 12 months old paused PR is not great marketing. Regardless of what we decide to do about benchmarking, we should tilt this PR...

Another datapoint here. The latest versions of Beluga seem ot have a lot of memory, far more than older versions (start of year). Updating the kobuki stack's beluga version to...