Results of Cobra

Mapping: Campus (without semantics)

roslaunch r3live r3live_bag_ouster128_raw.launch
roslaunch nvblox_ros nvblox_lidar_ros_fusionportable.launch

Mapping: SemanticKITTI Sequence07 (LiDAR-based semantics)

rosbag play semantickitti_sequence07.bag
roslaunch nvblox_ros nvblox_lidar_ros_kitti.launch

Mapping: KITTI-360 (Image-based semantics)

rosbag play nvblox_mesh_2013_05_28_drive_0003_sync.bag
roslaunch nvblox_ros nvblox_lidar_ros_kitti360.launch

Mapping: FusionPortable (Image-based semantics)

Navigation:

Chart

2. Usage

Test with the FusionPortable Dataset

bash scripts/run_cobra_fusionportable.sh

Test with the SemanticFusionPortable Dataset

bash scripts/run_cobra_semanticfusionportable.sh

Test with the SemanticKITTI Dataset

bash scripts/run_cobra_semantickitti.sh

Batch test with all datasets

rosparam set use_sim_time true
cd src/cobra_tools/scripts/bash
bash run_nvblox_proposed.bash

Monitor the CPU, GPU, and memory of the PC

rosrun cobra_tools monitor_pc_status.py -c /Spy/dataset/tmp/logs/cpu_gpu_utils_0.1

3. Key parameters

voxel_size: 0.3 (SemanticKITTI00, 02, 08), 0.25 (other sequences)
mesh: 0 (not save mesh result), 1 (save mesh result)
dataset_type: the id of different datasets
max_mesh_update_time: the frequency of saving mesh. For example: 0.1 for 10Hz
performance_monitor: 0 (not monitor CPU and GPU usage), 1 (monitor CPU and GPU usage)

Citation

If you found any of the above modules useful, we would really appreciate if you could cite our work:

• [2] Jiao, J., Wei, H., Hu, T., Hu, X., Zhu, Y., ... & Liu, M. FusionPortable: A Multi-Sensor Campus-Scene Dataset for Evaluation of Localization and Mapping Accuracy on Diverse Platforms. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE.

@inproceedings{jiao2022fusionportable,
  title={FusionPortable: A Multi-Sensor Campus-Scene Dataset for Evaluation of Localization and Mapping Accuracy on Diverse Platforms},
  author={Jiao, Jianhao and Wei, Hexiang and Hu, Tianshuai and Hu, Xiangcheng and Zhu, Yilong and He, Zhijian and Wu, Jin and Yu, Jingwen and Xie, Xupeng and Huang, Huaiyang and others},
  booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={3851--3856},
  year={2022},
  organization={IEEE}
}

Open-Source Datasets

We release an open-source dataset: FusionPortable [1] for real-life tests. The dataset provides:

• 3D LiDAR
• Stereo Frame Cameras
• Stereo Event Cameras
• IMU data
• Ground-Truth Odometry
• Static TF (ground-truth poses of static objects)

Acknowledgments

License

BSD License