crowdbot-evaluation-tools

</>

Repository for crowd tracking and robot performance evaluation in navigation experiments

Files & Folders

• docs/: documentation
• qolo/: codespace for crowdbot evaluation
• notebook/: example notebooks for demo
  • introtodataset.ipynb
  • controllercomparisonanalysis.ipynb
  • sharedcontrolcrowddensitycluster_analysis.ipynb
  • comprehensive_eval.ipynb
• sh_scripts/: shell scripts to execute pipelines for extracting source data, applying algorithms, and evaluating with different metrics
• crowdbot_tools_archive/: archive of https://github.com/danjia21/crowdbot_tools

Dataset

Structure

Proposed dataset structure

Demo

| Example | Visualization | | ------------------------------------------------------------ | ------------------------------------------------------------ | | Qolo trajectories with tracked bounding box (generated using gen_viz_img.py and gen_animation.py) | | | Crowd density (generated using eval_crowd.py) | | | Minimal distance of pedestrian to Qolo (generated using eval_crowd.py) | | | Path efficiency (generated using eval_qolo_path.py) | | | Qolo command (generated using eval_qolo_ctrl.py) | | | Qolo state (generated using eval_qolo_ctrl.py) | |

References:

Crowd navigation DATASET:

Paez-Granados D., He Y., Gonon D., Huber L., & Billard A., (2021), 3D point cloud and RGBD of pedestrians in robot crowd navigation: detection and tracking., Dec. 2021. IEEE Dataport, doi: https://dx.doi.org/10.21227/ak77-d722.

Qolo Robot:

[1] Paez-Granados, D., Hassan, M., Chen, Y., Kadone, H., & Suzuki, K. (2022). Personal Mobility with Synchronous Trunk-Knee Passive Exoskeleton: Optimizing Human-Robot Energy Transfer. IEEE/ASME Transactions on Mechatronics, 1(1), 112. https://doi.org/10.1109/TMECH.2021.3135453

[2] Paez-Granados, D. F., Kadone, H., & Suzuki, K. (2018). Unpowered Lower-Body Exoskeleton with Torso Lifting Mechanism for Supporting Sit-to-Stand Transitions. IEEE International Conference on Intelligent Robots and Systems, 27552761. https://doi.org/10.1109/IROS.2018.8594199

Reactive Navigation Controllers:

[3] Gonon, D. J., Paez-Granados, D., & Billard, A. (2021). Reactive Navigation in Crowds for Non-holonomic Robots with Convex Bounding Shape. IEEE Robotics and Automation Letters, 6(3), 47284735. https://doi.org/10.1109/LRA.2021.3068660

[4] Huber, L., Billard, A., & Slotine, J.-J. (2019). Avoidance of Convex and Concave Obstacles With Convergence Ensured Through Contraction. IEEE Robotics and Automation Letters, 4(2), 14621469. https://doi.org/10.1109/lra.2019.2893676

[5] Paez-Granados, D., Gupta, V., & Billard, A. (2021). Unfreezing Social Navigation : Dynamical Systems based Compliance for Contact Control in Robot Navigation. Robotics Science and Systems (RSS) - Workshop on Social Robot Navigation, 1(1), 14.http://infoscience.epfl.ch/record/287442?&ln=en. https://youtu.be/y7D-YeJ0mmg

Qolo shared control:

[6] Chen, Y., Paez-Granados, D., Kadone, H., & Suzuki, K. (2020). Control Interface for Hands-free Navigation of Standing Mobility Vehicles based on Upper-Body Natural Movements. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2020). https://doi.org/10.1109/IROS45743.2020.9340875

Acknowledgment

We thank Prof. Kenji Suzuki from AI-Lab, University of Tsukuba, Japan for lending the robot Qolo used in these experiments and data collection.

This project was partially founded by:

The EU Horizon 2020 Project CROWDBOT (Grant No. 779942): http://crowdbot.eu