The Journal of Korea Robotics Society (로봇학회논문지)

Korea Robotics Society (한국로봇학회)
권호 표지
DOI QR코드

DOI QR Code

Learning-based Inertial-wheel Odometry for a Mobile Robot

모바일 로봇을 위한 학습 기반 관성-바퀴 오도메트리

  • Myeongsoo Kim (Graduate School of Convergence Science and Technology, Seoul National University) ;
  • Keunwoo Jang (Artificial Intelligence and Robotics Institute, Korea Institute of Science and Technology) ;
  • Jaeheung Park (Graduate School of Convergence Science and Technology, ASRI, RICS, Seoul National University)
  • Received : 2023.05.27
  • Accepted : 2023.08.30
  • Published : 2023.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a method of estimating the pose of a mobile robot by using a learning model. When estimating the pose of a mobile robot, wheel encoder and inertial measurement unit (IMU) data are generally utilized. However, depending on the condition of the ground surface, slip occurs due to interaction between the wheel and the floor. In this case, it is hard to predict pose accurately by using only encoder and IMU. Thus, in order to reduce pose error even in such conditions, this paper introduces a pose estimation method based on a learning model using data of the wheel encoder and IMU. As the learning model, long short-term memory (LSTM) network is adopted. The inputs to LSTM are velocity and acceleration data from the wheel encoder and IMU. Outputs from network are corrected linear and angular velocity. Estimated pose is calculated through numerically integrating output velocities. Dataset used as ground truth of learning model is collected in various ground conditions. Experimental results demonstrate that proposed learning model has higher accuracy of pose estimation than extended Kalman filter (EKF) and other learning models using the same data under various ground conditions.

Keywords

Acknowledgement

This work was supported by Imdang Scholarship & Cultural Foundation

References

  1. J. Borenstein and L. Feng, "Measurement and correction of systematic odometry errors in mobile robots," IEEE Transactions on robotics and automation, vol. 12, no. 6, pp. 869-880, Dec., 1996, DOI: 10.1109/70.544770.
  2. K. S. Chong and L. Kleeman, "Accurate odometry and error modelling for a mobile robot," IEEE International Conference on Robotics and Automation (ICRA), Albuquerque, USA, vol. 4, pp. 2783-2788, 1997, DOI: 10.1109/ROBOT.1997.606708.
  3. A. Martinelli, N. Tomatis, and R. Siegwart, "Simultaneous localization and odometry self calibration for mobile robot," Autonomous Robots, vol. 22, pp. 75-85, 2007, DOI: 10.1007/s10514-006-9006-7.
  4. A. Angelova, L. Matthies, D. Helmick, and P. Perona, "Slip prediction using visual information," Robotics: Science and Systems, Pennsylvania, USA, 2006, DOI: 10.15607/RSS.2006.II.014.
  5. D. M. Helmick, S. I. Roumeliotis, Y. Cheng, D. S. Clouse, M. Bajracharya, and L. H. Matthies, "Slip-compensated path following for planetary exploration rovers," Advanced Robotics, vol. 20, no. 11, pp. 1257-1280, Apr., 2012, DOI: 10.1163/156855306778792470.
  6. T. Qin, P. Li, and S. Shen, "Vins-mono: A robust and versatile monocular visual-inertial state estimator," IEEE Transactions on Robotics, vol. 34, no. 4, pp. 1004-1020, Aug., 2018, DOI: 10.1109/TRO.2018.2853729.
  7. T. Qin and S. Shen, "Online temporal calibration for monocular visual-inertial systems," 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, pp. 3662-3669, 2018, DOI: 10.1109/IROS.2018.8593603.
  8. J. Zhang and S. Singh, "Loam: Lidar odometry and mapping in real-time," Robotics: Science and Systems, Berkeley, USA, pp. 1-9, 2014, DOI: 10.15607/RSS.2014.X.007.
  9. T. Shan, B. Englot, D. Meyers, W. Wang, C. Ratti, and D. Rus, "LIO-SAM: Tightly-coupled lidar inertial odometry via smoothing and mapping," 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, USA, pp. 5135-5142, 2020, DOI: 10.1109/IROS45743.2020.9341176.
  10. S. Zhao, H. Zhang, P. Wang, L. Nogueira, and S. Scherer, "Super odometry: Imu-centric lidar-visual-inertial estimator for challenging environments," 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic, pp. 8729-8736, 2021, DOI: 10.1109/IROS51168.2021.9635862.
  11. J. Yi, H. Wang, J. Zhang, D. Song, S. Jayasuriya, and J. Liu, "Kinematic modeling and analysis of skid-steered mobile robots with applications to low-cost inertial-measurement-unit-based motion estimation," IEEE transactions on robotics, vol. 25, no. 5, pp. 1087-1097, Oct., 2009, DOI: 10.1109/TRO.2009.2026506.
  12. U. Onyekpe, V. Palade, A. Herath, S. Kanarachos, and M. E. Fitzpatrick, "Whonet: Wheel odometry neural network for vehicular localisation in gnss-deprived environments," Engineering Applications of Artificial Intelligence, vol. 105, pp. 104421, Oct., 2021, DOI: 10.1016/j.engappai.2021.104421.
  13. M. Brossard, A. Barrau, and S. Bonnabel, "Ai-imu dead-reckoning," IEEE Transactions on Intelligent Vehicles, vol. 5, no. 4, pp. 585-595, Dec., 2020, DOI: 10.1109/TIV.2020.2980758.
  14. M. A. Esfahani, H. Wang, K. Wu, and S. Yuan, "Orinet: Robust 3-d orientation estimation with a single particular imu," IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 399-406, Apr., 2020, DOI: 10.1109/LRA.2019.2959507.
  15. M. Brossard, S. Bonnabel, and A. Barrau, "Denoising imu gyroscopes with deep learning for open-loop attitude estimation," IEEE Robotics and Automation Letters, vol. 5, no. 3, pp. 4796-4803, Jul., 2020, DOI: 10.1109/LRA.2020.3003256.
  16. S. Herath, H. Yan, and Y. Furukawa, "Ronin: Robust neural inertial navigation in the wild: Benchmark, evaluations, & new methods," 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, pp. 3146-3152, 2020, DOI: 10.1109/ICRA40945.2020.9196860.
  17. W. Liu, D. Caruso, E. Ilg, J. Dong, A. I. Mourikis, K. Daniilidis, V. Kumar, and J. Engel, "Tlio: Tight learned inertial odometry," IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 5653-5660, Oct., 2020, DOI: 10.1109/LRA.2020.3007421.
  18. M. Zhang, M. Zhang, Y. Chen, and M. Li, "IMU data processing for inertial aided navigation: A recurrent neural network based approach," 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, pp. 3992-3998, 2021, DOI: 10.1109/ICRA48506.2021.9561172.
  19. M. Brossard and S. Bonnabel, "Learning wheel odometry and imu errors for localization," 2019 International Conference on Robotics and Automation (ICRA), Montreal, Canada, pp. 291-297, 2019, DOI: 10.1109/ICRA.2019.8794237.
  20. A. Geiger, P. Lenz, and R. Urtasun, "Are we ready for autonomous driving? the kitti vision benchmark suite," 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, pp. 3354-3361, 2012, DOI: 10.1109/CVPR. 2012.6248074.
  21. J. Jeong, Y. Cho, Y.-S. Shin, H. Roh, and A. Kim, "Complex urban dataset with multi-level sensors from highly diverse urban environments," The International Journal of Robotics Research, vol. 38, no. 6, pp. 642-657, Apr., 2019, DOI: 10.1177/0278364919843996.
  22. N. Carlevaris-Bianco, A. K. Ushani, and R. M. Eustice, "University of michigan north campus long-term vision and lidar dataset," The International Journal of Robotics Research, vol. 35, no. 9, pp. 1023-1035, Dec., 2015, DOI: 10.1177/0278364915614638.
  23. M. Burri, J. Nikolic, P. Gohl, T. Schneider, J. Rehder, S. Omari, M. W. Achtelik, and R. Siegwart, "The euroc micro aerial vehicle datasets," The International Journal of Robotics Research, vol. 35, no. 10, pp. 1157-1163, Jan., 2016, DOI: 10.1177/0278364915620033.
  24. D. Schubert, T. Goll, N. Demmel, V. Usenko, J. Stuckler, and D. Cremers, "The tum vi benchmark for evaluating visual-inertial odometry," 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, pp. 1680-1687, 2018, DOI: 10.1109/IROS.2018.8593419.
  25. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, "PyTorch: An imperative style, high-performance deep learning library," Advances in neural information processing systems, vol. 32, 2019, [Online], paper_files/paper/2019/hash/bdbca288fee7f92f2bfa9f7012727740-Abstract.html.
  26. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv:1412.6980, Dec., 2014, DOI: 10.48550/arXiv.1412.6980.
  27. V. Peretroukhin and J. Kelly, "DPC-Net: Deep pose correction for visual localization," IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 2424-2431, Jul., 2018, DOI: 10.1109/LRA.2017.2778765.