ETRI Journal

  • 제45권2호
  • /
  • Pages.329-337
  • /
  • 2023
  • /
  • 1225-6463(pISSN)
  • /
  • 2233-7326(eISSN)
한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

A robust collision prediction and detection method based on neural network for autonomous delivery robots

  • Seonghun Seo (Cognition & Transportation ICT Research Section, Electronics and Telecommunications Research Institute) ;
  • Hoon Jung (Postal and Logistics Technology Research Center, Electronics and Telecommunications Research Institute)
  • 투고 : 2021.10.27
  • 심사 : 2023.01.02
  • 발행 : 2023.04.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

키워드

과제정보

This work was supported by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00297-001, Development of delivery assistant technology and commercialization field test for high weight movable delivery service based on 5G).

참고문헌

  1. A. Dekhne, G. Hastings, J. Murnane, and F. Neuhaus, Mckinsey, 2019.
  2. F. M. Moura and M. F. Silva, Application for automatic programming of palletizing robots, (Proc. IEEE International Conference on Autonomous Robot Systems and Competitions, Torres Vedras, Portugal), 2018, pp. 48-53.
  3. S. Smys and G. Ranganathan, Robot assisted sensing, control and manufacture in automobile industry, J ISMAC 1 (2019), no. 3, 180-187. https://doi.org/10.36548/jismac.2019.3.005
  4. G. A. Fontanelli, G. Paduano, R. Caccavale, P. Arpenti, V. Lippiello, L. Villani, and B. Siciliano, A reconfigurable gripper for robotic autonomous depalletizing in supermarket logistics, IEEE Robot Autom Lett 5 (2020), no. 3, 4612-1617.
  5. A. Lourenco, F. Marques, R. Mendonca, E. Pinto, and J. Barata, On the design of the ROBO-PARTNER intra-factory logistics autonomous robot, (Proc. IEEE Int. Conf. Syst. Man Cybern., Budapest, Hungary), 2016, pp. 2647-2652.
  6. D. Wahrmann, A. Hildebrandt, C. Schuetz, R. Wittmann, and D. Rixen, An autonomous and flexible robotic framework for logistics applications, J. Intel. Robot. Syst. 93 (2019), no. 3, 419-431. https://doi.org/10.1007/s10846-017-0746-8
  7. R. Krug, T. Stoyanov, V. Tincani, H. Andreasson, R. Mosberger, G. Fantoni, and A. J. Lilienthal, The next step in robot commissioning: Autonomous picking and palletizing, IEEE Robot Autom Lett 1 (2016), no. 1, 546-553. https://doi.org/10.1109/LRA.2016.2519944
  8. A. Mohammed, B. Schmidt, and L. Wang, Active collision avoidance for human-robot collaboration driven by vision sensors, Int J Comp 30 (2017), no. 9, 970-980.
  9. M. Fritzsche, J. Saenz, and F. Penzlin, A large scale tactile sensor for safe mobile robot manipulation, (Proc. ACM/IEEE Int. Conf. Human-Robot Interaction, Christchurch, New Zealand), 2016, pp. 427-428.
  10. Y. Sun, L. Guan, Z. Chang, C. Li, and Y. Gao, Design of a lowcost indoor navigation system for food delivery robot based on multi-sensor information fusion, Sensors 19 (2019), no. 22, 4980.
  11. N. Kawarazaki, L. T. Kuwae, and T. Yoshidome, Development of human following mobile robot system using laser range scanner, Procedia Comp Sci 76 (2015), 455-460. https://doi.org/10.1016/j.procs.2015.12.310
  12. A. Asvadi, C. Premebida, P. Peixoto, and U. Nunes, 3D lidarbased static and moving obstacle detection in driving environments: An approach based on voxels and multi-region ground planes, Rob Autom Sys 83 (2016), 299-311. https://doi.org/10.1016/j.robot.2016.06.007
  13. A. Ravankar, A. A. Ravankar, A. Rawankar, and Y. Hoshino, Autonomous and safe navigation of mobile robots in vineyard with smooth collision avoidance, Agriculture 11 (2021), no. 10, 954.
  14. J.-H. Cho, D.-S. Pae, M.-T. Lim, and T.-K. Kang, A real-time obstacle avoidance method for autonomous vehicles using an obstacle-dependent Gaussian potential filed, J Adv Transp 2018 (2018), 15.
  15. X. Xue, Z. Li, D. Zhang, and Y. Yan, A deep reinforcement learning method for mobile robot collision avoidance based on double DQN, (Proc. IEEE Int. Symp. Industrial Electronics, Vancouver, Canada), 2019, pp. 2131-2136.
  16. F. Becker and M. Ebner, Collision detection for a mobile robot using logistic regression, (Proc. Int. Conf. Informatics in Control, Automation and Robotics, Lisbon, Portugal), 2019, pp. 167-173.
  17. S. Yang, X. Yu, Y. Zhou, LSTM and GRU neural network performance comparison study, (Proc. Int. Workshop on Electronic Communication and Artificail Intelligence, Shanghai, China), 2020, pp. 98-101.
  18. G. Chan, LidarPerception/segmenters_lib, 2020. Available from: http://github.com/LidarPerception/segmenters_lib/ [last accessed October 2021].
  19. S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Comput 9 (1997), no. 8, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  20. Unity Technologies, Unity documentation, 2021, Available from: https://docs.unity3d.com/kr/2021.2/Manual/PhysicsSection.html/ [last accessed October 2021]