In cooperative transportation, multiple robots share work that is difficult to perform using a single robot. This transformation enables a flexible combination of robots to transport objects, enabling efficient operation according to the situation. In recent years, the cooperative transportation of objects has been studied using formation-change algorithms with reinforcement learning. Although individual tasks, such as transport or formation change, have been studied, the coordination of all tasks in cooperative transport and control has not been discussed. In this paper, a formation-control system using a state machine is proposed for transportation tasks in a complex environment. First, reinforcement learning algorithms specialized for multiple agents were used to change the formation. As precise environmental sensing in the vicinity of a formation is required for cooperative transport, an integrated sensing system that shares omnidirectional camera and light detection and ranging (LiDAR) sensor information with all the transport robots was constructed. Next, the formation was controlled using a state machine with an integrated virtual LiDAR sensor. Finally, two scenarios with multiple robots were demonstrated to evaluate the effectiveness of the proposed system.

1. [1] L. F. C. Ccari and P. R. Yanyachi, “A novel neural network-based robust adaptive formation control for cooperative transport of a payload using two underactuated quadcopters,” IEEE Access, Vol.11, pp. 36015-36028, 2023. https://doi.org/10.1109/ACCESS.2023.3265957
2. [2] X. Chen, Y. Fan, G. Wang, and Y. Jiang, “Adaptive formation control of multi-quadrotors cooperative transportation,” 9th Int. Conf. on Automation, Control and Robotics Engineering (CACRE), pp. 291-297, 2024. https://doi.org/10.1109/CACRE62362.2024.10635022
3. [3] X. An et al., “Multi-robot systems and cooperative object transport: Communications, platforms, and challenges,” IEEE Open J. of the Computer Society, Vol.4, pp. 23-36, 2023. https://doi.org/10.1109/OJCS.2023.3238324
4. [4] H. Yamaguchi, A. Nishijima, and A. Kawakami, “Control of two manipulation points of a cooperative transportation system with two car-like vehicles following parametric curve paths,” Robotics and Autonomous Systems, Vol.63, Part 1, pp. 165-178. 2015. https://doi.org/10.1016/j.robot.2014.07.007
5. [5] X. Li et al., “Cooperative target enclosing and tracking control with obstacles avoidance for multiple nonholonomic mobile robots,” Applied Sciences, Vol.12, No.6, Article No.2876, 2022. https://doi.org/10.3390/app12062876
6. [6] A. Yufka and M. Ozkan, “Formation-based control scheme for cooperative transportation by multiple mobile robots,” Int. J. of Advanced Robotic Systems, Vol.12, No.9, Article No.120, 2015. https://doi.org/10.5772/60972
7. [7] T. Iori et al., “Modeling and control of a cooperative conveyance system with multiple AGVs,” IFAC-PapersOnLine, Vol.56, No.2, pp. 6382-6387, 2023. https://doi.org/10.1016/j.ifacol.2023.10.829
8. [8] S. Yasuda, T. Kumagai, and H. Yoshida, “Cooperative transportation robot system using risk-sensitive stochastic control,” 2021 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 5981-5988, 2021. https://doi.org/10.1109/IROS51168.2021.9636238
9. [9] J. Alonso-Mora, S. Baker, and D. Rus, “Multi-robot formation control and object transport in dynamic environments via constrained optimization,” The Int. J. of Robotics Research, Vol.36, No.9, pp. 1000-1021, 2017. https://doi.org/10.1177/0278364917719333
10. [10] N. Matsunaga, K. Murata, and H. Okajima, “Robust cooperative transport system with model error compensator using multiple robots with suction cups,” J. Robot. Mechatron., Vol.35, No.6, pp. 1583-1592, 2023. https://doi.org/10.20965/jrm.2023.p1583
11. [11] A. Budiyanto and N. Matsunaga, “Deep Dyna-Q for rapid learning and improved formation achievement in cooperative transportation,” Automation, Vol.4, No.3, pp. 210-231, 2023. https://doi.org/10.3390/automation4030013
12. [12] A. Budiyanto, K. Azetsu, and N. Matsunaga, “Accelerated transfer learning for cooperative transportation formation change via SDPA-MAPPO (Scaled Dot Product Attention-Multi-Agent Proximal Policy Optimization),” Automation, Vol.5, No.4, pp. 597-612, 2024. https://doi.org/10.3390/automation5040034
13. [13] J. Boo and D. Chwa, “Fuzzy integral sliding mode observer-based formation control of mobile robots with kinematic disturbance and unknown leader and follower velocities,” IEEE Access, Vol.10, pp. 76926-76938, 2022. https://doi.org/10.1109/ACCESS.2022.3192839
14. [14] T. T. H. T. Nguyen, T. T. Dao, T. B. Ngo, and V. A. Phi, “Self-driving car navigation with single-beam LiDAR and neural networks using JavaScript,” IEEE Access, Vol.12, pp. 190203-190219, 2024. https://doi.org/10.1109/ACCESS.2024.3511572
15. [15] S. Chen et al., “NDT-LOAM: A real-time lidar odometry and mapping with weighted NDT and LFA,” IEEE Sensors J., Vol.22, No.4, pp. 3660-3671, 2022. https://doi.org/10.1109/JSEN.2021.3135055
16. [16] F. Wang et al., “A method coupling NDT and VGICP for registering UAV-LiDAR and LiDAR-SLAM point clouds in plantation forest plots,” Forests, Vol.15, No.12, Article No.2186, 2024. https://doi.org/10.3390/f15122186
17. [17] R. B. Hamarsudi, I. K. Wibowo, and M. M. Bachtiar, “Radial search lines method for estimating soccer robot position using an omnidirectional camera,” 2020 Int. Electronics Symp., pp. 271-276, 2020. https://doi.org/10.1109/IES50839.2020.9231901
18. [18] J. Caracotte, F. Morbidi, and E. M. Mouaddib, “Photometric stereo with twin-fisheye cameras,” 25th Int. Conf. on Pattern Recognition, pp. 5270-5277, 2021. https://doi.org/10.1109/ICPR48806.2021.9412357
19. [19] T. A. C. Garcia, M. B. Campos, L. F. Castanheiro, A. Maria, and G. Tommaselli, “A proposal to integrate ORB-SLAM fisheye and convolutional neural networks for outdoor terrestrial mobile mapping,” 2021 IEEE Int. Geoscience and Remote Sensing Symp., pp. 578-581, 2021. https://doi.org/10.1109/IGARSS47720.2021.9554752
20. [20] R. Lowe et al., “Multi-agent actor-critic for mixed cooperative-competitive environments,” arXiv:1706.02275, 2017. https://doi.org/10.48550/arXiv.1706.02275
21. [21] K. Murata, K. Miyazaki, and N. Matsunaga, “Experiment of cooperative transportation using multi-robots by multi-agent deep deterministic policy gradient,” 13th Asian Control Conf., pp. 1120-1123, 2022. https://doi.org/10.23919/ASCC56756.2022.9828156
22. [22] H. Okajima, “Model error compensator for adding robustness toward existing control systems,” IFAC-PapersOnLine, Vol.56, No.2, pp. 3622-3629, 2023. https://doi.org/10.1016/j.ifacol.2023.10.1524