Autonomous Navigation of a Two-wheeled Mobile Robot with Timed Elastic Band Planner in Greenhouse Environment = 온실환경에서 TEB 경로계획 방법을 사용한 두바퀴 모바일 로봇의 자율주행

국문 초록 (Abstract)

첨단 대형 온실은 농업 발전의 중요한 발전을 나타내며, 운영 효율성 개선과
노동력 감소를 갖어왔습니다. 온실 환경에 맞춤형으로 개발된 자율이동 로봇은
기존 노동력 기반의 농업과 단순 자동화 기술의 제약을 해결하는 데 중요한 역
할을 하고 있습니다. 하지만, 온실 내 GPS 신호의 이용이 불가능하여 위치 추정
이 어려운 점은 온실 자율이동 로봇의 한계로 나타나고 있습니다. 이로 인해 온
실 내 자율주행 및 위치 추정의 구현이 복잡해지기 때문에 온실 내 자율주행
내비게이션과 정밀 위치추정 기술은 온실 무인 자동화를 위한 핵심기술입니다.
본 연구의 목표는 온실 내 도로 및 레일 표면에 적응할 수 있는 새로운 바
퀴 메커니즘을 개발하고, 센서 시스템과 알고리즘을 통합하여 정밀한 내비게이션
을 보장하며, 이동 로봇의 운동학적 모델링을 수행하고, Hector SLAM을 사용해
고해상도 온실 지도를 작성하며, 적응형 몬테카를로 위치 추정(AMCL)과 비주얼
SLAM 기술을 통해 위치 추정 정확도를 향상시키는 것입니다.
본 연구의 결과는 제한된 농업 환경인 온실 내에서 SLAM 기반의 이동 로
봇 내비게이션을 통해 실증되었습니다. 먼저, 마커를 레일 중앙에 위치시켜 레일
중앙 포인트를 추출하고, 컴퓨터비전 기술을 사용해 정확한 중앙 포인트를 결정
합니다. 온실 환경이 맵핑된 후 마커를 제거하고, 인식된 레일 중앙 포인트를 이
용하여 레일 인식의 계산 복잡성을 줄일 수 있습니다. 이동로봇의 위치 추정은
라이다 스캔을 2D 그리드 지도와 정렬한 후 적응형 몬테카를로 위치 추정
(AMCL) 알고리즘을 통해 실시간으로 인지됩니다. 글로벌 내비게이션 경로 계획
은 Dijkstra 알고리즘을 사용하며, 로컬 내비게이션 경로 계획은 TEB 접근 방식
을 사용합니다.
실험 결과, 온실 환경 내에서 로봇의 위치 누적 오류를 최소화하는 AMCL
및 비주얼 SLAM 기반의 통합 위치 시스템의 효과가 입증되었습니다. 0.4, 0.6,
0.8 m/s의 로봇 주행속도에서 최대 측면 오차는 0.55cm 미만이었으며, 평균 제
곱근 오차(RMSE)는 0.2cm 미만이었습니다. x 및 y 축 방향의 평균 글로벌 위치
오류는 5cm 미만이었으며, 궤적 추적 정확도는 96%를 초과했습니다. 이러한 실
험결과는 제안된 시스템을 통해 온실 환경 내 자율주행 로봇의 정밀한 내비게이
션이 가능함을 보여주었습니다.

다국어 초록 (Multilingual Abstract)

The large greenhouses signify a crucial advancement in agricultural development, improved operational efficiency, and decreased labor requirements. Autonomous mobile robots tailored for greenhouse environments are essential for addressing the challenges associated with manual labor and the limitations of traditional automation technologies. Moreover, indoor localization presents a unique challenge, as conventional GPS signals are unavailable within greenhouse settings. This limitation complicates efforts to implement autonomous navigation and precise localization for indoor agricultural robots. Addressing these complexities is vital for achieving the full potential of greenhouse automation to enhance productivity and sustainability in agriculture. The objectives encompass the development of a novel wheel mechanism capable of adapting to road and rail surfaces within greenhouses, along with integrating advanced sensor systems and algorithms to ensure precise navigation, the kinematic modeling of mobile robots, using Hector Simultaneous Localization and Mapping (SLAM) for high- fidelity greenhouse mapping, and improving localization using adaptive Monte Carlo localization (AMCL) and visual SLAM techniques for enhanced localization accuracy. The results were demonstrated in a greenhouse using SLAM based mobile robot navigation within confined agricultural environments, specifically in greenhouses. Our methodology involves extracting rail center points with markers; the markers are strategically placed at the center of rails, and lidar technology is utilized for accurate center point determination. Once the environment is mapped, the markers are removed, and the precise rail center points are employed for subsequent robot navigation. During localization, known positions of rail center points in a 2D space prevent the need for additional recognition system, thereby reducing computational complexity. The mobile robot localization algorithm aligns lidar scans with a 2D occupancy grid map, providing real-time position information through the Adaptive Monte Carlo Localization (AMCL) algorithm. This integration of lidar data with the existing 2D map achieves global positioning. Global navigation path planning employs the Dijkstra algorithm, while local navigation path planning utilizes the Timed-Elastic-Band (TEB) approach. Experimental results demonstrate the effectiveness of the integrated positioning system based on AMCL and visual SLAM in minimizing the robot's positioning cumulative error within the greenhouse environment. Across three travel speeds of 0.4, 0.6, and 0.8 m/s, the maximum lateral error remains under 0.55 cm with a root mean square error (RMSE) of less than 0.2 cm. The average global positioning error in the x and y-axis directions is less than 5 cm, and the trajectory tracking accuracy rate exceeds 96%. The autonomous robot's precise and secure navigation within the greenhouse environment showcases the accuracy achieved through the overall proposed system. Keywords: Mobile Robot, Greenhouse, Autonomous Navigation, Obstacle Avoidance, Simultaneous Localization and Mapping (SLAM)

목차 (Table of Contents)

• Contents i
• List of Figures iv
• List of Tables vii
• Abbreviations viii
• Abstract x
• 1. Introduction 1
• 1.1. Background · 1
• 1.2. Objectives 4
• 2. Related Work 6
• 2.1. Mobile Robot Platform in Greenhouse · 6
• 2.2. Localization · 11
• 2.3. Path Planning 15
• 2.3.1. A* Search Planner · 16
• 2.3.2. Dijkstra Planner 17
• 2.3.3. Dynamic Window Approach (DWA) Planner 18
• 2.3.4. Timed Elastic Band (TEB) Planner 20
• 3. Experimental Systems and Methods 23
• 3.1. Experimental Greenhouse 23
• 3.2. Mobile Robot System 25
• 3.2.1. Mobile Robot Platform 25
• 3.2.2. Unified Robot Description Format (URDF) · 33
• 3.3. Mobile Robot Kinematics · 35
• 3.4. Autonomous Mobile Robot Control System 40
• 3.5. Greenhouse Map 43
• 3.6. Localization · 48
• 3.6.1. Adaptive Monte Carlo Localization (AMCL) Algorithm 49
• 3.7. Path Planning 52
• 3.7.1. Dijkstra Path Planner 53
• 3.7.2. Timed Elastic Band (TEB) Path Planner · 55
• 3.8. Obstacle Avoidance Algorithm 58
• 3.9. Voice Commands for Autonomous Mobile Robot Control 60
• 3.9.1. Integration of Voice Commands with Navigation Stack 61
• 3.9.2. Implementation of ROS with Voice Command Systems 63
• 4. Results and Discussions 65
• 4.1. Map Generation 65
• 4.2. Mobile Robot Localization 66
• 4.3. Autonomous Navigation 68
• 4.3.1. Navigation Performance at Various Initial Heading Angles 70
• 4.3.2. Navigation Performance in Reaching Target Points · 82
• 4.3.3. Localization Performance on the Rail 83
• 4.3.4. Navigation Performance at Various Travel Speeds · 88
• 4.4. Obstacle Avoidance 89
• 4.4.1. Static Obstacle Avoidance 89
• 4.4.2. Dynamic Obstacle Avoidance · 93
• 4.5. Mobile Robot Control using Voice Commands 97
• 4.5.1. Collection of Target Points in Map 99
• 4.5.2. Mobile Robot Positioning using Voice Commands 103
• 4.5.3. Signal Strength of Voice Commands · 104
• 5. Conclusions and Future Works 106
• 5.1. Conclusions · 106
• 5.2. Future works 108
• References 110
• Abstract in Korean · 119

참고문헌 (Reference)

1. Autonomous systems, Watson, D. P. and Scheidt, D. H., 26(4): 368-376, , 2005

2. AI-IMU dead-reckoning, Barrau, A. and, Bonnabel, S., Brossard, M., 5(4): 585-595, , 2020

3. The HTK Bookfor HTK Version, Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., ... & Woodland, P., 3.4, , 2006

4. The DRAGON system - An overview, Baker, J. K., 23(1): 24-29, , 1975

5. Coordinated multi-robot exploration, Burgard, W., Moors, M., Stachniss, C., and Schneider, F., 21(3): 376- 386, , 2005

6. An introduction to Hidden Markov Models, Rabiner, L. R. and, Juang, B. H., 3(1): 4-16, , 1986

7. A survey on wireless position estimation, Gezici, S., 44(3): 263-282, , 2005

8. Modular Self-Reconfigurable Robot Systems, Yim, M., et al, 7(1): 43-52, , 2000

9. MorphBot: A Morphologically Adaptive Robot, Liu, Y. et al, IEEE Transactions on Robotics, 35(4): 789-802, , 2019

10. A note on two problems in connection with graphs, Dijkstra, E. W., 1(1): 269-271, , 1959

11. Dual-Mode Robots for Search and Rescue Missions., Ha, S. and, Park, J., 36(6): 1025-1045, , 2019

12. Omnidirectional Wheel Systems for Robotic Mobility, Hoffman, H. et al, 33(4): 556-572, , 2014

13. The dynamic window approach to collision avoidance, Fox, D., Burgard, W., and Thrun, S., 4(1): 23- 33, , 1997

14. Research in autonomous agriculture vehicles in Japan, Torii, T., 25(1-2): 133-153, , 2000

15. A comprehensive study for robot navigation techniques, Gul, F., Rahiman, W. and Nazli Alhady, S. S., 6(1): 1632046, , 2019

16. Behavior-based formation control for multirobot teams, Balch, T., and Arkin, R. C., 14(6): 926-939, , 1998

17. Cooperative, mobile robotics: Antecedents and directions, Cao, Y. U., Fukunaga, A. S., and Kahng, A. B, 4(1): 7-27, , 1997

18. ORB-SLAM: a versatile and accurate monocular SLAM system, Mur-Artal, R., Montiel, J. M. M., and Tardos, J. D., 31(5): 1147-1163, , 2015

19. ROS-based unmanned mobile robot platform for agriculture, Im, D. Y., Baek, E. T. and, 12(9): 4335, , 2022

20. The potential role of GIS in autonomous field operations, Blackmore, B. S., Thomas, G. and, Earl, R., 25(1-2): 107-120, , 2000

21. HyLander: A Hybrid Locomotion System for Enhanced Mobility, Kim, J. et al, 39(3): 123-145, , 2020

22. Adaptive artificial potential fields for multi-robot systems, Gonzalez, R., and Adorno, B. V., 68(1): 3-19, , 2012

23. Numerical potential field techniques for robot path planning, Barraquand, J., Langlois, B., and Latombe, J. C., 22(2): 224-241, , 1992

24. Voice Controlled Mobile Applications Using Google Speech API, Ramesh, M. V. and, Kannan, K., 118(24): 1-12, , 2018

25. Localization and mapping in GPS-denied greenhouse environments, Dietmayer, K., Müller, A., Schreiber, M. and, 5(2): 2458-2465, , 2020

26. Real-time obstacle avoidance for manipulators and mobile robots, Khatib, O, 5(1): 90-98, , 1986

27. Autonomous navigation using a robot platform in a sugar beet field, Bakker, T., van Asselt, K., Bontsema, J., Müller, J. and van Straten, G., 109(4): 357-368, , 2011

28. A formal basis for the heuristic determination of minimum cost paths, Nilsson, N. J., Hart, P. E., Raphael, B., 4(2): 100-107, , 1968

29. ALLIANCE: An architecture for fault-tolerant multi-robot cooperation, Parker, L. E., 14(2): 220-240, , 1998

30. Autonomous agricultural robots: Current trends and future challenges, Milella, A. and, Reina, G., Nielsen, M., Computers and Electronics in Agriculture, 142: 94-104, , 2017

31. Obstacle avoidance and path planning for autonomous greenhouse robots, Krause, J., Rösmann, C., Müller, A. and, 36(4): 765-782, , 2019

32. Voronoi diagrams—a survey of a fundamental geometric data structure, Aurenhammer, F., ACM Computing Surveys (CSUR), 23(3): 345-405, , 1991

33. Coordinating hundreds of cooperative, autonomous vehicles in warehouses, D'Andrea, R. and, Wurman, P. R., Mountz, M., AI Magazine, 29(1): 9-20, , 2008

34. A multi-state constraint Kalman filter for vision-aided inertial navigation, Mourikis, A. I., and Roumeliotis, S. I, pp. 3565-3572, , 2007

35. A novel tracking control method based on LADRC for autonomous mobile robots, Han, W., Yuan, P., Chen, D., Li, Y., Lai, T., Lin, M., Shi, Z. and Wang, T., 501-506, , 2015

36. Plant detection and mapping for agricultural robots using a 3D LIDAR sensor, Weiss, U. and Biber, P., 59(5): 265-273, , 2011

37. Improved techniques for grid mapping with Rao-Blackwellized particle filters, Grisetti, G., Stachniss, C., and Burgard, W., 23(1): 34-46, , 2007

38. Trajectory modification considering dynamic constraints of autonomous robots, Rösmann, C., Feiten, W., Wösch, T., Hoffmann, F., and Bertram, T., 1-6, , 2012

39. Stability Analysis and Navigational Techniques of Wheeled Mobile Robot: A Review, Borkar, K. K., Aljrees, T., Pandey, S. K., Kumar, A., Singh, M. K., Sinha, A., Singh, K. U. and Sharma, V., 11(12): 3302, , 2023

40. A tutorial on Hidden Markov Models and selected applications in speech recognition, Rabiner, L. R., 77(2): 257-286, , 1989

41. Collaborative path planning and task allocation for multiple agricultural machines, Wang, N., Yang, X., Wang, T., Xiao, J., Zhang, M., Wang, H. and Li, H., 213: 108218, , 2023

42. On global uniform asymptotic stability of nonlinear time-varying systems in cascade, Panteley, E. and Loria, A., 33(2): 131-138, , 1998

43. Harvesting robots for high-value crops: State-of-the-art review and challenges ahead, Bac, C. W., Van Henten, E. J., Hemming, J., and Edan, Y, 31(6): 888-911, , 2014

44. Integrated indoor positioning system of greenhouse robot based on uwb/imu/odom/lidar, Long, Z., Xiang, Y., Lei, X., Li, Y., Hu, Z. and Dai, X., 22(13): 4819, , 2022

45. Autonomous navigation system for greenhouse tomato picking robots based on laser SLAM, Liu, K., Yu, J., Huang, Z., Liu, L. and Shi, Y., 100: 208-219, , 2024

46. Comparing ICP variants on real-world data sets: Open-source library and experimental protocol, Pomerleau, F., Colas, F., Siegwart, R. and Magnenat, S., 34: 133-148, , 2013

47. Motion Planning Method for Car-Like Autonomous Mobile Robots in Dynamic Obstacle Environments, Wang, Z., Li, P., Li, Q., Wang, Z. and Li, Z., 11: 137387-137400, , 2023

48. Design and experiment with a greenhouse self-balancing mobile robot based on a PR joint sensor, Zhang, D., Zhang, Y., Song, Y., Yang, L., Lu, F., Cui, T., Zhang, K., He, X. and, 13(10):2040, , 2023

49. Field evaluation of path-planning algorithms for autonomous mobile robots in intelligent farms, Kim, J., Park, Y. and Son, H. I., Pak, J.,, 10: 60253-60266, , 2022

50. System Design, Analysis, and Control of an Intelligent Vehicle for Transportation in Greenhouse, Xu, X., Wu, C., Tang, X. and, 13(5): 1020, , 2023

51. An Autonomous Navigation Framework for Holonomic Mobile Robots in Confined Agricultural Environments, Tsiakas, K., Papadimitriou, A., Pechlivani, E. M., Giakoumis, D., Frangakis, N., Gasteratos, A. and Tzovaras, D., 12(6): 146, , 2023

52. Performance evaluation of vision-based path planning for dynamic real-time scenarios of mobile robots, Karthikeyan, R., Singh, A., Sridhar, Y., Kalaichelvi, V. and, Multimedia Tools and Applications: 1-24, , 2024

53. An improved timed elastic band (TEB) algorithm of autonomous ground vehicle (AGV) in complex environment, Wu, J., Wang, H., Peng, T. and, Ma, X., 21(24): 8312, , 2021

54. Developing an autonomous navigation system using a two-dimensional laser scanner in an orchard application, Barawid Jr, O. C., Mizushima, A., Ishii, K. and Noguchi, N., 96(2): 139-149, , 2007

55. Impact of rice nursery nutrient management, seeding density and seedling age on yield and yield attributes, Adhikari, B., Mehera, B., and Haefele, S., vol. 4, no. 12, 2013, pp. 146-155, , 2013

56. Improving grid-based SLAM with Rao-Blackwellized particle filters by adaptive proposals and selective resampling, Grisetti, G., Stachniss, C., and Burgard, W., 2432-2437, , 2005

57. A smart city application: A fully controlled street lighting isle based on wireless technology and UWB localization, Leccese, F., Cagnetti, M., and Trinca, D., 17(10): 2275, , 2017

58. Wheeled mobile robots: state of the art overview and kinematic comparison among three omnidirectional locomotion strategies, Tagliavini, L., Colucci, G., Botta, A., Cavallone, P., Baglieri, L. and Quaglia, G., 106(3): 57, , 2022

59. Design and experiment with a SLAM system for low-density canopy environments in greenhouses based on an improved Cartographer framework, Tan, H., Zhao, X., Zhai, C., Fu, H., Chen, L. and Yang, M., 15: 1276799, , 2024