REVIEW OF VIBRATION-BASED SURFACE & TERRAIN CLASSIFICATION FOR WHEEL-BASED ROBOT IN PALM OIL PLANTATION: 27th October 2022; 13th December 2022; 21st January 2023; 23rd January 2023

Bukhary Ikhwan Ismail; Hishamadie Ahmad; Shahrol Hisham Baharom; Mohammad Fairus Khalid; Muhammad Nurmahir Mohamad Sehmi

doi:10.20319/mijst.2023.9.3548

Authors

Bukhary Ikhwan Ismail Senior Staff Researcher, Industrial Autonomy, IoT Systems, MIMOS Berhad, Kuala Lumpur, Malaysia
Hishamadie Ahmad Senior Engineer, Industrial Autonomy, IoT Systems, MIMOS Berhad, Kuala Lumpur, Malaysia
Shahrol Hisham Baharom Staff Engineer, Industrial Autonomy, IoT Systems, MIMOS Berhad, Kuala Lumpur, Malaysia
Mohammad Fairus Khalid Principal Engineer, Industrial Autonomy, IoT Systems, MIMOS Berhad, Kuala Lumpur, Malaysia
Muhammad Nurmahir Mohamad Sehmi Engineer, Industrial Autonomy, IoT Systems, MIMOS Berhad, Kuala Lumpur, Malaysia

DOI:

https://doi.org/10.20319/mijst.2023.9.3548

Keywords:

Robot, Surface Classification, Terrain Classification, Vibration, Palm Oil, Plantation

Abstract

Palm oil can grow in almost flexible topography. On flats, slopes, hilly, or undulating areas and whether on inland or reclaimed coastal areas. This makes the palm oil plantation environment unique with various soil types & surfaces. Each surface has a unique physical characteristic that directly influences the driving, handling, power efficiency, stability and safety of a robot. A mobile robot should have knowledge not limited to obstacles, but also the surface that the robot traverses to estimate wheel slippage and apply corrective measures. This paper discusses the harshness factors in palm oil plantation estates and the effects on wheel traction. We then present our review of several vibration-based surface classification techniques. Based on our survey, a combination of multimodal sensory for surface classification is more suitable to identify surfaces and terrain in palm oil plantations.

References

Aini, I. N., Aimrun, W., Amin, M. S. M., Ezrin, M. H., & Shafri, H. Z. (2014). Auto guided oil palm planter by using multi-GNSS. IOP Conference Series: Earth and Environmental Science, 20(1). https://doi.org/10.1088/1755-1315/20/1/012013

Bai, C., Guo, J., Guo, L., & Song, J. (2019). Deep multi-layer perception-based terrain classification for planetary exploration rovers. Sensors (Switzerland), 19(14), 1–18. https://doi.org/10.3390/s19143102

Bhd, M. Sdn. (n.d.). Plantation Inventory using UAV or Satellite Images | Professional Drone/UAV/LiDAR Mapping Services. http://myspatial.com.my/services/gis-database-development/gis-data-development-for-oil-palm-plantation/plantation-inventory-using-uav-or-satellite-images/

Concon, M., Wong, W. K., Juwono, F. H., & Apriono, C. (2021). Deep learning for terrain surface classification: Vibration-based approach. CEUR Workshop Proceedings, 2786, 237–243.

Deraman, M. S., Abd Rahim, S., Zaprunnizam, M. A., Aminulrashid, M., & Hartini, M. H. (2013). Rhyno: A Multipurpose Wheel type transporter for oil palm Activities on undulating terrain and soggy Areas. MPOB Information Series TT No. 535, June, 29–32.

DuPont, E. M., Moore, C. A., Collins, E. G., & Coyle, E. (2008). Frequency response method for terrain classification in autonomous ground vehicles. Autonomous Robots 2007 24:4, 24(4), 337–347. https://doi.org/10.1007/S10514-007-9077-0

Giguere, P., & Dudek, G. (2011). A simple tactile probe for surface identification by mobile robots. IEEE Transactions on Robotics, 27(3), 534–544. https://doi.org/10.1109/TRO.2011.2119910

Gonzalez, R., & Iagnemma, K. (2018). DeepTerramechanics: Terrain Classification and Slip Estimation for Ground Robots via Deep Learning. http://arxiv.org/abs/1806.07379

Khalid, M. R., Shuib, A. R., & Kamarudin, N. (2021). Mechanising oil palm loose fruits collection - A review. Journal of Oil Palm Research, 33(1), 1–11. https://doi.org/10.21894/jopr.2020.0069

Masha, D., & Burke, M. (2021). Importance Sampling Forests for Location Invariant Proprioceptive Terrain Classification. Communications in Computer and Information Science, 1342, 154–168. https://doi.org/10.1007/978-3-030-66151-9_10

Mei, M., Chang, J., Li, Y., Li, Z., Li, X., & Lv, W. (2019). Comparative study of different methods in vibration-based terrain classification for wheeled robots with shock absorbers. Sensors (Switzerland), 19(5). https://doi.org/10.3390/s19051137

Muhamad, Z.-M., & Aziz, M. F. A. (2018). Mechanization in Oil Palm Harvesting. International Journal of Academic Research in Business and Social Sciences, 8(5), 246–255. https://doi.org/10.6007/ijarbss/v8-i5/4098

Otsu, K., Ono, M., Fuchs, T. J., Baldwin, I., & Kubota, T. (2016). Autonomous Terrain Classification with Co-and Self-Training Approach. IEEE Robotics and Automation Letters, 1(2), 814–819. https://doi.org/10.1109/LRA.2016.2525040

Sattar, S., Li, S., & Chapman, M. (2018). Road surface monitoring using smartphone sensors: A review. Sensors (Switzerland), 18(11). https://doi.org/10.3390/s18113845

Sayed, M. E., Nemitz, M. P., Aracri, S., McConnell, A. C., McKenzie, R. M., & Stokes, A. A. (2018). The limpet: A ROS-enabled multi-sensing platform for the ORCA hub. Sensors (Switzerland), 18(10), 1–23. https://doi.org/10.3390/s18103487

Shuib, A. R., Md Radzi, M. K. F., Mohamed, A., & Mohd Khalid, M. R. (2020). Evaluation of Soil Stabilizer in Oil Palm Plantation Road Construction. Advances in Agricultural and Food Research Journal, 1(2), 1–13. https://doi.org/10.36877/aafrj.a0000122

Woittiez, L. S. (n.d.). Sustainable Oil Palm Farming - Akvopedia. https://akvopedia.org/wiki/Sustainable_Oil_Palm_Farming

Yi, C. W., Chuang, Y. T., & Nian, C. S. (2015). Toward Crowdsourcing-Based Road Pavement Monitoring by Mobile Sensing Technologies. IEEE Transactions on Intelligent Transportation Systems, 16(4), 1905–1917. https://doi.org/10.1109/TITS.2014.2378511

Fair, J. (2020). Investigation begins into alleged deforestation by Olam, ‘world’s largest farmer.’ https://www.eco-business.com/news/investigation-begins-into-alleged-deforestation-by-olam-worlds-largest-farmer/