Autonomous navigation for unmanned ground vehicles in nstructured terrain

• Autorzy: Nowakowski Marek

Identyfikatory

DOI

10.34739/si.2024.31.09

• Języki publikacji: EN

Abstrakty

EN

The problem of autonomous navigation for Unmanned Ground Vehicles (UGVs) in unstructured environments is both challenging and crucial for their deployment in real-world applications. Perception is important, as it provides the necessary information for terrain traversability and environmental awareness. In this article, the developed manned-unmanned vehicle designed to carry out autonomous missions in unstructured terrain is presented, along with the system requirements essential for such operations. Challenges related to environmental perception and navigation in unstructured environments are discussed. Achievements in developing AI models capable of interpreting sensor data are highlighted, demonstrating significant progress in the field of autonomous navigation. However, several gaps remain, particularly in the areas of sensor fusion, real-time decision-making, and adaptability to highly dynamic conditions. Development in the field of autonomous systems allows for a wider expansion of the potential applications ofUGVs in various fields, including disaster response, environmental monitoring, and exploration of hazardous environments.

Słowa kluczowe

EN

autonomous systems; unmanned ground vehicles navigation; unstructured terrain

• Wydawca: Wydawnictwo Uniwersytetu Przyrodniczo-Humanistycznego w Siedlcach
• Czasopismo: Studia Informatica : systems and information technology
• Rocznik: 2024
• Tom: vol. 2 (31)
• Strony: 117--121
• Opis fizyczny: Bibliogr. 10 poz., fot., rys.

Twórcy

autor

Nowakowski Marek

• Military Institute of Armoured and Automotive Technology, ul. Okuniewska 1, 05-070 Sulejówek, Poland

• https://orcid.org/0000-0003-3864-076X

Bibliografia

• 1. Ni, Jun, Jibin Hu, and Changle Xiang. A review for design and dynamics control of unmanned groundvehicle. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of AutomobileEngineering 235.4 (2021): 1084-1100.
• 2. Rossiter, Ash. Bots on the ground: an impending UGV revolution in military affairs?. Robotics,Autonomous Systems and Contemporary International Security. Routledge, 2020.
• 3. Ginerica, C.; Zaha, M.; Floroian, L.; Cojocaru, D.; Grigorescu, S. A Vision DynamicsLearning Approach to Robotic Navigation in Unstructured Environments. Robotics 2024. https://doi.org/10.3390/robotics13010015
• 4. Grigorescu, S.; Trasnea, B.; Cocias, T.; Macesanu, G. A survey of deep learning techniques forautonomous driving. pp.362-386 J. Field Robot. 2020.
• 5. Guastella, D.C.; Muscato, G. Learning-Based Methods of Perception and Navigationfor Ground Vehicles in Unstructured Environments: A Review. Sensors 2021, 21, 73. https://doi.org/10.3390/s21010073
• 6. Rothrock, B.; Kennedy, R.; Cunningham, C.; Papon, J.; Heverly, M.; Ono, M. SPOC: Deep Learning-based Terrain Classification for Mars Rover Missions. In Proceedings of the AIAA SPACE 2016,Long Beach, CA, USA, 13-16 September 2016.
• 7. Chavez-Garcia, R.O.; Guzzi, J.; Gambardella, L.M.; Giusti, A. Learning Ground Traversability FromSimulations. IEEE Robot. Autom. Lett. 2018, 3, 1695-1702.
• 8. Holder, C.J.; Breckon, T.P. Learning to Drive: Using Visual Odometry to Bootstrap Deep Learningfor Off-Road Path Prediction. pp. 2104-2110 In Proceedings of the 2018 IEEE Intelligent VehiclesSymposium (IV), Changshu, China, 26-30 June 2018.
• 9. Zhang, Yuxiao, et al. Perception and sensing for autonomous vehicles under adverse weather conditions: A survey.pp.146-177 ISPRS Journal of Photogrammetry and Remote Sensing 196 (2023).
• 10. Gao, X., Roy, S., Xing, G., 2021. MIMO-SAR: A hierarchical high-resolution imaging algorithmfor mmwave FMCW radar in autonomous driving.pp.7322-7334 IEEE Trans. Veh. Technol. 70.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).