STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Advancements in Robotics Original Research

Enhancing Robot Autonomy: Integrating AI for Advanced Decision-making in Autonomous Robotic Systems

  1. Mritunjay Kr. Ranjan School of Computer Sciences and Engineering, Sandip University Nashik, Nashik
  2. Ashish Singh School of Computer Sciences and Engineering, Sandip University Nashik, Nashik
  3. Pankaj Patil School of Computer Sciences and Engineering, Sandip University Nashik, Nashik
  4. Aniket Anand Dept. of Computer Science and Information Technology, Magadh University, Bodh Gaya
  5. Mansi P. Mahajan School of Computer Sciences and Engineering, Sandip University Nashik, Nashik
  6. Shilpi Saxena Department of Computer Application & IT, Lords University, Alwar

Abstract

The capabilities of autonomous robotic systems have been drastically changed by the rapid progress in artificial intelligence (AI) technologies. In this work, we investigate the integration of AI approaches to improve robot autonomy by presenting even more advanced mechanisms for decision-making. Almost all traditional robotic systems involve predefined algorithms, making them unable to cope with dynamic environments. They can also help with learning based on machine learning and deep learning methodologies to make use of experience and make themselves flexible and efficient over a period. In this work, a model is proposed that combines reinforcement learning with real-time sensory data processing to allow autonomous robots to react in unfamiliar situations. We explain several AI models as well as how effective they are in practical use cases such as autonomous navigation, obstacle avoidance, and task optimization in addition, we consider the attendant ethical consequences and practical issues that arise when AI is used for making decisions within robotics systems in terms of safety requirements. We have confirmed that the performance of AI-driven robotic systems is improved over conventional methods through simulations and experimental results. The work represents an important step for AI in enabling the future creation of smarter, more capable robots that can properly function within complex dynamic environments. The decision-making skills of autonomous robotic systems have been transformed by the incorporation of AI, allowing for increased adaptability in dynamic contexts. This study introduces a novel paradigm to enhance robot autonomy in novel scenarios by fusing real-time sensory data processing with reinforcement learning. In real-world applications like task optimization, obstacle avoidance, and autonomous navigation, we evaluate how well different AI models perform.

Keywords

References (18)

  1. Beer JM, Fisk AD, Rogers WA. Toward a Framework for Levels of Robot Autonomy in Human-Robot Interaction. Journal of Human-Robot Interaction. 2014;3(2):74. doi:10.5898/jhri.3.2.beer
  2. Saxena S, Ranjan MK, Sattar AM. Brain-Computer Interfaces. 2024 1st International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU), Bhubaneswar, India. 2024. pp. 1–8. doi:10.1109/IC-CGU58078.2024.10530664.
  3. Ranjan MK, Roy K, Mahind A, Bhavsar D, Nemade S, Sattar AM. Unlocking the Potential: Machine Learning Driven Explainable AI Applications Across Diverse Domains. International Journal of Software Computing and Testing. 2023. doi:10.37628/ijosct.v9i1.948
  4. Ranjan MK, Sattar AM, Tiwari SK. Blockchain in Healthcare Systems. Advances in Healthcare Information Systems and Administration. 2023:238-259. doi:10.4018/978-1-6684-8913-0.ch010
  5. Ho TM, Nguyen KK, Cheriet M. Federated Deep Reinforcement Learning for Task Scheduling in Heterogeneous Autonomous Robotic System. IEEE Transactions on Automation Science and Engineering. 2024;21(1):528-540. doi:10.1109/tase.2022.3221352
  6. Al-Rahmani N, Mohan DM, Awad MI, Wasti SA, Hussain I, Khalaf K. Lower-limb robotic assistance devices for drop foot: A review. IEEE Access. 2022;10:51964–94. DOI: 10.1109/ 2022.3174686.
  7. Le NMD, Nguyen NH, Nguyen DA, Ngo TD, Ho VA. ViART: Vision-Based Soft Tactile Sensing for Autonomous Robotic Vehicles. IEEE/ASME Transactions on Mechatronics. 2024;29(2):1420-1430. doi:10.1109/tmech.2023.3301022
  8. Li K, Xu Y, Meng MQH. An overview of systems and techniques for autonomous robotic ultrasound acquisitions. IEEE Trans Med Robot Bionics. 2021;3:510–24. doi:10.1109/TMRB. 3072190.
  9. Alwala A, El-Hussieny H, Mohamed A, Iwasaki K, Assal SFM. Hybrid Impedance Control-based Autonomous Robotic System for Natural-like Drinking Assistance for Disabled Persons. International Journal of Control, Automation and Systems. 2023;21(6):1978-1992. doi:10.1007/s12555-022-0690-7
  10. Lins RG, Givigi SN. FPGA-Based Design Optimization in Autonomous Robot Systems for Inspection of Civil Infrastructure. IEEE Systems Journal. 2020;14(2):2961-2964. doi:10.1109/jsyst.2019.2960309
  11. Kober J, Bagnell JA, Peters J. Reinforcement learning in robotics: A survey. The International Journal of Robotics Research. 2013;32(11):1238-1274. doi:10.1177/0278364913495721
  12. Jiang Z, Xu D, Liang J. A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem. arXiv Preprint ArXiv:1706.10059. 2017.
  13. Garcia F, Rachelson E. Markov decision processes. In: Sigaud O, Buffet O, editors. Markov Decision Processes in Artificial Intelligence. John Wiley & Sons; 2013. p. 1–38. doi:10.1002/9 ch1.
  14. Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O. Proximal policy optimization algorithms. arXiv.org. 2017. Available from: https://arxiv.org/abs/1707.06347. doi:10.48550/arXiv.1707.
  15. Steyvers M, Kumar A. Three Challenges for AI-Assisted Decision-Making. Perspectives on Psychological Science. 2023;19(5):722-734. doi:10.1177/17456916231181102
  16. Bojić L, Cinelli M, Ćulibrk D, Delibašić B. CERN for AI: a theoretical framework for autonomous simulation-based artificial intelligence testing and alignment. European Journal of Futures Research. 2024;12(1). doi:10.1186/s40309-024-00238-0
  17. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine. 2019;25(1):44-56. doi:10.1038/s41591-018-0300-7
  18. Crandall JW, Cummings ML. Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction. ACM; 2007. p. 33–40. doi:10.1145/1228716.1228722.
Support