CONTINUOUS PLANNING AND SITUATIONAL CONTROL AS AN FEELING ARTIFICIAL INTELLIGENCE TASK

Authors

  • Anatolii Kargin
  • Dmytro Hiievskyi
  • Dmytro Oliinyk

DOI:

https://doi.org/10.26906/SUNZ.2024.2.106

Keywords:

Autonomous intelligent unmanned systems, Feeling Artificial Intelligence, continuous planning, situational control

Abstract

Motivation Despite significant progress in the field of creating unmanned systems, ensuring the necessary level of their autonomy remains an urgent task. Artificial intelligence plays an important role in its solution. Features of unmanned systems have given rise to a new model of Feeling Artificial Intelligence (FAI) that supports autonomy. The goal of this work is to develop an algorithm that supports the model of continuous planning and situational control implemented in the Goal-Directed Control system of FAI. The object of research is the methods and models of controlling autonomous mobile robots based on data from various sensors. Results. The peculiarity of the task of autonomous mobile robots control is that they use the state of execution of the plan, the current situation and the possibility of executing the remaining part o f the action plan to achieve the goal in order to make a decision in real time regarding the current actions. The struc ture of a multilevel distributed system of fuzzy rules in combination with a system of production planning rules is given. A modified mechanism of fuzzy inference is considered, which, thanks to the introduction of a certainty factor, is able to process b oth facts about the state of the environment and the state of plan execution. The continuous planning algorithm and examples of control calculations are given. Conclusions. It is shown that the modification of the traditional mechanism of logical reasoning in fuzzy logic systems, firstly, by introducing a context memory containing contextual facts, and secondly, the representation o f the state of facts, as well as the values of the input variables in the form of fuzzy certainty factors, allows applying them for autonomous intelligence unmanned system control and take full advantage of fuzzy control in handling uncertainty. The development of a traditional fuzzy system aimed at managing the implementation of an action plan for an autonomous robot, taking into account the above conditions, characterized by a significant number of input numerical variables from sensors, is an intractable task. The proposed model, which consists of components of two types of systems, fuzzy systems with linguistic variables and fuzzy production systems with certainty factors, overcomes the listed problems and preserves the advantages of traditional fuzzy systems in dealing with uncertainty.

Downloads

References

L. Joseph, A.K. Mondal, Eds, Autonomous Driving and Advanced Driver-Assistance Systems (ADAS). Applications, Development, Legal Issues, and Testing. 1st edn. CRC Press, Boca Raton, 2021, doi:10.1201/9781003048381.

“Sikorsky and DARPA's Autonomous Black Hawk Flies Logistics And Rescue Missions Without Pilots On Board,” Lockheed Martin Corporation, 2022, USA, Accessed: Aug. 10, 2023. [Online]. Available: https://news.lockheedmartin.com/2022-11-02-Sikorsky-and-DARPAs-Autonomous-Black-Hawk-R-Flies-Logistics-and-Rescue-Missions-Without-Pilots-on-Board

J. Deichmann et al., “Autonomous driving’s future: Convenient and connected,” McKinsey Center for Future Mobility. Report, Jan. 2023, Accessed: August 15, 2023. [Online]. Available: https://www.mckinsey.com/

H. Chen et al., “From Automation System to Autonomous System: An Architecture Perspective,” J. of Marine Sci. and Eng., vol. 9, no. 6, Jun. 2021, doi: 10.3390/jmse9060645.

Rail Technical Strategy. Innovating across Britain’s railway. Oct. 2022. Accessed: Aug. 10, 2023. [Online]. Available: https://railtechnicalstrategy.co.uk/wp-content/uploads/2022/10/The-Rail-Technical-Strategy.pdf

T. Zhang et al., "Current trends in the development of intelligent unmanned autonomous systems," Frontiers Inf. Technol. Electron. Eng., vol. 18, Feb. 2017, pp. 68–85, doi: 10.1631/FITEE.1601650.

J. Reis, Y. Cohen, N. Melao, J. Costa, and D. Jorge, "High-Tech Defense Industries: Developing Autonomous Intelligent Systems," Appl. Sci. , vol. 11, 4920, 2021, doi: 10.3390/app11114920.

J. Chena, J. Sun, and G.Wang, "From Unmanned Systems to Autonomous Intelligent Systems," Engineering, vol.12, May 2022, pp. 16-19, doi: 10.1016/j.eng.2021.10.007.

M. Czerwinski, J. Hernandez, D. Mcduff, "Building an AI that feels," Appl. Sci., vol.11, 4920, Apr. 2021, doi: 10.3390/app11114920.

M. Huang and R. Rust, "Artificial Intelligence in Service," J. of Service Res., vol. 21(2), Feb. 2018, pp.155-172, doi: 10.1177/1094670517752459.

A. Kargin, T. Petrenko, “Feeling Artificial Intelligence for AI-Enabled Autonomous Systems” in Conf. Proc. of 2022 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Alamein New City, Egypt, 18-21 December 2022, P.88-93..

A. Kargin and T. Petrenko, “Spatio-Temporal Data Interpretation Based on Perceptional Model,” in Advances in Spatio-Temporal Segmentation of Visual Data. Studies in Computational Intelligence, V. Mashtalir, I. Ruban, V. Levashenko, Eds., vol. 876, Springer, Cham, 2020, pp. 101-159.

A. Kargin and T. Petrenko, “Multi-level Computing With Words Model to Autonomous Systems Control,” in Proc. 9th Int. Conf. Inf. Control Sys.&Tech (ICST-2020), A. Pakštas, T. Hovorushchenko, V. Vychuzhanin, H. Yin, N. Rudnichenko. Eds. Odessa, Ukraine, Sep. 24–26, 2020, CEUR Workshop Proceedings, vol. 2711, pp. 16-30. [Online]. Available: http://ceur-ws.org/Vol-2711/

Published

2024-04-30