A method to evaluate the autonomic control capability of a mobile robot

An actual task is to evaluate the capabilities of the mobile robot control system that ensures the robot’s autonomous operation. Such an analysis not only allows for the determination of the current capabilities of the robot control system but also helps identify areas for its further improvement, leading to increased overall efficiency and stability of autonomous robots in real-world operational scenarios. This paper is dedicated to developing a method for evaluating the capability of a mobile robot’s autonomous control. To achieve this aim, an analysis of existing approaches for determining the level of autonomy in unmanned systems was conducted, and a correspondence was established between the evaluation values of the mobile robot’s autonomous control capabilities and specific levels of the robot’s autonomy. The dependence of this evaluation on the assessment of autonomous control capabilities during the robot’s execution of particular tasks was also determined. A relationship was identified between the value of the autonomous control assessment when performing a given task and the probabilities of various autonomy subtypes of the control system, which, in turn, depend on operating conditions. The results show that autonomy, defined as the capacity of a robotic system to perform assigned tasks independently, is invariably governed by the robot’s technical characteristics and the environmental conditions. Augmentation of the technical and informational-algorithmic resources of the control system, in conjunction with increasing its degree of independence from human operators — assuming that environmental complexity and task difficulty either remain constant or decrease — serves to significantly enhance the probability of achieving successful autonomous control during task execution. In cases of maximum independence from the operator, when the control system’s resources match the environmental and task complexity levels, or when resources are abundant, the assessment of autonomous control capability is based on the availability of technical and informational-algorithmic resources within the robot’s control system.
EDN: HHEOSW, https://elibrary/hheosw

References

[1] Ermolov I.L. Rasshirenie funktsionalnykh vozmozhnostey mobilnykh tekhnologicheskikh robotov putem povysheniya urovnya ikh avtonomnosti s ispolzovaniem ierarkhicheskoy kompleksnoy obrabotki bortovykh dannykh. Diss. dok. tekh. nauk [Expanding the functionality of mobile technological robots by increasing their level of autonomy using hierarchical integrated processing of on-board data. Kand. tech. sci. diss.]. Moscow, MGTU Stankin Publ., 2012. 350 p. (In Russ.).

[2] Huang H.-M., Messina E., Wade R. et al. Autonomy measures for robots. IMECE, 2004, paper IMECE2004-61812, pp. 1241–1247; doi: https://doi.org/10.1115/IMECE2004-61812

[3] Huang H.-M., Pavek K., Albus J. et al. Autonomy levels for unmanned systems (ALFUS) framework: an update. Proc. SPIE, 2005, vol. 5804, doi: https://doi.org/10.1117/12.603725

[4] Huang H.-M., Messina E., Albus J. Autonomy levels for unmanned systems (ALFUS) framework. Vol. II: Framework models version 1.0. NIST, 2007, 73 p.

[5] Borkar S., Chien A.A. The future of microprocessors. CACM, 2011, vol. 54, no. 5, pp. 67–77, doi: https://doi.org/10.1145/1941487.1941507

[6] Mikołajczyk T., Mikołajewski D., Kłodowski A. et al. Energy sources of mobile robot power systems: a systematic review and comparison of efficiency. Appl. Sci., 2023, vol. 13, no. 13, art. 7547, doi: https://doi.org/10.3390/app13137547

[7] Zidar J., Matić T., Aleksi I. et al. Dynamic voltage and frequency scaling as a method for reducing energy consumption in ultra-low-power embedded systems. Electronics, 2024, vol. 13, no. 5, art. 826, doi: https://doi.org/10.3390/electronics13050826

[8] Das R., Gupta V. A systematic literature review on graphics processing unit accelerated realm of high-performance computing. IJCE, 2024, vol. 5, no. 3, pp. 10–21, doi: https://doi.org/10.47941/ijce.1813

[9] Lane D.M., Sahafi A. ADNA: automating application-specific integrated circuit development of neural network accelerators. Electronics, 2025, vol. 14, no. 7, art. 1432, doi: https://doi.org/10.3390/electronics14071432

[10] Dastres R., Soori M. A review in advanced digital signal processing systems. IJECE, 2021, vol. 15, no. 3, pp. 122–127, doi: https://doi.org/10.6084/M9.FIGSHARE.14330879

[11] Rostum H.M., Hammami N., Salih O.M. FPGA implementation in mobile robot applications: state of the art review. Multidisciplinary Sciences, 2023, vol. 13, no. 2, pp. 232–249, doi: https://doi.org/10.35925/j.multi.2023.2.21

[12] Gao M., Chen H., Liu D. An ASIP for neural network inference on embedded devices with 99% PE utilization and 100% memory hidden under low silicon cost. Sensors, 2022, vol. 22, no. 10, art. 3841, doi: https://doi.org/10.3390/s22103841

[13] Cirstea M., Benkrid K., Dinu A. et al. Digital electronic system-on-chip design: methodologies, tools, evolution, and trends. Micromachines, 2024, vol. 15, no. 2, art. 247, doi: https://doi.org/10.3390/mi15020247

[14] Hameed Ul Hassan Mohammed. Chiplet-based architectures: redefining the future of System-on-Chip (SoC) design. IJCNIS, 2025, vol. 17, no. 7, pp. 15–29.

[15] Alsadik B., Karam S. The simultaneous localization and mapping (SLAM)-an overview. JASTT, 2021, vol. 2, no. 4, pp. 147–158, doi: https://doi.org/10.38094/jastt204117

[16] Placed J.A., Strader J., Carrillo H. et al. A survey on active simultaneous localization and mapping: state of the art and new frontiers. IEEE Trans. Robot., 2023, vol. 39, no. 3, pp. 1686–1705, doi: https://doi.org/10.1109/TRO.2023.3248510

[17] Qiao J., Guo J., Li Y. Simultaneous localization and mapping (SLAM)-based robot localization and navigation algorithm. Appl. Water Sci., 2024, vol. 14, no. 7, art. 151, doi: https://doi.org/10.1007/s13201-024-02183-6

[18] Bezmen P.A. The study of the convergence rate of the algorithm extended Kalman filter — adaptive digital filter system. Izvestiya vysshikh uchebnykh zavedeniy. Mashinostroenie [BMSTU Journal of Mechanical Engineering], 2025, no. 9, pp. 11–20. EDN: QZXTMB (In Russ.).

[19] Soori M., Arezoo B., Dastres R. Artificial intelligence, machine learning and deep learning in advanced robotics, a review. COGR, 2023, vol. 3, pp. 54–70, doi: https://doi.org/10.1016/j.cogr.2023.04.001

[20] Yeom K. Design of deep neural network based model predictive controller for a car-like mobile robot. Int. J. Mech. Eng. Robot. Res., 2022, vol. 11, no. 8, pp. 606–613, doi: https://doi.org/10.18178/ijmerr.11.8.606-613