pubmed.ncbi.nlm.nih.gov

Cognitive Control Architecture for the Practical Realization of UAV Collision Avoidance - PubMed

  • ️Mon Jan 01 2024

Cognitive Control Architecture for the Practical Realization of UAV Collision Avoidance

Qirui Zhang et al. Sensors (Basel). 2024.

Abstract

A highly intelligent system often draws lessons from the unique abilities of humans. Current humanlike models, however, mainly focus on biological behavior, and the brain functions of humans are often overlooked. By drawing inspiration from brain science, this article shows how aspects of brain processing such as sensing, preprocessing, cognition, obstacle learning, behavior, strategy learning, pre-action, and action can be melded together in a coherent manner with cognitive control architecture. This work is based on the notion that the anti-collision response is activated in sequence, which starts from obstacle sensing to action. In the process of collision avoidance, cognition and learning modules continuously control the UAV's repertoire. Furthermore, simulated and experimental results show that the proposed architecture is effective and feasible.

Keywords: anti-collision; cognitive control architecture; conditioned reflex; unmanned aerial vehicles.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1

Brain pathway of the conditioned reflex cycle in the human anti-collision response.

Figure 2
Figure 2

The cognitive control architecture of a UAV.

Figure 3
Figure 3

The architecture of the RBN for an anti-collision response.

Figure 4
Figure 4

The hierarchical RBN model of the trust region, flight path, and waypoints.

Figure 5
Figure 5

A brain-like conditioned reflex cycle in cognitive UAVs.

Figure 6
Figure 6

Structure of obstacle-avoidance mapping.

Figure 7
Figure 7

Improved structure of obstacle-avoidance mapping.

Figure 8
Figure 8

Gridding model of a UAV.

Figure 9
Figure 9

The 12 diverse training samples.

Figure 10
Figure 10

The relation between developmental knowledge and the training samples.

Figure 11
Figure 11

Comparison of CR and AC among crowded obstacles.

Figure 12
Figure 12

Comparison of CR and CG among crowded obstacles.

Figure 13
Figure 13

The UAV’s perception model.

Figure 14
Figure 14

The selected equipment and materials of the UAV.

Figure 15
Figure 15

A UAV’s anti-collision response to one obstacle.

Figure 16
Figure 16

Anti-collision test in the constructed right-angle-obstacle environment.

Figure 17
Figure 17

Anti-collision test in the constructed horizontal-obstacle environment.

Similar articles

References

    1. Amin J.N., Boskovic J.D., Mehra K. A Fast and Efficient Approach to Path Planning for Unmanned Vehicles; Proceedings of the AIAA Guidance, Navigation, and Control Conference; Keystone, Colorado. 21–24 August 2006.
    1. Czubenko M., Kowalczuk Z., Ordys A. Autonomous Driver Based on an Intelligent System of Decision-Making. Cogn. Comput. 2015;7:569–581. doi: 10.1007/s12559-015-9320-5. - DOI - PMC - PubMed
    1. Wei R., Zhang Q., Xu Z. Peers’ Experience Learning for Developmental Robots. Int. J. Soc. Robot. 2019;12:35–45. doi: 10.1007/s12369-019-00531-0. - DOI
    1. Zhang Q., Wei R. Unmanned aerial vehicle perception system following visual cognition invariance mechanism. IEEE Access. 2019;7:45951–45960. doi: 10.1109/ACCESS.2019.2909098. - DOI
    1. Beard R.W., McLain T.W. Trajectory Planning for Coordinated Rendezvous of Unmanned Air Vehicles; Proceedings of the AIAA Guidance, Navigation, and Control Conference and Exhibit; Denver, CO, USA. 14–17 August 2000.

LinkOut - more resources