journal article·2026-04-23

A biologically inspired neural network for optic flow-based reactive navigation with dual depth encoding *

Zipei Li, Lining Yin, Lanyun Cui, Ying Yu, Qingyun Wang

Bioinspiration & Biomimetics· Volume 21· Issue 2
Publisher page

Abstract

Abstract Animals and humans rely on optic flow to navigate cluttered and unknown environments. While most previous studies have focused on how organisms achieve self-motion perception through optic flow information, biological neural networks for navigation based on optic flow remain unexplored. Here, we propose a biologically plausible neural network model for optic flow-based reactive navigation. The model incorporates a primary visual cortex, which is responsible for generating a cortical representation of the optic flow field; a higher-order cortex, which calculates the focus of expansion (FOE) of the optic flow field; and a cerebellum, which generates motor commands. A feedback inhibitory pathway from V1 layer VI to layer IV is introduced, enhancing heading sensitivity and enabling rapid adaptation in dynamic environments. To achieve precise obstacle localization, we propose a dual encoding strategy that combines optic flow with depth maps derived from the optic flow field, FOE, and control acceleration. This strategy mitigates distortions in depth estimation near the expansion center and ensures more reliable obstacle representation. The cerebellum outputs motor commands for heading direction and speed control based on the output of the visual cortex. Simulations and real-world experiments with an intelligent vehicle confirm that the proposed model enables collision-free navigation across diverse scenarios and outperforms classical optic flow balance strategies in complex environments. These findings demonstrate that biologically inspired neural networks provide a feasible solution for visual reactive navigation in autonomous agents.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Visual perception and processing mechanisms · Neurobiology and Insect Physiology Research · Memory and Neural Mechanisms

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (80)

Show source-provided references
1. Browning · 2015 · pp 42510.1002/9783527680863.ch18 ↗
2. A bee in the corridor: centering and wall-following10.1007/s00114-008-0440-6 ↗
3. Vision, perception, navigation and cognition in honeybees and applications to aerial robotics10.1016/j.bbrc.2020.09.052 ↗
4. Floor and ceiling mirror configurations to study altitude control in honeybees10.1098/rsbl.2021.0534 ↗
5. Honeybees change their height to restore their optic flow10.1007/s00359-010-0510-z ↗
6. Altitude control in honeybees: joint vision-based learning and guidance10.1038/s41598-017-09112-5 ↗
7. Honeybees’ speed depends on dorsal as well as lateral, ventral and frontal optic flows10.1371/journal.pone.0019486 ↗
8. Bio-inspired intelligence with applications to robotics: a survey10.20517/ir.2021.08 ↗
9. The perception of the visual world by James J Gibson10.2307/426044 ↗
10. The dynamics of primate retinal ganglion cells10.1016/S0079-6123(01)34003-7 ↗
11. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex10.1113/jphysiol.1962.sp006837 ↗
12. Structure and function of parallel pathways in the primate early visual system10.1113/jphysiol.2005.088047 ↗
13. Receptive fields and functional architecture of monkey striate cortex10.1113/jphysiol.1968.sp008455 ↗
14. Object vision and spatial vision: two cortical pathways10.1016/0166-2236(83)90190-X ↗
15. Structure and function of visual area MT10.1146/annurev.neuro.26.041002.131052 ↗
16. Response of monkey MST neurons to optic flow stimuli with shifted centers of motion10.1523/JNEUROSCI.15-07-05192.1995 ↗
17. Optic flow is used to control human walking10.1038/84054 ↗
18. Vision for mobile robot navigation: a survey10.1109/34.982903 ↗
19. Real-time single-workstation obstacle avoidance using only wide-field flow divergence10.1109/ICPR.1996.546964 ↗
20. Real-time detection of moving objects in a dynamic scene from moving robotic vehicles10.1109/IROS.2003.1248826 ↗
21. Fusion of stereo and optical flow data using occupancy grids10.1109/ITSC.2006.1707392 ↗
22. D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO
24. Optic flow regulation: the key to aircraft automatic guidance10.1016/j.robot.2004.09.016 ↗
25. A biomimetic vision-based hovercraft accounts for bees’ complex behaviour in various corridors10.1088/1748-3182/9/3/036003 ↗
26. Flying over uneven moving terrain based on optic-flow cues without any need for reference frames or accelerometers10.1088/1748-3182/10/2/026003 ↗
27. Accommodating unobservability to control flight attitude with optic flow10.1038/s41586-022-05182-2 ↗
28. A neural model of visually guided steering, obstacle avoidance and route selection10.1037/a0016459 ↗
29. A neural model of how the brain computes heading from optic flow in realistic scenes10.1016/j.cogpsych.2009.07.002 ↗
30. Cortical dynamics of navigation and steering in natural scenes: motion-based object segmentation, heading and obstacle avoidance10.1016/j.neunet.2009.05.007 ↗
31. R-ADVANCE: rapid adaptive prediction for vision-based autonomous navigation, control and evasion10.1002/rob.21744 ↗
32. Range perception through apparent image speed in freely flying honeybees10.1017/S095252380000136X ↗
33. Optical flow based robot obstacle avoidance10.5772/5715 ↗
34. Optic flow-based collision-free strategies: from insects to robots10.1016/j.asd.2017.06.003 ↗
35. Guidance of locomotion on foot uses perceived target location rather than optic flow10.1016/S0960-9822(07)00492-7 ↗
36. Optic flow asymmetries bias high-speed steering along roads10.1167/13.10.23 ↗
37. A GPU-accelerated cortical neural network model for visually guided robot navigation10.1016/j.neunet.2015.09.005 ↗
38. A theory of cerebellar function10.1016/0025-5564(71)90051-4 ↗
39. A cerebellar model for predictive motor control tested in a brain-based device10.1073/pnas.0511281103 ↗
40. Perceiving path from optic flow10.1167/11.1.22 ↗
41. Insect inspired vision-based velocity estimation through spatial pooling of optic flow during linear motion10.1088/1748-3190/ac1f7b ↗
42. Laminar origins and terminations of cortical connections of the occipital lobe in the rhesus monkey10.1016/0006-8993(79)90485-2 ↗
43. Organizing principles of cortical layer 610.3389/neuro.04.003.2010 ↗
44. A selective impairment of motion perception following lesions of the middle temporal visual area (MT)10.1523/JNEUROSCI.08-06-02201.1988 ↗
45. Integration of direction signals of image motion in the superior temporal sulcus of the macaque monkey10.1523/JNEUROSCI.06-01-00145.1986 ↗
46. Shape and spatial distribution of receptive fields and antagonistic motion surrounds in the middle temporal area (V5) of the macaque10.1111/j.1460-9568.1995.tb00629.x ↗
47. Neural model of first-order and second-order motion perception and magnocellular dynamics10.1364/JOSAA.16.000953 ↗
48. Neural dynamics of motion integration and segmentation within and across apertures10.1016/S0042-6989(01)00131-6 ↗
49. Contour enhancement, short term memory and constancies in reverberating neural networks10.1002/sapm1973523213 ↗
50. A quantitative description of membrane current and its application to conduction and excitation in nerve10.1113/jphysiol.1952.sp004764 ↗
51. Neural models for sustained and on-off units of insect lamina10.1007/BF00202453 ↗
52. Real-time path planning and tracking control using a neural dynamics based approach10.3182/20020721-6-ES-1901.00829 ↗
53. The mechanism of directionally selective units in rabbit’s retina10.1113/jphysiol.1965.sp007638 ↗
54. Mechanisms and circuitry underlying directional selectivity in the retina10.1038/nature01179 ↗
55. Anatomical organization of macaque monkey striate visual cortex10.1146/annurev.ne.11.030188.001345 ↗
56. Contrast-sensitive perceptual grouping and object-based attention in the laminar circuits of primary visual cortex10.1016/S0042-6989(99)00229-1 ↗
57. Primate extrastriate cortical area MST: a gateway between sensation and cognition10.1152/jn.00384.2020 ↗
58. A neural network for the processing of optic flow from ego-motion in man and higher mammals10.1162/neco.1993.5.3.374 ↗
60. Centrifugal directional bias in the middle temporal visual area (MT) of the macaque10.1017/S0952523800012037 ↗
61. ARTFLOW: a fast, biologically inspired neural network that learns optic flow templates for self-motion estimation10.3390/s21248217 ↗
62. Modeling physiological sources of heading bias from optic flow10.1523/ENEURO.0307-21.2021 ↗
63. A motion pooling model of visually guided navigation explains human behavior in the presence of independently moving objects10.1167/12.1.20 ↗
64. Monocular distance estimation from optic flow during active landing maneuvers10.1088/1748-3182/9/2/025002 ↗
65. The anatomy of the cerebellum10.1016/S1364-6613(98)01210-8 ↗
66. Sensitivity of human visual cortical area V6 to stereoscopic depth gradients associated with self-motion10.1152/jn.01120.2010 ↗
67. Review: approaches to visual-motor control in baseball batting10.1097/OPX.0000000000001719 ↗
68. A bio-inspired flying robot sheds light on insect piloting abilities10.1016/j.cub.2006.12.032 ↗
69. PyBullet, a Python module for physics simulation for games, robotics and machine learning
70. Robot operating system 2: design, architecture and uses in the wild10.1126/scirobotics.abm6074 ↗
71. Biomimetic autopilot based on minimalistic motion vision for navigating along corridors comprising U-shaped and S-shaped turns10.1016/S1672-6529(14)60099-8 ↗
72. The visual fields in aphakia
73. Cortical motion perception emerges from dimensionality reduction with evolved spike-timing-dependent plasticity rules10.1523/JNEUROSCI.0384-22.2022 ↗
74. Dissociation of self-motion and object motion by linear population decoding that approximates marginalization10.1523/JNEUROSCI.1177-17.2017 ↗
75. From insect vision to robot vision10.1098/rstb.1992.0106 ↗
76. Insect inspired behaviours for the autonomous control of mobile robots10.1109/ICPR.1996.546010 ↗
77. Hippocampal replay reflects specific past experiences rather than a plan for subsequent choice10.1016/j.neuron.2021.07.029 ↗
78. Hierarchical models of object recognition in cortex10.1038/14819 ↗
79. Panoramic optic-flow profile guiding aerial exploration through turns in simulated environments
80. Netting and background distinction with in-flight optic flow10.1007/s42235-025-00677-w ↗