An autonomous robot inspired by insect neurophysiology pursues moving features in natural environments

Bagheri, Zahra M.; Cazzolato, B.; Grainger, Sally; O’Carroll, David C.; Wiederman, Steven D.

doi:10.1088/1741-2552/aa776c

Cited by 34 publications

(29 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vast majority of researches have been concentrating on the LGMD1. 9 This neuron has been demonstrated to play dominant roles in locusts capable of flying [231,175,171,211,227,170]. In terms of neuromorphology, the Fig.…”

Section: Biological Research Backgroundmentioning

confidence: 99%

“…More specifically, the ESTMD-EMD indicates that the ESTMD cascades with the EMD while the EMD-ESTMD indicates that the EMD cascades with the ESTMD. These two hybrid models have been successfully used for target tracking against cluttered backgrounds in an autonomous mobile ground robot [9,11,10]. Another directionally selective STMD model, the directionally selective small target motion detector (DSTMD in the Fig.…”

Section: Computational Models and Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review

Wang

et al. 2019

Artificial Life

View full text Add to dashboard Cite

Motion perception is a critical capability determining a variety of aspects of insects' life, including avoiding predators, foraging and so forth. A good number of motion detectors have been identified in the insects' visual pathways.Computational modelling of these motion detectors has not only been providing effective solutions to artificial intelligence, but also benefiting the understanding of complicated biological visual systems. These biological mechanisms through millions of years of evolutionary development will have formed solid modules for constructing dynamic vision systems for future intelligent machines. This article reviews the computational motion perception models originating from biological research of insects' visual systems in the literature. These motion perception models or neural networks comprise the looming sensitive neuronal models of lobula giant movement detectors (LGMDs) in locusts, the translation sensitive neural systems of direction selective neurons (DSNs) in fruit flies, bees and locusts, as well as the small target motion detectors (STMDs) in dragonflies and hover flies. We also review the applications of these models to robots and vehicles. Through these modelling studies, we summarise the methodologies that generate different direction and size selectivity in motion perception. At last, we discuss about multiple systems integration and hardware realisation of these bio-inspired motion perception models.

show abstract

Section: Biological Research Backgroundmentioning

confidence: 99%

Section: Computational Models and Applicationsmentioning

confidence: 99%

Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review

Wang

et al. 2019

Artificial Life

View full text Add to dashboard Cite

show abstract

“…Wiederman et al [9] proposed the ESTMD, to model an STMD neuron with spatially integrated multiple ESTMDs. Although the ESTMD shows size selectivity, it is not directionally selective.Wiederman and O'Carroll [10] and Bagheri et al [11]- [13] mentioned that two hybrid models, i.e., EMD-ESTMD and ESTMD-EMD, could exhibit both size and direction selectivities. However, characteristics and performance of these directionally selective STMD models, are unclear, since direction selectivity has not been systematically studied.…”

Section: Small Target Motion Detectormentioning

confidence: 99%

“…1) The existing STMD-based models, including ESTMD [9], EMD-ESTMD [10], and ESTMD-EMD [10], have not provided unified and rigorous mathematical description. 2) Wiederman and O'Carroll [10] and Bagheri et al [11]- [13] focused on the size selectivity, tracking mechanisms and non-directionally selective properties, e.g., velocity and contrast tuning. Since direction selectivity has not been systematically studied, characteristics and performance of the directionally selective STMD models, are unclear.…”

Section: Introductionmentioning

confidence: 99%

A Directionally Selective Small Target Motion Detecting Visual Neural Network in Cluttered Backgrounds

Wang

Peng

Yue

2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Discriminating targets moving against a cluttered background is a huge challenge, let alone detecting a target as small as one or a few pixels and tracking it in flight. In the insect's visual system, a class of specific neurons, called small target motion detectors (STMDs), have been identified as showing exquisite selectivity for small target motion. Some of the STMDs have also demonstrated direction selectivity which means these STMDs respond strongly only to their preferred motion direction. Direction selectivity is an important property of these STMD neurons which could contribute to tracking small targets such as mates in flight. However, little has been done on systematically modeling these directionally selective STMD neurons. In this paper, we propose a directionally selective STMD-based neural network for small target detection in a cluttered background. In the proposed neural network, a new correlation mechanism is introduced for direction selectivity via correlating signals relayed from two pixels. Then, a lateral inhibition mechanism is implemented on the spatial field for size selectivity of the STMD neurons. Finally, a population vector algorithm is used to encode motion direction of small targets. Extensive experiments showed that the proposed neural network not only is in accord with current biological findings, i.e., showing directional preferences, but also worked reliably in detecting small targets against cluttered backgrounds.

show abstract

“…Bio-plausible visual models inspired from insects are getting importance in robotics for various of visual-motor tasks, such as the trajectory stabilization and navigation task inspired by Elementary Motion Detector (EMD) [1], collision avoidance (CA) inspired by Lobular Giant Movement Detector (LGMD) [2,3], homing task inspired by the mushroombody of ants [4] and also navigation in spired by Small Target Motion Detectors (STMD) [5], by taking advantage of their reliability in coping with rapid changing scenarios with only minimum amount of neurons occupied. Comparing to conventional reactive navigation algorithms based on computer vision techniques such as standard optic flow [6], these bio-inspired models are usually free from massive calculation such as object recognition or distance estimation.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Visual-Model Based Robot Control Strategy for Micro Ground Robots

Liu

et al. 2018

From Animals to Animats 15

View full text Add to dashboard Cite

This paper proposed a hybrid vision-based robot control strategy for micro ground robots by mediating two vision models from mixed categories: a bio-inspired collision avoidance model and a segmentation based target following model. The implemented model coordination strategy is described as a probabilistic model using finite state machine (FSM) that allows the robot to switch behaviours adapting to the acquired visual information. Experiments demonstrated the stability and convergence of the embedded hybrid system by real robots, including the studying of collective behaviour by a swarm of such robots with environment mediation. This research enables micro robots to run visual models with more complexity. Moreover, it showed the possibility to realize aggregation behaviour on micro robots by utilizing vision as the only sensing modality from non-omnidirectional cameras.

show abstract

An autonomous robot inspired by insect neurophysiology pursues moving features in natural environments

Abstract: Our results provide insight into the neuronal mechanisms that underlie biological target detection and selection (from a moving platform), as well as highlight the effectiveness of our bio-inspired algorithm in an artificial visual system.

Cited by 34 publications

References 51 publications

Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review

Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review

A Directionally Selective Small Target Motion Detecting Visual Neural Network in Cluttered Backgrounds

A Hybrid Visual-Model Based Robot Control Strategy for Micro Ground Robots

Contact Info

Product

Resources

About