The 2019 UK Neural Computation event was held at the University of Nottingham, United Kingdom on the 2nd -3rd July 2019. The full programme can be viewed here.

This event was attended by ULTRACEPT researchers from the University of Lincoln Hongxin Wang, Jiannan  Zhao, Fang Lei, Hao Luan and Xuelong Sun.

As well as attending presentations at the event, the researchers attended a tutorial for early PhD student where they learnt a lot about doing research.

Hongxin states “I attended the tutorial,  communicated with researchers who worked on relevant fields such as  computational neuroscience,  and acquired new ideals for further improving robustness of the STMD models and how to simulate feedback mechanism in the STMD neural pathways.”

Jiannan advised that he participated in the meeting discussion, discussed the interesting topic in Neural Computing field.

Modelling the optimal integration of navigational strategies in the insect brain

Xuelong Sun presented a poster at this event. You can view Xuelong’s poster here.

Sun X, Mangan M, Yue S 

Insect are expert navigators capable of searching out sparse food resources over large ranges in complex habitats before relocating their often hidden nesting sites. These feats are all the more impressive given the limited sensing and processing available to individual animals. Recently, significant advances have been made in identifying the brain areas driving specific navigational  behaviours, and their functioning, but an overarching computational model remains elusive. In this study, we present the first biologically constrained, computational model that integrates visual homing, visual compass and path integration behaviours. Specifically, we demonstrate the challenges faced when attempting to replicate visual navigation behaviours (visual compass and visual homing) using the known mushroom body anatomy (MB) and instead propose that the central 54 complex (CX) neuropil may instead compute the visual compass. We propose that the role of the mushroom body (MB) is to modulate the weighting of the path integration and visual guidance systems depending on the current context (e.g. in a familiar or unfamiliar visual surrounding). Finally, we demonstrate that optimal integration of directional cues can be achieved using a biologically realistic ring attractor network.

The 2019 15th International Conference on Artificial Intelligence Applications and Innovations AIAI was held on the 24th -26th May 2019  in Crete, Greece at the Knossos Royal Beach Resort. The detailed program can be found here.

The conference was attended by the ULTRACEPT researchers Hongxin Wang and Jiannan Zhao from the University of Lincoln and Xingzao Ma from Lingnan Normal University.

AIAI Session 2: (AUV-LE) Autonomous Vehicles-Learning

Jiannan Zhao presented at this conference.

Room B: 10:30- 11:45

Jiannan Zhao, Xingzao Ma, Qinbing Fu, Cheng Hu, Shigang Yue

An LGMD Based Competitive Collision Avoidance Strategy for UAV

Abstract. Building a reliable and efficient collision avoidance system For unmanned aerial vehicles (UAVs) is still a challenging problem. This research takes inspiration from locusts, which can y in dense swarms for hundreds of miles without collision. In the locust’s brain, a visual pathway of LGMD-DCMD (lobula giant movement detector and descending contra-lateral motion detector) has been identified as collision perception system guiding fast collision avoidance for locusts, which is ideal for designing artificial vision systems. However, there is very few works investigating its potential in real-world UAV applications. In this paper, we present an LGMD based competitive collision avoidance method for UAV indoor navigation. Compared to previous works, we divided the UAV’s field of view into four subfields each handled by an LGMD neuron. Therefore, four individual competitive LGMDs (C-LGMD) compete for guiding the directional collision avoidance of UAV. With more degrees of freedom compared to ground robots and vehicles, the UAV can escape from collision along four cardinal directions (e.g. the object approaching from the left-side triggers a rightward shifting of the UAV). Our proposed method has been validated by both simulations and real-time quadcopter arena experiments.

AIAI Session 10: (AG-MV) Agents-Machine Vision

Hongxin Wang presented at this conference.

Room C: 12:00-13:15

Constant Angular Velocity Regulation for Visually Guided Terrain Following

Huatian Wang, Qinbing Fu, Hongxin Wang, Jigen Peng, Shigang Yue

Insects use visual cues to control their flight behaviours. By estimating the angular velocity of the visual stimuli and regulating it to a constant value, honeybees can perform a terrain following task which keeps the certain height above the undulated ground. For mimicking this behaviour in a bio-plausible computation structure, this paper presents a new angular velocity decoding model based on the honeybee’s behavioural experiments. The model consists of three parts, the texture estimation layer for spatial information extraction, the motion detection layer for temporal information extraction and the decoding layer combining information from pervious layers to estimate the angular velocity. Compared to previous methods on this field, the proposed model produces responses largely independent of the spatial frequency and contrast in grating experiments. The angular velocity based control scheme is proposed to implement the model into a bee simulated by the game engine Unity. The perfect terrain following above patterned ground and successfully flying over irregular textured terrain show its potential for micro unmanned aerial vehicles’ terrain following.