Workshop 2

Reporting recent modelling and invertebrate visual neural biology developments, preliminary selection for candidate neural systems towards multimodalities and VLSI realisation, relevant to WP1, WP3 and WP4.

The ULTRACEPT Workshop Two was hosted by UoL and took place on the 28th July 2020.  Due to the travel restrictions caused by COVID-19, the workshop was held as an online event using MS Teams. The following day the group also held a training seminar.

  • Day 1: 28 July 2020 Workshop 2
  • Day 2: 29 July 2020 Training Seminar

The workshop was attended by 30 participants from project partners and provided an opportunity for a group discussion and to share project news and updates. New researchers to the group were introduced by each partner and they provided a short summary of their field of work. This discussion enabled members to learn more about the variety of research being undertaken in order to achieve the ULTRACEPT work packages.

UTLRACEPT Workshop 2 group image

ULTRACEPT: Ultra-layered perception with brain-inspired information processing for vehicle collision avoidance

Marie Skłodowska-Curie Actions – Research and Innovation Staff Exchange (RISE)

This research has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 778062.

Date: Tuesday 28 July 2020

Time: UK 11:00; China 18:00; Germany 12:00; Buenos Aires 07:00

Location: MS Teams

Workshop Schedule
UK Time Item Presenters
11:00-11:10 Arrival and welcome Shigang Yue
11:10-12:10 Round table discussion All
12:10-12:30

Adaptive Inhibition Matters to Robust Collision Perception in Highly Variable Environments

  • University of Lincoln

10min presentation & 10min discussion

Qinbing Fu
12.35-12.55

Modelling Near Range Emergency Collision Sensitive Neural Network for UAV Application

  • University of Lincoln

10min presentation & 10min discussion

Jiannan Zhao
12:55-13:30 Break
13:30-13:50

Competition between ON and OFF Neural Pathways Enhancing Collision Selectivity

  • University of Lincoln

10min presentation & 10min discussion

Fang Lei
13:55-14:25

Unified Model Explaining Optimal Coordination of Insect Navigation 

  • University of Lincoln

20min presentation & 10min discussion

Xuelong Sun
14:30-14:50 Computational modelling of insect stereoscopic depth detectors

  • University of Newcastle

10min presentation & 10 min Q&A

James O’Keeffe
14:50-15:00 Final comments All

The meeting was opened with an introduction by Prof Shigang Yue, the ULTRACEPT project Coordinator from the University of Lincoln. Following this was a round table discussion, then a series of talks delivered by ULTRACEPT researchers. This provided an opportunity for the researchers to share their work with the group including recently published papers and papers in the process of being submitted.

The first presentation was delivered by Dr Qinbing Fu from the University of Lincoln on ‘Adaptive Inhibition Matters to Robust Collision Perception in Highly Variable environments’.

Qinbing Fu presentation ULTRACEPT Workshop 2
Qinbing Fu presentation

Following Dr Fu was a presentation by University of Lincoln researcher Jiannan Zhao on ‘Modelling Near Range Emergency Collision Sensitive Neural Network for UAV Application’.

Jiannan Zhao presentation ULTRACEPT Workshop 2
Jiannan Zhao presentation

Following a short break, Fang Lei from the University of Lincoln presented ‘Morphological LGMD1 Neural Network’.

Fang Lei presentation ULTRACEPT Workshop 2
Fang Lei presentation

Xuelong Sun from the University of Lincoln delivered a longer presentation on his ULTRACEPT research ‘A unified model explaining optimal coordination of insect navigation’.

ULTRACEPT Workshop 2 Xuelong Sun presentation
Xuelong Sun presentation

The final presentation for the workshop was delivered by James O’Keefe from the University of Newcastle on ‘Computational modelling of insect stereoscopic depth detectors’.

James Okeefe presentation ULTRACEPT Workshop 2
James Okeefe presentation

Ultra-layered perception with brain-inspired information processing for vehicle collision avoidance