You are part of the MSCA-RISE consortium ‚ULTRACEPT‘. In a nutshell, what is this project all about?
The project ‘Ultra-layered perception with brain-inspired information processing for vehicle collision avoidance’ (ULTRACEPT), is being funded by the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Actions (MSCA) - Research and Innovation Staff Exchange (RISE) grant number 778062.
The project has 18 partners in total, of which 3 are companies within the robotics sector. The University of Lincoln is the lead coordinator and the University Putra Malaysia (UPM) is listed as a project partner for the duration of the project. The project started on 1 December 2018 and will last for 4 years.
This consortium proposes an innovative solution with brain-inspired multiple layered and multiple modalities information processing for trustworthy vehicle collision detection. It takes the advantages of low cost spatial-temporal and parallel computing capacity of bio-inspired visual neural systems and multiple modalities data inputs in extracting potential collision cues at complex weather and lighting conditions.
Your institute at UPM is one of the partners in this international consortium. How did UPM become involved?
Discussions for possible collaborations on research projects began during my sabbatical period from 2015 at the Computation Intelligence Lab, School of Computer Science, University of Lincoln (UoL) with Professor Shigang Yue. As a visiting researcher then, I was invited to give a talk enabling me to highlight some of the work done at Faculty of Computer Science and Information Technology, UPM, and in particular with the Digital Information Computation and Retrieval (DICR) Research Group which I was leading. Upon my return to UPM in 2016, discussions continued on the possible areas of collaborations. An invitation to participate as a consortium partner with the Ultracept project was received in 2017 and areas in which the members of the DICR lab could contribute were finalised. The Ultracept project proposal was accepted in 2018.
What is your role in the consortium?
The consortium comprises nine multidisciplinary partners. The research is coordinated by Prof. Shigang Yue of UoL and managed by a Research Management Board comprising representatives from each of the partners. The Research Management Board is chaired by the project coordinator and will carry out the executive management of the research programme and the administrative functions of the research. It will initially comprise one member from each partner. As for my role in the consortium, I was the appointed member of the board representing UPM.
You are currently on secondment in the UK. How do secondments work and what are you doing at the partner’s lab?
As a member of Ultracept’s Research Management Board representing UPM, I have the responsibility of managing the secondments and ensuring the completion of tasks assigned in the related project’s work packages (WPs). Following the 36 secondment months allocated to UPM, two Experienced Researchers (ERs) with doctoral degrees including me and one ESR (Early Stage Researcher) have undertaken the secondments up to 12 months each at UOL and partner institutions of the consortium.
UPM has been working on the theme of road safety related to the project. The tasks assigned to UPM were mainly based on the work packages, WP2 and WP4. The team has focused in particular on contributions for task 2.3 in WP2 -- ‘To develop long range hazard perception methods coping with low light conditions’.
My secondment began in Dec 2018. The first few months included initial meetings with partners and the completion of proposal discussions for a collaborative PhD research work with Siavash Bahrami. The tasks completed have been based on this collaborative PhD research being co-supervised by UPM and UoL. Siavash began his secondment at UoL in June 2019. The research involves investigating the use of sound data for road wetness levels estimation to support the development of long range hazard methods coping with low light conditions. The preliminary work planned has been completed and two new
CNN architectures were proposed using MFCCs as acoustic signal features. The evaluation for these proposals was performed on a dataset of tyre recordings available on https://lexfridman.com/wetroad/. For the next phase of a larger dataset development, recording equipment has been purchased and data collection has just begun on several roads in Lincoln.
Dr. Azreen Azman, an Associate Professor has just been seconded as an ER from UPM to UoL and the team will continue to utilise audiovisual technologies towards the development of Brain-inspired vision systems for long-range hazard perception (WP2).
Why would you say participation in an MSCA-RISE is beneficial for Malaysian research groups?
Amongst the aims of the MSCA-RISE are knowledge creation, sharing know-how, and skills development. These are valuable opportunities for a large number of Malaysian research groups which are in their early growth stages to expand and build world-class research labs.
This Marie Sklodowska-Curie secondment has given my student access to facilities and recording equipment needed for compiling the dataset needed for both his PhD studies and the Ultracept project. In addition, weekly meetings with other seconded members from Ultracept’s partner institutions provided him the opportunity to discuss with a wider research community and broaden his knowledge in various related research fields.
What advice would you have to your research peers on how to get involved in future RISE consortia?
The first advice would be to work closely with European colleagues forming RISE consortiums and discussing possible areas of collaborations. Alternatively, researchers could also initiate discussions with potential partners based on ongoing research that would highly benefit from a large scale international collaboration. In addition to forming the research teams, it would be important to identify the administrative team members from your institution. In general, RISE consortiums comprise large multidisciplinary research partners from various parts of the world. Managing both the research and administrative tasks would have to be well coordinated via communications not just with the coordinating partner but also within your organisation’s team members.
Thank you Dr Shyamala!td