All posts by comitchell

NEWS

Road pavement condition detection from Acoustic signals: A Deep Learning approach

Siavash Bahrami is undertaking his PhD at project partner University Putra Malaysia (UPM). Siavash is currently on secondment to the University of Lincoln as an Early Stage Researcher. He is supporting the following Work Packages and Tasks as part of the Ultracept Project which is funded by European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement 778062:

  • WP2 – Brain-inspired vision systems for long-range hazard perception

Task 2.3: To develop long range hazard perception methods coping with low light conditionsSiavash Bahrami standing by car

During my secondment at the University of Lincoln, I am working on the development of a neural network model utilizing acoustic signals. This research will be useful where sound data for road wetness levels estimation would be able to support the development of long-range hazard methods coping with low light conditions.

Attaching microphone to vehicle
Attaching microphone to vehicle

My preliminary experiment was performed on a dataset of tyre recordings available on “Detecting Road Surface Wetness from Audio with Recurrent Neural Networks” to evaluate the proposed CNN architectures. MFCCs were used as acoustic signal features to classify the wet and dry road for preliminary investigation which resulted in 98.7% accuracy.

Microphone recording tyre sound
Microphone recording tyre sound
Microphone in vehicle recording road sound
Microphone in vehicle recording road sound

In the next phase of my study, I’m going to develop a larger dataset, where recording equipment has been purchased and data collection has just begun on several roads in Lincoln.

I am also looking forward to my next Ultracept secondment with the project partner Visomorphic Technology Ltd.

This Marie Sklodowska-Curie secondment has given me access to facilities and recording equipment needed for compiling the dataset needed for both my PhD studies and the Ultracept project. In addition, the weekly meetings with other members of the project has given me the opportunity to discuss and broaden my knowledge in various related research fields.

Uncategorized

Mid-Term Project Review Meeting Feb 2020

ULTRACEPT mid-term meeting held in Cambridge UK
ULTRACEPT mid-term meeting held in Cambridge UK

The ULTRACEPT mid-term meeting was hosted by UoL at the Cambridge Hotel in Cambridge, United Kingdom. It took place on the 26th February 2020. Attendees included students, researchers, academic staff, partner leads, the project manager and the EU Project Officer.

Due to the travel restrictions caused by the global pandemic Covid-19, the meeting was attended both in person and via Zoom video conferencing.

The mid-term meeting provided partners with an opportunity to engage in a fruitful and constructive dialogue between the consortium and the Research Executive Agency.

ULTRACEPT mid-term meeting held in Cambridge UK
ULTRACEPT mid-term meeting held in Cambridge UK

Members shared progress on the secondments, milestones and deliverables for the ULTRACEPT project. It also provided partners an opportunity to discuss challenges and to develop strategies for overcoming them.

In addition to this, a number of presentations were delivered by partner leads, researchers, and students as listed below. Presenters were able to demonstrate their research and share learning with others. In the afternoon, attendees had the opportunity to further network and share ideas.

ULTRACEPT Mid-Term Project Review Meeting

Wednesday 26th February 2020

Venue: Cambridge Hotel, Cayley Suite, Granta Place, Mill Ln, Cambridge CB2 1RT, United Kingdom

  • 09:00-09:30: Arrival/registration
  • 09:30-09:45: Introduction by Prof Shigang Yue

Coordinator’s/WP Leader Reports

  • 09.45-10.05: WP1 Visual Neural Systems Modelling for near range emergent collision detection – Presented by Shigang Yue UoL and Julieta Sztarker UBA
  • 10.05-10.25: WP2 Brain-inspired vision systems for long-range hazard perception – Presented by Xiaoyi Jiang WWM via video conference and Shyamala Doraisamy UPM.
  • 10.25-10.45: WP3 Visual computation of multi-modality sensor data for collision detection – Presented by Shigang Yue UoL.
  • 10.45-11.05: WP4 Systems integration, miniaturization, verification and demonstration – Presented by Shuang Li UHAM.

11.05-11.20: Mid-morning break

Shyamala Doraisamy presenting at the ULTRACEPT mid-term meeting held in Cambridge UK
Shyamala Doraisamy presenting at the ULTRACEPT mid-term meeting held in Cambridge UK

Coordinator’s/WP Leader Reports

  • 11.20-11.40: WP5 Joint workshops, conference and dissemination – Presented by Shigang Yue UoL.
  • 11.40-12.00: WP6: Project management and exploitation – Presented by Shigang Yue UoL
Shuang Li presenting at the ULTRACEPT mid-term meeting held in Cambridge UK
Shuang Li presenting at the ULTRACEPT mid-term meeting held in Cambridge UK

Researcher presentations

  • 12.00-12.10: Detection of objects on the road in low light condition using deep learning – Presented by Azreen Azman UPM.
  • 12.10-12.20: Road Wetness classification using acoustic signals – Presented by Siavash Bahrami UPM
  • 12.20-12.30: Secondment Report for ULTRACEPT Meeting – Presented by Huatian Wang UoL via video conference
  • 12.30-12.50: Multimodal teleoperation of robotic hand-arm system – Presented by Shuang Li UHAM.
  • 12.50-13.00: Thermal imaging for vehicle collision prediction and avoidance – Presented by Yicheng Zhang UoL.
Azreen Azman presenting at the ULTRACEPT mid-term meeting held in Cambridge UK
Azreen Azman presenting at the ULTRACEPT mid-term meeting held in Cambridge UK
Yicheng Zhang presenting at the ULTRACEPT mid-term meeting held in Cambridge UK
Yicheng Zhang presenting at the ULTRACEPT mid-term meeting held in Cambridge UK

13.00-14.00: Lunch

14.00-15.00: Meeting between seconded researchers and the REA Representative, Irina Tiron. Attendees: Azreen Azman, Siavash Bahrami, Peimin Li, Huatian Wang (attend via video conference).

14.00-15.00: Team leaders – meet to discuss arrangements for the outstanding joint workshop and training seminar.  

15.00-15.15: Afternoon break

15.15-16.15: Open discussion

16.15-16.30: Closing comments          

16.30: Meeting close   

NEWS

Joint Tsinghua University and the University of Lincoln Team Wins Robotics Championship

Jiannan Zhao with his award at the Robotics Championship 2019
Jiannan Zhao with his award at the Robotics Championship

August 2019

In exciting news for Tsinghua University and the University of Lincoln, their joint robotics team has taken first prize in the first International Competition for Autonomous Running Intelligent Robots. The team consisted of five students, four from Tsinghua and 1 from Lincoln, who were awarded a total prize of $10,000.

The student from the University of Lincoln, Jiannan Zhao, supports our Ultracept project and is currently carrying out a secondment at Guangzhou University.

Tsinghua University is one of the partners involved with our Ultracept project.

The event was held in Beijing in August 2019 with 33 teams competing with representatives from over 20 countries and regions.

The competition was judged on the performance of the robot across three segments:

  • Standard
  • Freestyle
  • Performance

During the competition, the robots had to rely solely on their “brains” as no operator assistance was allowed. The robot had to autonomously analyse and make decisions on how best to cross barriers and handle variable track conditions.

Robot competition team photo
Robot competition team photo

Watch the robots in action!

See the China Daily website for a video of the event. Watch at the 53 second mark to see the winning robot in action.

Below is a video of the event from CCTV English.