An Integrated Vision and Control Architecture for Agile Robotic Exploration
Lead Research Organisation:
University of Bristol
Department Name: Computer Science
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Publications
Bose L
(2017)
Visual Odometry for Pixel Processor Arrays
Castillo-Elizalde H
(2021)
Weighted Node Mapping and Localisation on a Pixel Processor Array
Dudek P
(2022)
Sensor-level computer vision with pixel processor arrays for agile robots.
in Science robotics
Greatwood C
(2017)
Tracking control of a UAV with a parallel visual processor
Liu Y
(2022)
On-sensor binarized CNN inference with dynamic model swapping in pixel processor arrays.
in Frontiers in neuroscience
Liu Y
(2021)
Agile reactive navigation for a non-holonomic mobile robot using a pixel processor array
in IET Image Processing
Liu Yanan
(2021)
Direct Servo Control from In-Sensor CNN Inference with A Pixel Processor Array
in arXiv e-prints
Liu Yanan
(2022)
On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array
in arXiv e-prints
Liu Yanan
(2021)
Bringing A Robot Simulator to the SCAMP Vision System
in arXiv e-prints
McConville A
(2020)
Visual Odometry Using Pixel Processor Arrays for Unmanned Aerial Systems in GPS Denied Environments.
in Frontiers in robotics and AI
Description | We have developed novel algorithms for knowing how a camera has moved in space when the camera is of the special type of having a processor at every pixel. These new algorithms have been published at top international conferences in Computer Vision and Robotics. The interest from academic colleagues as well of industry is very encouraging as the new type of cameras and algorithms we are developing on this project can have a dramatic impact for robots and AI systems that move and have to perceive in real-time. My colleague partners are setting up a startup as a direct result of this award and one of my post-docs will be joining that company after completing research his associate activity. |
Exploitation Route | We are currently being approached by colleagues from another UK university interested in collaborating as well as colleagues from another European institution. My colleague partners are setting up a startup as a direct result of this award and one of my post-docs will be joining that company after completing research his associate activity. |
Sectors | Aerospace Defence and Marine Digital/Communication/Information Technologies (including Software) Electronics |
URL | https://sites.google.com/view/project-agile |
Description | Our project partners at the University of Manchester did set up a spin-out company to further develop the technology of Pixel Processor Arrays. This was expanded and underpinned by the Computer Vision algorithms developed in this research project. That startup has been wound down. But there is interest in creating further commerial impact. On late 2023 we have been awarded additional funding to develop research further in the space of on-sensor computation in combination with Univeristy of Manchester and new expanded partners with Imperial College. |
Sector | Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Electronics |
Impact Types | Economic |
Description | On-Sensor Computer Vision |
Amount | £3,352,475 (GBP) |
Funding ID | EP/Y022629/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 08/2024 |
End | 08/2028 |
Description | Initial collaboration with Imperial College London |
Organisation | Imperial College London |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | As we aim to expand the impact of Pixel Processor Arrays we have supported Imperial College Researchers to get a better understanding of the technology and ways to program devices with computer vision algorithms. |
Collaborator Contribution | At least one paper has been written and will be submitted soon. |
Impact | Still pending |
Start Year | 2019 |
Title | Scamp5d semi-simulation platform with Coppeliasim Robot Simulator |
Description | Software that allows a robot simulator to be used as input to the Pixel Processor Array SCAMP-5 |
Type Of Technology | Software |
Year Produced | 2021 |
Open Source License? | Yes |
Impact | Winner of best poster paper at the IEEE ICRA 2021 workshop On- and Near-sensor Vision Processing, from Photons to Applications (ONSVP) |
URL | https://github.com/yananliusdu/scamp5d_interface |
Description | Inaugural Keynote, Encuentro Nacional de Computación (ENC) Conference 2021 |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Professional Practitioners |
Results and Impact | Opening Keynote at the main Annual event organized by the Mexican Society of Computer Sciences. This is the principal academic event in Mexico in Computer Science. It is attended (this year online) by students from undergrad to post doctoral as well as by principal investigators and scientific leadership in CS in Mexico. |
Year(s) Of Engagement Activity | 2021 |
URL | http://computo.fismat.umich.mx/enc2021/ |
Description | Invited talk: Towards Integrated Perception and Control for UAVs with Pixel Processor Arrays |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | This was an invited talk at this leading workshop on agile perception for UAVs as part of the IROS conference in Vancouver, CA. |
Year(s) Of Engagement Activity | 2017 |
URL | http://www.seas.upenn.edu/~loiannog/workshopIROS2017uav/ |
Description | Keynote at 1st Autonomous Vehicle Vision Workshop at Winter Applications of Computer Vision conference (WACV) |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Keynote talk at specialist workshop |
Year(s) Of Engagement Activity | 2020,2021 |
Description | Keynote at IEEE ICRA 2021 Workshop On- and Near-sensor Vision Processing, from Photons to Applications (ONSVP) |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Keynote at specialist workshop |
Year(s) Of Engagement Activity | 2021 |
URL | https://sites.google.com/view/onsvp-icra-2021-workshop/home |
Description | Popular article about this research |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | https://www.techradar.com/news/ai-security-cameras-inspired-by-frog-eyes-could-be-coming-soon |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.techradar.com/news/ai-security-cameras-inspired-by-frog-eyes-could-be-coming-soon |
Description | Popular article about this research -Photonics World |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | News article about our work in this award |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.photonics.com/Articles/SCAMP_Brings_Computer_Vision_Closer_to_Natural/a66564 |