UWE Aerospace’s Steve Wright has been popular in the news this month, most recently reassuring local Bristol businesses, Rolls Royce and Airbus, with his predictions of recovery after Covid-19. Read Steve’s expert opinion on how the pandemic will effect the aviation industry.
Technology from the Centre for Machine Vision (CMV) has been making moves to improve animal welfare and maximize crop harvesting.
First off, the 3D imagery system, Herdvision, that helps farmers assess cows’ wellbeing, was featured on the BBC six o’clock news in 2019 as it began a trial by Arla UK 360 farmers.
The technology developed in collaboration with Kingshay and AgsenZe, uses visual monitoring, data recording and automated intelligence to identify changes in each cow’s physical wellbeing, mobility and weight, before they are visible to the human eye.
Facial recognition used to assess pig’s emotions
Animal behaviourists from Scotland’s Rural College in Edinburgh, are using the technology provided by machine vision experts at UWE, to picture a range of pig facial expressions. The hope is that emotions can be identified and facial recognition used to improve pig welfare.
The BBC reported on the study in spring last year and the work is due to appear as part of a Netflix program in 2020.
The potato harvester based data capture system –Harvest Eye – provides insight on size, count and crop variation on unwashed potatoes as they are harvested. The integrated data analytics shows precisely what is being lifted and from where in the field, insights that will help maximise marketable yield and reduce crop imbalance.
The technology’s utility was recognised at the Potato Industry Event 2019/20, when it picked up second prize (out of 15 nominations) .
Harvest Eye was developed by CMV for B-hive, who then patented the technology in collaboration with CMV, and now B-Hive / Branston have established a new company, HarvestEye Ltd, to supply the HarvestEye technology to Grimme,a major manufacturer of root crop harvesters.
But the team at CMV aren’t stopping there.
“We’re working on a new funding bid right now to add functionality.”
Melvyn Smith, CMV
Mark Hansen, who led development of the technology, represented CMV, as part of the team that picked up the award.
A new project studies how to investigate accidents with social robots, Alan Winfield explains why this is needed…
Originally posted on September 17th, 2019 by Alan Winfield on his blog.
Imagine that your elderly mother, or grandmother, has an assisted living robot to help her live independently at home. The robot is capable of fetching her drinks, reminding her to take her medicine and keeping in touch with family. Then one afternoon you get a call from a neighbour who has called round and sees your grandmother collapsed on the floor. When the paramedics arrive they find the robot wandering around apparently aimlessly. One of its functions is to call for help if your grandmother stops moving, but it seems that the robot failed to do this.
Fortunately your grandmother recovers but the doctors find bruising on her legs, consistent with the robot running into them. Not surprisingly you want to know what happened: did the robot cause the accident? Or maybe it didn’t but made matters worse, and why did it fail to raise the alarm?
Although this is a fictional scenario it could happen today. If it did you would be totally reliant on the goodwill of the robot manufacturer to discover what went wrong. Even then you might not get the answers you seek; it’s entirely possible the robot and the company that made it are just not equipped with the tools and processes to undertake an investigation.
Right now there are no established processes for robot accident investigation.
Of course accidents happen, and that’s just as true for robots as any other machinery .
Finding statistics is tough. But this web page shows serious accidents with industrial robots in the US since the mid 1980s. Driverless car fatalities of course make the headlines. There have been five (that we know about) since 2016. But we have next to no data on accidents in human robot interaction (HRI); that is for robots designed to interact directly with humans. Here is one – a security robot – that happened to be reported.
But a Responsible Roboticist must be interested in all accidents, whether serious or not. We should also be very interested in near misses; these are taken very seriously in aviation , and there is good evidence that reporting near misses improves safety.
First we will look at the technology needed to support accident investigation.
In a paper published 2 years ago Marina and I argued the case for an Ethical Black Box (EBB) . Our proposition is very simple: that all robots (and some AIs) should be equipped by law with a standard device which continuously records a time stamped log of the internal state of the system, key decisions, and sampled input or sensor data (in effect the robot equivalent of an aircraft flight data recorder). Without such a device finding out what the robot was doing, and why, in the moments leading up to an accident is more or less impossible. In RoboTIPS we will be developing and testing a model EBB for social robots.
But accident investigation is a human process of discovery and reconstruction. So in this project we will be designing and running three staged (mock) accidents, each covering a different application domain: assisted living robots, educational (toy) robots, and driverless cars. In these scenarios we will be using real robots and will be seeking human volunteers to act in three roles, as the subject(s) of the accident, witnesses to the accident, and as members of the accident investigation team. Thus we aim to develop and demonstrate both technologies and processes (and ultimately policy recommendations) for robot accident investigation. And the whole project will be conducted within the framework of Responsible Research and Innovation; it will, in effect, be a case study in Responsible Robotics.
 Dhillon BS (1991) Robot Accidents. In: Robot Reliability and Safety. Springer, New York, NY
 Macrae C (2014) Close Calls: Managing risk and resilience in Airline flight safety, Palgrave macmillan.
 Winfield AFT and Jirotka M (2017) The Case for an Ethical Black Box. In: Gao Y, Fallah S, Jin Y, Lekakou C (eds) Towards Autonomous Robotic Systems. TAROS 2017. Lecture Notes in Computer Science, vol 10454. Springer, Cham.
In 2018, Women Like Me launched at UWE as a tiered mentoring project for women in engineering. Delivered by Dr Laura Fogg-Rogers and Dr Laura Hobbs, the project was a great success, engaging over 10,000 children with engineering outreach and significantly improving engineers’ confidence. Some findings of the first year’s project report are summarised here.
Only 12% of engineers in the UK are women. For democratic, utilitarian and equity reasons this is not enough. Both recruitment and retention are important – more girls need to connect with engineering as a creative, socially conscious, collaborative discipline, and more women need to be supported to make a difference in the workplace.
Funded in 2018-2019 by a Royal Academy of Engineering Ingenious grant, the ‘Curiosity Connections – Women Like Me’ project aimed to change this through tiered mentoring and role modelling. Previous research by Laura Fogg-Rogers indicates how important peer group and leadership support is for women, providing vicarious experience and changing social norms. This means that women need peer support to thrive in the workplace, and that girls need to see women succeeding in STEM careers in order to feel that engineering is for them.
This project therefore paired 21 mid-career (senior) women engineers with 21 junior women engineers (less than five years’ experience) in the Bristol and Bath area, in order to provide career and public engagement mentoring. The outreach activities resulted in over 10,240 children being engaged in public engagement with women engineers, through a variety of methods including school visits, public events and nationwide online presentations.
Junior engineers felt significantly more equipped to take part in public engagement
The junior engineers reported that they now feel significantly more equipped to take part in public engagement; 54% of junior engineers felt fairly well equipped before the project and this increased to 68% after the project, with 38% indicating they were very well equipped. Similarly, the mean score on the Engineering Outreach Self-Efficacy Scale significantly improved from 6.80 to 8.41 (out of 10). This indicates that the engineers are now much more confident to undertake education outreach, and are then more likely to continue public engagement following the project.
The report therefore concludes that mentoring is highly important to ensure a supportive workplace, which means that women are more likely to be retained in the engineering industry.
The full reportcan be downloaded from the UWE research repository and a paper in Journal of Science Communication, drawing on the results, is now available (open access).
Women Like Mewill relaunch in October 2019. To express an interest in taking part, please register your email address here.
This year, 6500 students from Universities across the UK took part in the challenge organised by EWB-UK. Fewer than 200 got through to the Grand Finals. The UWE team (Amelie, Marwan, Liberty, Conrad, Caner and Nicholas) were amongst the talented few. They presented their PEEPOWER inspired solution with much enthusiasm.
On Tuesday 21st May an autonomous vehicle was used by older people around the St Monica Trust’s Cote Lane retirement village, bringing a world-leading research project to a close.
The £5.5M project, “Flourish”, is delivered by a consortium of organisations including UWE Bristol and is the only Innovate UK funded project focused on older people. Launched in 2016, the project aims to develop a driverless vehicle integrating older people’s mobility needs with a secure and connected infrastructure.
The project works across three specialist areas at UWE Bristol, including the Bristol Robotics Laboratory. The demonstration explored how driverless vehicles, known as CAVs (connected and autonomous vehicles) could make a difference to older people’s everyday lives.
Professor Alan Winfield will be starting a new five year EPSRC funded project with Professor Marina Jirotka (University of Oxford), staging mock human-robot accidents in order to deeply explore the problem of robot accident investigation and develop both technical (i.e. data logging and explainer systems) and process solutions (i.e. frameworks for how to responsibly conduct such investigations).
The team will explore three scenarios, likely to be: assisted living (care) robots; robot toys and Autonomous Vehicles – with human volunteers role playing as the subject of, witnesses to, and the investigators of the accident. Alan believes this will be the first research project in the world to fully and systematically study this important aspect of real world robotics.
The Great Science Share is a national event nurturing children’s natural curiosity by encouraging them to share their original science investigations with scientists, with the regional Bristol and Bath event taking place at UWE Bristol in June:
10 am – 2 pm
Filton Road, UWE Bristol
Scientists and engineers are invited to attend, to find out what local children aged 8 – 13 have come up with, and to inspire participants with their research, demos and cutting-edge technology.
In this guest post, Katie Winkle of the Bristol Robotics Laboratory tells us about an opportunity to get involved in her exciting research.
I’m going to be
running an ambitious (and exciting!) research study over the summer
period and am putting out a first call for participants. This will be my
final big study as a PhD student and brings together all of my previous work to
date – some of you may have taken part in my previous experiments e.g. doing
wrist turns with Pepper or arm exercises with the NAO robot. I would really
appreciate it if you would consider taking part and/or share with friends
and family etc. who may be interested.
We will be installing a Pepper robot (picture below from one of my previous studies) in the Wallscourt Gym here on campus and using it to guide people through the NHS designed ‘Couch to 5k’ programme (https://www.nhs.uk/live-well/exercise/get-running-with-couch-to-5k/) designed to help people work up to running 5 km. Over the course of the programme, we will be investigating the use of supervised machine learning to have a human fitness instructor train the robot on how to be an encouraging ‘coach’.
The programme is
made up of 3x ~30 minute exercise sessions per week over 9 weeks – so
participants should be available and able to visit campus over the summer
period (approx.3rd June up until 18thAugustbut there
is time built in for participants to take a week or two off for holidays etc. We
will make the robot and exercise instructor available at set times each week
and set-up an online booking system for participants to choose slots from. One
reason for starting to recruit now is so that we can make sure these time
slots work for as many people as possible.
An initial information sheet is attached above, but essentially we are looking for participants who are:
– over 18, fluent
in English, with no health conditions that might prevent engaging in the
Couch to 5K programme
available and able to attend 3x ~30 minute weekly exercise sessions
at the Wallscourt Gym on Frenchay Campus from early June
– interested in
signing up for a long-term exercise programme to get running!
If you are interested in taking part please drop me an email and/or go ahead and complete this poll to give an idea of what day/times you might be available to work out! https://forms.gle/PG7zjHA1DVBqUmEx9