Job opportunity: Systems Engineering Research Associate/Senior Research Associate in Trustworthy Autonomous Systems

Cutting-edge autonomous systems can change functionality during operation through autonomous learning and adaptation. This gives them enormous potential, including being able to operate autonomously in complex and dynamic real-world environments. However, the ability to evolve in functionality also poses significant challenges to current processes for specifying, designing, analysing, verifying, and validating these systems.

This position sets out to address this Systems Engineering challenge with a focus on ensuring that these adaptive systems are safe, reliable and demonstrably trustworthy. The research will involve working with a multidisciplinary team to develop new systems engineering approaches and apply them to specific case studies in swarm robotics, soft robotics and machine learning unmanned air vehicles.

Further information

For more details about the role and how to apply, visit the University of Bristol job site: Vacancy ref. ACAD106473

Closing date: 5 December 2022

 

Job opportunity: Research Associate/Senior Research Associate in Aerial Robotics

This exciting research position sets out to develop flight control systems for Uncrewed Air Vehicles (UAVs) based on machine learning. You will be developing reinforcement learning based flight control systems for micro quadcopters and hybrid flight control systems for morphing wing UAVs. You will then experimentally test and validate these using advanced free flight and wind tunnel testing facilities.

This position is part of our multidisciplinary UKRI Trustworthy Autonomous Systems Node in Functionality which explores how to develop trustworthy adaptive autonomous systems. The successful applicant will be part of a large multidisciplinary team of researchers from ethics, sociology, computer science and engineering working together to develop design-for-trustworthiness techniques for a wide range of autonomous systems, including swarm robotics, soft robots, and unmanned air vehicles. They will also be a part of the larger national £33 million UKRI Trustworthy Autonomous Systems programme.

The position will be based at the Bristol Robotics Laboratory, the largest centre for multidisciplinary research in the UK. This position will also involve close interaction with the Bio-inspired Flight Lab, and the Bristol Flight Lab at the University of Bristol.

Further information

For more details about the role and how to apply, visit the University of Bristol job site: Vacancy ref. ACAD106468

Closing date: 1 December 2022

Functionality research showcase at FUTURES 2022

Last week our Ethics and Regulation researchers participated in the FUTURES 2022 Schools Research Fair in the SS Great Britain’s dockyard in Bristol. They joined research teams from the Universities of Bristol and Bath each showing interactive exhibits aimed to excite young children about the wide range of research across the University’s portfolio.

At the TAS Functionality Node stand, children from local primary and secondary schools were asked to consider a number of questions, such as:

“Should there be a human driver present ready to take-over in an autonomous car?”
“Should online medical advice provided by AI inform users they are communicating with a non-human?”
“Should self-driving cars be as safe or safer than the average human driver?”

Ideas were collated into a word cloud (pictured) summarising the range of feelings participants expressed about trusting and regulating autonomous technologies.

Dr Arianna Manzini, Research Associate in Ethics of Autonomous Systems, who led the exhibition said:

“We are grateful to all the schools who participated. It was fantastic to see so many children engaging with our questions and sharing their views about the future of robotics!”

The Schools Research Fair was held as part of the FUTURES 2022 festival of discovery taking place at venues across the South West of the UK this Autumn. The overall ambition of this series of free events is to provide multiple opportunities for the public to find out about innovative, world-class research that universities are leading on across the region. The focus is on interactivity and fun, bringing research to life to inspire others to get involved or learn more.

Our participation in the event formed part of a series of outreach events planned for the whole TAS Functionality Node Programme. Follow us on Twitter @tas_function or via our Events listings on this site to be the first to hear about future events.

Wordcloud of feedback from participants
Word cloud generated by survey responses
Photo of the TAS Functionality Node exhibition at FUTURES 2022
Our exhibition stand at FUTURES 2022

Recycling materials in soft robotics

It’s important for all fields to consider their environmental impact, and robotics doesn’t currently have a rich history of research into sustainability. In this recent paper Professor Rossiter, Dr Partridge and Dr Manzini, from our TAS Functionality Node, demonstrate their research into reducing the waste for soft robotics.

The need for soft bodies and actuators in this field leads to the use of large amounts of silicon, rubber and other elastomers, which isn’t normally recycled. In the paper the authors present a non-chemical process to recycle and reuse these elastomeric materials, which, as well as decreasing the amount the harmful waste, has the extra benefits of minimising the amount of new material needed and lowering costs. The material from old and broken soft actuators was ground into granules ranging from 1mm in diameter to 3mm in diameter and used to create new soft actuators without loss of function. Characterisation tests showed that although some functionality reduced with the percentage of recycled material, the silicone composites exhibited very comparable elastic properties to the pristine silicone.

The authors propose that these materials could then form a pipeline where every time they’re recycled they’re used in lower and lower risk applications. This technique could also help other fields reduce their waste.

Watch this short video to see the research in action:

Access the full paper: ReRobot: Recycled Materials for Trustworthy Soft Robots

And please do leave a comment – we’d love to hear from you!

Robot Hackathon

In June this year the universities of York, Manchester and Sheffield hosted a hackathon – a competition designed to collaboratively solve a problem in a particular field. The competing teams were a mix of undergraduates, postgraduates and post-doctoral researchers. The goal of the competition was to produce some code that would allow a single operator to control a group of 5 robots. The TAS functionality node was represented at the event by Dr Sabine Hauert and Dr James Wilson.

Over the three days attendees heard from an expert panel discussing key challenges around swarm robotics, which included Dr Hauert, and helped develop solutions for remotely operating robot swarms, using Pi-puck and MONA robots.  On the final day teams made presentations, with prizes for the best solutions.

The competition involved the robots moving around a small arena and gathering in locations (generated virtually) to score points. The locations themselves were labelled from 1-5, which was the amount of robots you needed gathered there in order to gain points. Most of the devised solutions involved control over a single agent with others following along autonomously, though some groups put together fully autonomous solutions. Some groups were even able to run code on swarms remotely at other universities which was fun!

Thanks to the universities, organisers, hosts and speakers for a brilliant time.

 

 

Autonomous vehicle testing using game engines

We’re excited to announce the recent publication by some members of our team, Professor Kerstin Eder and Dr Greg Chance of the Trustworthy Systems Laboratory (https://www.bristol.ac.uk/tsl), of research into the determinism of game engines used for simulation-based autonomous vehicle verification. These simulations are useful in developing control systems and test environments for the vehicles; but only if they behave deterministically, and therefore yield reliable and repeatable results. Unfortunately, this isn’t a characteristic of game engines and they often produce different outcomes for the same initial conditions. The paper, published in IEEE Transactions on Intelligent Transportation Systems, presents the causes and effects of this non-deterministic behaviour, and sets forth a case study showing the shortcomings of a particular simulator, and a methodology to assess and minimize simulation precision. To read the paper please go here: On Determinism of Game Engines Used for Simulation-Based Autonomous Vehicle Verification 

Participants wanted for SWARM study

Would you like to help with research on the regulation of what future AI-driven nanomedicines should look like? If so, we are looking for volunteers to discuss ethical and regulatory issues of using AI driven cancer therapies with swarm behaviour through a series of interviews.

The research is part of the SWARM study – Small robots With collective behaviour as AI-driven cancer therapies; building Regulations for future nanoMedicines.

We are looking for:

  • Oncology healthcare professionals
  • Cancer patients
  • Regulatory or policymakers in drug delivery/oncology
  • Nanomedicine researcher or developers

Volunteers must be over the age of 18 years old to take part. We would love to hear from you. You can find out more about the study on our SWARM study webpage or by contacting Matimba Swana at matimba.swana@bristol.ac.uk.

If you would like to take part please complete this Expression of Interest Form.

Participants wanted for ethics study

Would you like to help in some research on the ethics of robots? If so, we are looking for volunteers to discuss ethical issues around robots and autonomous systems that are capable of learning from their surroundings and changing what they do.

The research is part of the ARET: Adaptable Robots, Ethics, and Trust study. In old English ‘aret’ means ‘to ‘entrust’, and ‘arête’ is a term used by Ancient Greek philosophers to indicate moral virtue or excellence.

If you are aged 18 or over, we would love to hear from you. You do not need to have any previous knowledge of autonomous systems to participate as we will show you images and videos to introduce you to the technologies.

You can find out more about the study on our ARET: Adaptable Robots, Ethics, and Trust study webpage or by contacting Arianna Manzini at arianna.manzini@bristol.ac.uk.

If you would like to take part please complete this volunteer form.

Powering emergency food distribution using swarms: Results from the DOTS competition are in

Find out how robots called DOTS (Distributed Organisation and Transport Systems) were used to help simulate the distribution of emergency food parcels in a competition run jointly by the Bristol Robotics Laboratory, Toshiba Bristol Research and Innovation Laboratory and the South Gloucestershire Council’s UMBRELLA project.

Increases in the number of emergency food parcels distributed by food banks have accelerated over the course of the coronavirus pandemic, particularly in those going to children. Robot swarms could help streamline the distribution of these emergency food parcels, while freeing up time for volunteers and workers to interface with the users and provide human contact.

Read about how participants in the competition brainstormed and engineered solutions to tackle the challenge and watch their simulations on the RoboHub website.