Month: May 2023

Researchers and industry try their hand at swarm and soft robotics

Posted on by miranda.addey

TAS Functionality Node invited developers, operators, end users and researchers to attend two masterclasses in April and May, taking place at Bristol Robotics Laboratory. Participants heard about the TAS Node project, its recent outputs and the test cases in swarm, soft and aerial robotics- and how these autonomous systems may be deployed in logistics, manufacturing and infrastructure industries. They then explored the capabilities of these technologies in soft and swarm robotics via an interactive ‘teaching and doing’ format. One participant Peta Masters, from King’s College, London thanked us for delivering “a terrific masterclass last Thursday and for showing us around the robotics lab, which I thought was just fabulous. What an exciting place to work. Really inspiring.”

In the swarm workshop the participants got to programme a swarm of robots and see their simulation enacted.

Participants were split into 3 teams, each responsible for programming one of the robots in the swarm. The objective was to get the robots to pick up a carrier without bumping into obstacles. Each team started by simulating programming their robot’s behaviour and testing it out through simulations. Then they got to transfer the code to the robots and see their algorithm plays out in real life.

In the soft robotics workshop, participants tried two different demos to show how easy it is to build a soft robot but how complex it is to control.

In the first demo, they built a soft continuous manipulator with a polythene roll they had to cut and hermetically seal. The manipulator was then inflated through a compressor, and participants had to figure out how to control it to bring down objects in specific positions without touching other things simultaneously. Due to their nature, soft robots have theoretically infinite degrees of freedom. The idea was to move it through cables, but the problems they had to solve were: Where are the best places to stick cables? How many cables do we need? In addition, cables needed to be guided along the structure; how much room do we have to leave between each guide? They experimented with how the behaviour of soft manipulators can change dramatically, only changing these aspects.

The second demo was about soft grippers and modularity. As we said before, soft robot control can be very complex, so if we divide the problem into smaller problems, would it be easier to control a soft robot? This is the thinking behind a modular soft gripper. Participants were asked to assemble a soft gripper joining together different pieces..

Lastly everyone learned more about cobotics (collaborative robots) by using the soft gripper they assembled with a traditional gripper mounted on the robotic arm UR10. In this collaborative simulation, one person had to operate the soft gripper, another the robotic arm, and another the hard gripper.

Thanks to everyone who came to try out our masterclass!

Robots unite! Somerset families swarm to play our robot game

Posted on by miranda.addey

How do natural swarms interact and how can we use that to our benefit in robotics? Visitors to the first ever Somerscience, which took place in Bruton on the May Day bank holiday, found out the answers to these questions and more and became robot swarms themselves in our special TAS swarm game. Neshika, Suet, Razanne, Fern and Matimba from our swarm team gave an insight into their research, whilst guiding the visitors of all ages to their spot on the leaderboard. In small teams the human ‘robots’ and their controller were asked to move all the boxes to the landing zone- and figure out the rules for moving the different types of boxes as they went along. The team also showed videos of the swarm robots and posters detailing their work. Later our very own Sabine took to the stage to answer questions for a special edition of I’m a Scientist, Get me out of here. By the end of the day we had a winning time of 1 minute 45 seconds– and our demonstrators really enjoyed talking to interested and enthusiastic members of the public. 

Thanks to all the organisers and visitors on the day- if you’d like a robot swarm to descend on your event, do get in touch.

Hasta la vista baby: is it time to terminate the term ‘autonomous systems’?

Posted on by Katie Drury

In a new paper published in AI & Society: Knowledge, Culture and Communication, the TAS Functionality Node’s Helen Smith, Kerstin Eder and Jonathan Ives argue that using the term ‘autonomous’ to describe the capabilities of highly automated systems is misleading at best.

Drawing on examples from widely-know science fiction, the Cyberdyne Systems Model T-800 depicted in the Terminator and Terminator 2 films is presented as a great example of an adaptive system that demonstrates evolving functionality and decision-making. However, the authors observe that it can hardly be defined as autonomous when its overall goals and limitations are set by another agent, removing autonomy or ‘freedom of choice’ from its functionality.

The authors look at the implications of describing a system as autonomous, since in doing so we would be assigning moral agency to it. On this basis, the expectation would be that a system is a moral agent and therefore can be held responsible for bad decisions, which is simply not feasible (‘a computer cannot be fined or put in jail when a bad decision is made’ (Dignum et al, 2018, p.63)).

The authors conclude that the correct use of language to describe critical systems is vital to ensure responsibility for the systems’ decisions and actions is attributed to those designing, developing and operating these systems, rather than the systems themselves.

More information

Read the full paper: https://doi.org/10.1007/s00146-023-01662-9

This paper was led by Dr Helen Smith, a Research Associate in Engineering Ethics and Registered Nurse based in the Centre for Ethics in Medicine at the University of Bristol. Helen works as part of the TAS Node team bringing her expertise in the ethical and legal challenges of AI use in healthcare (and beyond).