11 May 2020

If robots are to move among people in everyday life, they must be able to make decisions in real time, without human help. WASP doctoral student Olov Andersson describes in his thesis investigations into three different methods of learning.

Olov Andersson
Olov Andersson at Gränsö Manor. Photographer: Thor Balkhed
Reality is uncertain and changing – humans move in unpredictable ways, the weather is changeable, and cars, bicycles and animals can appear out of nowhere. It’s confusing for us, and even more confusing for a robot controlled by algorithms.

“The world doesn’t stand still and wait for the robot to make a decision – it has to happen here and now. Robots that navigate in traffic or in other public spaces must be able to make decisions in real time. The uncertainty from the surroundings is often mathematically neglected in the decision processes that control current autonomous systems”, says Olov Andersson, newly promoted doctor within WASP, the Wallenberg AI Autonomous Systems and Software Program.

Measuring uncertainty

It was this deficiency in dealing with uncertainty that he wanted to correct when he started working on his doctoral project at the Division for Artificial Intelligence and Integrated Computer Systems in the Department of Computer and Information Science. The reason that uncertainty is not included in the calculations is that it is not only complicated but also highly demanding, requiring extensive computing power. In addition, a small robot such as a drone is limited by the size and weight of processors and batteries it can carry.

Olov Andersson has investigated three different methods, which he has taken from artificial intelligence, machine learning and automatic control.

The first method, which has so far proved to be the best (or at least the most practical), is to use what is known as “probabilistic machine learning” combined with traditional optimisation-based control. The method gives a clear measure of the uncertainty, and the robot or drone learns to navigate safely and make sensible decisions as it flies.

Demonstration at Gränsö

Olov Andersson demonstrated this within the framework of WARA PS, the WASP arena for public safety, at Gränsö Manor in the autumn of 2019. The drone rapidly learned that Olov Andersson Photo credit Thor Balkhedtrees and lampposts stand still, so it could fly close to them, while it had to keep a close eye on people (Olov Andersson himself) and maintain a greater distance from them. Olov Andersson could also show on a screen that the uncertainty, the probability that a robot collides with something, was as low as a few percent after a short training session.

The second method that he investigated made use of neural networks and the type of artificial intelligence known as “deep learning”. This method is based on teaching a neural network which decisions are to be made, when and in which situation. Olov Andersson shows that the method can have advantages when it comes making fast decisions, but it requires huge amounts of training data. Further, it is more difficult to satisfy safety requirements.
“At the moment it requires a simulator to obtain sufficient training data, but I hope that neural networks can become more efficient in the future”, he says.

In the third method, he focussed on allowing the robot to learn more complex internal models of reality in real time, while at the same time having to act. One of the articles included in the thesis describes how this variant can be used to search for survivors after a disaster. It is also possible to include any other information available, such as observations, geographical data, etc.

Cross-disciplinary

“Autonomous systems is a field that needs both cross-disciplinary expertise and the opportunity to carry out experiments. The thesis contains articles that deal with artificial intelligence, robotics, and automatic control. It has been a huge advantage that I was part of WASP and the WASP graduate school. It gave me access to both deep and broad expertise in all these fields for discussions”, he says.

Olov Andersson is to continue his research career with Roland Siegwart, renowned professor in autonomous systems at ETH in Zürich.
“I have been awarded a Wallenberg postdoc through WASP, and I’m really looking forward to getting deeper into the field, such that my research can benefit society in the future.”

In addition to funding from WASP, parts of the research have been carried out within the strategic investment within IT and information technology, ELLIIT, and with funding from the Swedish Foundation for Strategic Research, SSF.

The thesis: Learning to make safe real-time decisions under uncertainty for autonomous robots, Olov Andersson, Department of Computer and Information Science, Linköping University 2020 Supervisor: Professor Patrick Doherty.
Olov Andersson successfully defended his thesis on 29 April 2020.

Video from Gränsö 2019

Video

Translated by George Farrants.



Contact

Olov Andersson

A robot politely gets out of the way

We are far from being able to coexist with flying robots in our urban landscapes, but one of the demonstrations this year within the WASP arena for public safety was a drone that politely gets out of the way when a person walks towards it.

A group of people sitting around a conference table

AI and interdisciplinarity go hand in hand

LiU has gained a strong position in artificial intelligence. In August, the government’s AI Commission visited Campus Valla to listen to researchers and acquaint themselves with supercomputers.

Portrait of Fredrik Heintz sitting on a staircase

Fredrik Heintz - member of the government’s new AI Commission

The Swedish government is appointing an AI Commission to strengthen Swedish competitiveness and develop the use of artificial intelligence (AI) in Sweden. One of the members is LiU professor Fredrik Heintz.

Latest news from LiU

Florian Trybel

The collaboration pushing back the boundaries of physics

Theoretician Florian Trybel has an irreplaceable role in creating new materials. Together with his experimental research colleague in Scotland he aims to expand the possibilities of materials in extreme conditions.

Kaiqian Wang.

Discovery about pain signalling may contribute to better treatment

LiU researchers have pinpointed the exact location of a specific protein fine-tuning the strength of pain signals. The knowledge can be used to develop drugs for chronic pain that are more effective and have fewer side effects.

Associate professor Jonathan Josefsson against a grey sky.

Unequal conditions for young people at UN climate summits

Today, young people can participate in major UN climate conferences. But inequality and bureaucracy make this impossible for many. This is the conclusion of a study carried out at Linköping University.