Explainability, Trust and Ethics for Robots and Autonomous Systems
Jim Torresen, Department
of Informatics
University of Oslo, Norway
jimtoer@ifi.uio.no
ABSTRACT
– A brief description of the tutorial
Explainability, trust and ethics for robots and autonomous
systems are getting increased attention. This is partly as a result of the
currently limited deployment of such systems in human support and interaction
settings. The tutorial will give an overview of the most commonly expressed ethical challenges and ways being undertaken to reduce their
impact using the findings in an earlier undertaken
review supplemented with
recent work and initiatives. The presentation will exemplify the challenges
related to privacy, security and safety through several examples from own and
others’ work.
KEYWORDS
Ethics, Robotics, Autonomous
systems, Privacy, Security and Safety
Outline of the tutorial
1.
Introduction
2. Ethical challenges and considerations and the
importance of explainable and trustworthy systems
3.
How to address ethical
considerations in research? – Examples from own research at Univ of Oslo
4.
Future opportunities in ethics
related research
Tutorial
slides can be found here (draft, to
be updated)
A detailed outline of the tutorial
Robots and artificial intelligence demonstrate to
effectively contribute to an increasing number of different domains. At the
same time, an increasing number of people – in the general public as well as in
research – have started to consider a number of potential ethical challenges
related to the development and use of such technology. There are also
initiatives across countries like the European Commission appointed High-Level
Expert Group on Artificial Intelligence (AI HLEG)
that has as a general objective to support the implementation of the European Strategy on Artificial Intelligence.
This tutorial will give an overview of the most commonly expressed ethical challenges and ways
being undertaken to reduce their impact using the findings in an earlier undertaken review
supplemented with recent work and initiatives.
Among the most important challenges are those related
to privacy, safety and security. Countermeasures can be taken first at design
time, second, when a user should decide where and when to apply a system and
third when a system is in use in its environment. In the latter case, there
will be a need for the system by itself to perform some ethical reasoning if
operating in autonomous mode. Specific attention will be needed if multiple,
fully autonomous systems are to interact and make decisions together. We are
currently undertaking research in various projects where the challenges appear,
including in robots for elderly at home and mental health care technology. The tutorial will introduce some examples
from our own and others work and how the challenges can be addressed both from
a technical and human side [1]-[5]. Ethical
issues should not be seen only as challenges but also as new research
opportunities contributing to more useful services and systems.
One example of the latter is
to study a robot to be located in the home of an older person living without a
partner. That is with the goal of developing multi-sensor mobile robot
solutions that can sense, learn and notify caregiver about abnormal events. We
have focussed on three crucial aspects of such a robot by addressing the
sensing system, the motion control system and considering the design and
behaviour of a robot from a user perspective. We see that key challenges for
such a robot relate to privacy, security and safety. The technological choices
being made with regards to hardware and software both make an impact on how
well the challenges are handled. The privacy
needs to be compromised between limiting sensor data collection and the ability
of a system to correctly notify the caregiver when some abnormal and emergency
situation has happened. At the same time, light conditions in a home can vary a
lot with sunlight at daytime and darkness at night-time. This puts certain
restrictions on what sensors that are most effective and that multiple
different sensors may be needed. However, rather than transmitting a lot of
personal sensor data to a caregiver facility, the local robot should train a
model to represent the regular activities of the person it supports. Then only
in the case of abnormal events, the robot would transmit data out of the home.
E.g., if the person does some daily exercises, a sudden increase in heart rate
would be expected while it is no so for a person not
usually doing any physical activity. Only in the latter case, sensor data
should be forwarded out of the home but only data that is regarded as essential
for the follow-up.
The tutorial will contain some parts where
participants discuss and comment on ethical challenges in small groups and in
plenary. Further, opinions within the audience will be collected through using
the Kahoot! voting tool (responding using smartphones to answer multiple-choice
questions). If virtual, text Q & A, live Q & A and attendee polls will
be used.
Length/format: Half day
Target
audience
There is increasing
attention on the ethical implications of robotics and AI research. Thus,
the tutorial will be targeting all attendees of the AAMAS-2021 conference.
The tutorial will give the audience insight into the main ethical implication
currently being discussed and also how that can open up for new directions in
autonomous agents and multiagent systems research. There is no specific prerequisite
knowledge required.
A
brief resume of the presenter
Name:
Jim Torresen
Postal
address:
PO Box 1080 Blindern, N-0316 Oslo, Norway
Phone numbers:
+4722852454 (office) +4792846669 (mobile)
E-mail
address: jimtoer@ifi.uio.no
Background in the tutorial area
Jim Torresen
is a professor at University of Oslo where he leads the Robotics and
Intelligent Systems research group. He received his M.Sc. and Dr.ing. (Ph.D)
degrees in computer architecture and design from the Norwegian University of
Science and Technology, Univ. of Trondheim in 1991 and 1996, respectively. He
has been employed as a senior hardware designer at NERA Telecom-munications (1996-1998) and at Navia
Aviation (1998-1999). Since 1999, he has been a professor at the Department of
Informatics at the Univ. of Oslo (associate professor 1999-2005). Jim Torresen has been a visiting researcher at Kyoto
University, Japan for one year (1993-1994), four months at Electrotechnical
laboratory (now AIST), Tsukuba, Japan (1997 and 2000)
and a visiting professor at Cornell University, USA for one year (2010-2011).
His research interests at the
moment include artificial intelligence, ethical aspects of AI and robotics,
machine learning, robotics, and applying this to complex real-world
applications. Several novel methods have been proposed. He has published over
200 scientific papers in international journals, books and conference
proceedings. 10 tutorials and a number of invited talks have been given at
international conferences and research institutes. He is in the program
committee of more than ten different international conferences, associate
editor of three international scientific journals as well as a regular reviewer
of a number of other international journals. He has also acted as an evaluator
for proposals in EU FP7 and Horizon2020 and is currently project manager/principal
investigator in four externally funded research projects/centres. He is a
member of the Norwegian Academy of Technological Sciences (NTVA)
and the National Committee for Research Ethics in Science and Technology (NENT) where he is a member of a working group on research
ethics for AI. More information and a list of publications can be found here: http://jimtoer.no/
Information about previous tutorials delivered by the
presenters
See an overview of past invited talks and tutorials here.
ACKNOWLEDGMENTS
This work is partially supported by
The Research Council of Norway as a part of Multimodal Elderly Care systems
(MECS) project, under grant agreement 247697, the INTROducing
Mental health through Adaptive Technology (INTROMAT)
project under grant agreement 259293 and Vulnerability in the Robot Society
(VIROS) under grant agreement 288285, Predictive
and Intuitive Robot Companion (PIRC)
under Grant Agreement No. 312333 and through its Centres
of Excellence scheme, RITMO with Project No. 262762.
REFERENCES
[1] Ryo Saegusa,
Hirokazu Ito, Duc Minh Duong, “Human-Care Rounds
Robot with Contactless Breathing Measurement", in proc. of 2019
International Conference on Robotics and Automation (ICRA),
Montreal, Canada, May 20-24, 2019 https://doi.org/10.1109/ICRA.2019.8794037
[2] Bringsjord,
Selmer & Tokhi, M.O. & Isabel, Maria & Aldinhas Ferreira, Maria Isabel & Govindarajulu,
Naveen. (2019). Hybrid Worlds: Societal and Ethical Challenges, CLAWAR Association Series on Robot Ethics and Standards, http://kryten.mm.rpi.edu/HybridWorlds.pdf
[3] Torresen,
J., “A Review of Future and Ethical Perspectives of Robotics and AI.” Frontiers
in Robotics and AI, vol. 4, article 75, 2018. https://doi.org/10.3389/frobt.2017.00075
[4] Winfield, A. F., Blum, C., and Liu,
W. (2014). “Towards an ethical robot: internal models, consequences and ethical
action selection,” in Advances in Autonomous Robotics Systems, eds
M. Mistry, A. Leonardis, M. Witkowski, and C. Melhuish, 2014 Springer, pp. 85–96. https://doi.org/10.1007/978-3-319-10401-0_8
[5] Winfield, A. F., Michael, K., Pitt
J. and Evers V., "Machine Ethics: The Design and Governance of Ethical AI
and Autonomous Systems [Scanning the Issue]," in Proceedings of
the IEEE, vol. 107, no. 3, pp. 509-517, March 2019. https://ieeexplore.ieee.org/document/8662743
Conference Name:ACM Woodstock
conference