Danica Kragić Jensfelt

Danica Kragić Jensfelt

Organised by University of Rijeka

In partnership with:
Ministry of Science and Education of the Republic of Croatia and the European Commission as part of the Croatian Presidency of the Council of the European Union

Date and Venue:
June 15-18, 2020, Zoom

Danica Kragic is a Professor at the School of Computer Science and Communication at the Royal Institute of Technology, KTH. She received MSc in Mechanical Engineering from the Technical University of Rijeka, Croatia in 1995 and PhD in Computer Science from KTH in 2001. She has been a visiting researcher at Columbia University, Johns Hopkins University and INRIA Rennes. She is the Director of the Centre for Autonomous Systems. Danica received the 2007 IEEE Robotics and Automation Society Early Academic Career Award. She is a member of the Royal Swedish Academy of Sciences, Roayls Swedish Academy of Engineering Sciences and Founding member of Young Academy of Sweden. She holds a Honorary Doctorate from the Lappeenranta University of Technology. She chaired IEEE RAS Technical Committee on Computer and Robot Vision and served as an IEEE RAS AdCom member. Her research is in the area of robotics, computer vision and machine learning. In 2012, she received an ERC Starting Grant and in 2019 Distinguished Professor Grant from the Swedish research Council. Her research is supported by the Knut and Alice Wallenberg Foundation, Swedish Foundation for Strategic Research, EU and Swedish Research Council.

Building systems and machines that are autonomous and intelligent, taking over dirty, dull and dangerous jobs, has been an integral part of human history for a long time. Recent advances in robotics, artificial intelligence and machine learning have demonstrated how these can be utilized in development of technologies that exhibit rather advanced capabilities. In integration with human decision making and experience, artificial systems are today used to make diagnostics in health applications, make estimations of weather conditions to secure crops, provide more informed predictions of potential earthquakes, and more. Apart from purely software solutions, we are also seeing the beginning of more advanced hardware solutions, robotic systems that are equipped with various sensor technologies and are built to physically interact with humans at workplaces, and sometimes in the future, even our homes.

 

Humans poses a fantastic ability to acquire complex behaviors from watching another person. It is remarkable to observe how even small children acquire advanced object manipulation skills, first  through observation, but then master these through training: extensive and rich interaction with the environment using not only vision but also proprioception and haptic feedback. Initial observations are needed to understand goals of complex behaviors but repeated, extensive interactions with the physical world are necessary to ground the behaviors in own sensing and reuse these in new situations.  Robots acquiring behaviors solely from human demonstrations and unstructured videos rather than through explicit programming has been a research vision for a long time – probably even from the time a first robot was built. But still, having a robot that is able to adapt and enrich its knowledge through self-supervised learning remains one of the open challenges.  Thus, to be deployed in natural environments, robots need the ability to learn skills autonomously, through continuous interaction with the environment, humans and other robots.

 

I will discuss a need for rethinking how we structure our research and development toward future society and professions. We need to be open and careful regarding the potential risks associated to the considered research areas. The advent of ubiquitous, intelligent robots in society poses fundamental social questions, particularly their effects on societal values such as privacy, individual autonomy, and social inclusion