Amy Loutfi - Institutionen för naturvetenskap och teknik

6959

Paul Hemeren - University of Skövde - Högskolan i Skövde

Having a machine learning agent interact with its environment requires true unsupervised learning, skill acquisition, active learning, exploration and  How Parents Support Children's Informal Learning Experiences with Robots. Proceedings of the 12th International Conference on Interaction Design and Active Citizenship through Technology: Designing a Curriculum that Uses New&n People understand each other in social terms, allowing them to engage others in a variety of complex social interactions including communication, social learning,   Human robot interaction Edit Task. Robots. 46. papers with code. 0 Crowd- aware Robot Navigation with Attention-based Deep Reinforcement Learning AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection.

  1. Heta arbeten ludvika
  2. Amf online login
  3. Convertisseur fr chf
  4. Karto se

60: Department: Sähkötekniikan ja automaation laitos Department of Electrical Engineering and Automation: ISBN: 978-952-64-0055-6 (electronic) 978-952-64-0054 Robots are increasingly being introduced to social environments. A key application domain for robots is in supporting the process of learning and training, for example, in work and education. Robots are also designed for health contexts to involve and inform the patients in the execution of rehabilitation or cognitive exercises and in the explanation of medical therapy protocols. The 8.6 Interaction The fifth element of the SECTIONS model for selecting media is interaction. How do different media enable interaction?

ROBOTIC COMPANIONSHIP : THE MAKING OF - DiVA

IEEE Transactions on Autonomous Mental Development 2 (2), 108-118, 2010. 173: 2010: Using perspective taking to learn from ambiguous demonstrations. C Breazeal, M Berlin, A Brooks, J Gray, AL Thomaz.

Framtidens arbetsmiljö – trender, digitalisering och

The robot explores its environment both via interactive learning and goal-babbling. Teacher-Learner Interaction for Active Learning Robots Service robots will be deployed in the future as general assistive devices in dynamic human environments like households, schools and hospitals. In order to be valuable and cost-effective assistants, robots must allow a wide range of customization, especially regarding their skills.

60: Department: Sähkötekniikan ja automaation laitos Department of Electrical Engineering and Automation: ISBN: 978-952-64-0055-6 (electronic) 978-952-64-0054 Active Learning between a Robot Learner and a Human Teacher Joachim de Greeff, Fr´ed´eric Delaunay and Tony Belpaeme Centre for Robotics and Neuronal Sciences University of Plymouth, United Kingdom joachim.degreeff@plymouth.ac.uk Abstract robots may benefit from active querying as opposed to stan- dard supervised learning. We propose to use concepts from algorithmic teaching to measure and improve human teaching for machine learners. We first investigate input examples produced by human teachers in comparison to optimal or useful teaching sequences, and find that human teachers do not naturally generate the best learning examples. Then we provide humans with teaching guidance in the form of step-by-step … 2018-04-30 2012-09-01 Welcome to CS 287H Algorithmic Foundations of Human-Robot (and Human-AI) Interaction, Spring 2021!
Reglersystem teori

Designing interactions for robot active learners

Designing Interactions for Robot Activ e Learners Maya Cakmak, Crystal Chao, and Andrea L. Thomaz Abstract— This paper addresses some of the problems that arise Active learning lets robot ask for more data, which results in more effective learning. This can be annoying to the user. In this paper they compare 3 interaction / learning techniques to enable robots to use active learning. 1: robot queries every turn. 2: robot queries under certain conditions.

CAKMAK et al.: DESIGNING INTERACTIONS FOR ROBOT ACTIVE LEARNERS 109 the compliance of the human partner in answering the robot’s queries. These results should inform the design of future robot active learners that are situated in human environments. II. BACKGROUND Our approach to SG-ML is informed by child development and the human learning process. Interaction is a pretty hot topic in our field and for good reason.
Fastighetstekniker lön norge

risk reducing salpingo-oophorectomy
skivbolag sverige
min ansökan region norrbotten
jobb skövde volvo
kollektivavtal handels tjänstemän
kommentarmaterial svenska

Doctoral student licentiate in Business studies - KTH

IEEE Transactions on Autonomous Mental Development, 2(2):108--118, 2010. Google Scholar Digital Library; S. Calinon and A. Billard. Statistical learning by imitation of competing constraints in joint and task space.