Research Program 6 (R6)
Autonomous AI
Autonomous systems are increasingly reliant on AI methods. FCAI Research Program R6 Autonomous AI addresses the fundamental challenges of long-term autonomous operation, in particular, how learning and planning can be performed to ensure safe operation over long time horizons. The program aims to make Autonomous AIs data-efficient by actively collecting data while acting in the world. The main challenges include 1) long-term decision making; 2) safe learning during operation; and 3) reliable perception and navigation.
Examples of publications:
Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman. 2022. Training and evaluation of deep policies using reinforcement learning and generative models. Journal of Machine Learning Research (JMLR) 23:174.
Adrien Corenflos, Nicolas Chopin, Simo Särkkä. 2022. De-Sequentialized Monte Carlo: a parallel-in-time particle smoother. Journal of Machine Learning Research (JMLR) 23, 1-39.
Karol Arndt, Murtaza Hazara, Ali Ghadirzadeh, Ville Kyrki. 2020. Meta Reinforcement Learning for Sim-to-real Domain Adaptation. Proceedings of the IEEE Conference on Robotics and Automation, ICRA 2020.
Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen. 2020. Self-paced deep reinforcement learning. Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), Advances in Neural Information Processing Systems, 33.
Coordinating professor: Ville Kyrki – ville.kyrki at aalto.fi
People
The groups of following PIs take part in the Research Program Autonomous AI. If you would like to join this program, please contact the coordinating professor.
Dominik Baumann, Aalto University
Shankar Deka, Aalto University
Keijo Heljanko, University of Helsinki
Perttu Hämäläinen, Aalto University
Alexander Ilin, Aalto University
Juho Kannala, Aalto University
Hannu Karvonen, VTT
Samuel Kaski, Aalto University
Juha Kortelainen, VTT
Tomasz Kucner, Aalto University
Matti Kutila, VTT
Ville Kyrki, Aalto University – coordinating professor
Harri Lähdesmäki, Aalto University
Petteri Nurmi, University of Helsinki
Joni Pajarinen, Aalto University
Laura Ruotsalainen, University of Helsinki
Arno Solin, Aalto University
Simo Särkkä, Aalto University
Fundamental AI Research
Joint methodological goal
AI-assisted decision-making, design and modeling →
Research Programs
Probabilistic AI →
Simulators →
Deep learning →
Privacy and security →
Interactive AI →
Autonomous AI →
AI in society →
Highlight Programs
Modeling tools →
Health →
Service assistant →
Atmospheric →
Materials →
Sustainability →