Few-shot model-based adaptation in noisy conditions

Karol Arndt*, Ali Ghadirzadeh, Murtaza Hazara, Ville Kyrki

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)
141 Downloads (Pure)


Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additional challenge may be posed by domain noise, which is present in virtually all real-world applications. In this letter, we propose to perform few-shot adaptation of dynamics models in noisy conditions using an uncertainty-aware Kalman filter-based neural network architecture. We show that the proposed method, which explicitly addresses domain noise, improves few-shot adaptation error over a blackbox adaptation LSTM baseline, and over a model-free on-policy reinforcement learning approach, which tries to learn an adaptable and informative policy at the same time. The proposed method also allows for system analysis by analyzing hidden states of the model during and after adaptation.

Original languageEnglish
Article number9384205
Pages (from-to)4193-4200
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number2
Publication statusPublished - Apr 2021
MoE publication typeA1 Journal article-refereed


  • Adaptation models
  • Data models
  • Kalman filters
  • Noise measurement
  • Predictive models
  • Task analysis
  • Uncertainty


Dive into the research topics of 'Few-shot model-based adaptation in noisy conditions'. Together they form a unique fingerprint.

Cite this