Sequential inference for real-time probabilistic modelling

Project Details

Description

This project aims at advancing the state of the art in probabilistic modelling related to sensor fusion. This is accomplished by the combination of recent advances in probabilistic model specification methods from machine learning with powerful computational methods in signal processing and control engineering. The methodology allows noisy information streams to be combined into one model. This computational methodology will allow real-time probabilistic inference on mobile devices with limited resources.
Short titleSolin Arno 31.8.2020
StatusFinished
Effective start/end date01/09/201731/08/2020

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.
  • Gaussian Process Priors for View-Aware Inference

    Hou, Y., Heljakka, A. & Solin, A., 2021, THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE. AAAI, p. 7762-7770 9 p. (AAAI Conference on Artificial Intelligence; vol. 35).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Open Access
  • PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation

    Solin, A., Cortés Reina, S., Rahtu, E. & Kannala, J., 2018, Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018. IEEE, p. 616-625 10 p. (IEEE Winter Conference on Applications of Computer Vision).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Open Access
    File
    21 Citations (Scopus)
    168 Downloads (Pure)
  • Scalable Magnetic Field SLAM in 3D Using Gaussian Process Maps

    Kok, M. & Solin, A., 5 Sep 2018, 21st International Conference on Information Fusion: FUSION 2018. IEEE, p. 1353-1360 8 p. 8455789

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Open Access
    File
    30 Citations (Scopus)
    151 Downloads (Pure)