Joint Inference and Belief Space Planning

Inference and decision making under uncertainty are essential in numerous robotics problems. In recent years, the similarities between inference and control triggered much work, from developing unified computational frameworks to pondering about the duality between the two. In spite of the aforementioned efforts, inference and control, as well as inference and belief space planning (BSP) are still treated as two separate processes. We propose a novel approach that utilizes the similarities between inference and BSP and make the key observation that inference can be efficiently updated using the precursory planning stage, thus paving the way towards a joint inference and BSP paradigm.

Updating inference with a precursory planning stage can be considered as a deviation from conventional Bayesian inference. Rather than updating the belief from the previous time instant with new incoming information (e.g. measurements), we propose to exploit the fact that similar calculations are already performed within planning in order to appropriately update the belief in inference by far more efficiently.

 

In Proceedings

  • E. Farhi and V. Indelman. Towards Efficient Inference Update through Planning via JIP – Joint Inference and Belief Space Planning. In IEEE International Conference on Robotics and Automation (ICRA), May 2017.
    [BibTeX] [PDF] [Slides]
    @InProceedings{Farhi17icra,
    author = {E. Farhi and V. Indelman},
    title = {Towards Efficient Inference Update through Planning via JIP - Joint Inference and Belief Space Planning},
    booktitle = "IEEE International Conference on Robotics and Automation (ICRA)",
    year = 2017,
    month = "May",
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Farhi17icra.pdf",
    slides = "http://indelman.github.io/ANPL-Website/Publications/Farhi17icra_ppt.pdf",
    location = {Singapore},
    researchtopic = {JIP},
    }

wordpress stat