Patric Jensfelt

TL;DR: The method uses multi-hypothesis Kalman filter based pose tracking combined with a probabilistic formulation of hypothesis correctness to generate and track Gaussian pose hypotheses online and generates movement commands for the platform to enhance the gathering of information for the pose estimation process.

TL;DR: An approach for creating conceptual representations of human-made indoor environments using mobile robots that is composed of layers representing maps at different levels of abstraction and incorporates a linguistic framework that actively supports the map acquisition process.

TL;DR: In this article, a probabilistic approach for mobile robot localization using an incomplete topological world model is presented, which is termed multi-hypothesis localization (MHL).

TL;DR: A probabilistic framework combining heterogeneous, uncertain, information such as object observations, shape, size, appearance of rooms and human input for semantic mapping that relies on the concept of spatial properties which make the semantic map more descriptive, and the system more scalable and better adapted for human interaction.

TL;DR: This work proposes an approach based on supervised learning to classify the pose of a mobile robot into semantic classes and introduces an approach to learn topological maps from geometric maps by applying the semantic classification procedure in combination with a probabilistic relaxation method.