• Publications
  • Influence
A comparative analysis of radar and lidar sensing for localization and mapping
It is shown that while producing slightly less accurate maps than a lidar, the radar can accurately perform SLAM and build a map of the environment, even including details such as corners and small walls.
The Auto-Complete Graph: Merging and Mutual Correction of Sensor and Prior Maps for SLAM
The Auto-Complete Graph is presented, a graph-based SLAM method merging elements of sensor and prior maps into one consistent representation that handled up to 40% of noise in odometry, was robust to varying levels of details between the prior and the sensor map, and could correct local scale errors of the prior.
A Method to Segment Maps from Different Modalities Using Free Space Layout MAORIS: Map of Ripples Segmentation
A flaw in the segmentation evaluation metric used in recent works is identified and a metric based on Matthews correlation coefficient (MCC) is proposed, which is shown to show better results than state of the art for both types.
SLAM auto-complete: Completing a robot map using an emergency map
This paper focuses on emergency maps as priors for robot mapping since they are easy to get and already extensively used by firemen in rescue missions, however, those maps can be outdated, information might be missing, and the scales of rooms are typically not consistent.
Using sketch-maps for robot navigation: Interpretation and matching
This paper proposes to use a Voronoi diagram obtained from the distance image on which a thinning parameter is used to remove spurious branches to interpret the sketch-map and uses an efficient error-tolerant graph matching algorithm to find correspondences, while keeping time and memory complexity low.
Helping robots help us : Using prior information for localization, navigation, and human-robot interaction
Maps are often used to provide information and guide people and sketch maps can easily be drawn to give directions.
URSIM: Unique Regions for Sketch Map Interpretation and Matching
We present a method for matching sketch maps to a corresponding metric map, with the aim of later using the sketch as an intuitive interface for human–robot interactions. While sketch maps are not