SkiMap: An efficient mapping framework for robot navigation

Gregorio, Daniele De; Stefano, Luigi Di

doi:10.1109/icra.2017.7989299

Cited by 26 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first task is to build the RGB Volume, just as in the original SkiMap approach [1]. Accordingly, colour information is fused into a RGBWeightedVoxel data structure implementing weighted sum/subtraction operations.…”

Section: Frame Integration Modulementioning

confidence: 99%

“…Accordingly, colour information is fused into a RGBWeightedVoxel data structure implementing weighted sum/subtraction operations. As mentioned in our previous work [1], this is a peculiar trait of SkiMap, which allows the system to integrate new sensor measurements or de-integrate past data marked as invalid.…”

Section: Frame Integration Modulementioning

confidence: 99%

“…We introduce SkiMap++, an extension to the recently proposed SkiMap mapping framework for robot navigation [1]. The extension deals with enriching the map with semantic information concerning the presence in the environment of certain objects that may be usefully recognized by the robot, e.g.…”

Section: Introductionmentioning

confidence: 99%

“…For example, a simple 2D occupancy grid allows for efficiently planning a path through a large environment but might turn out much less effective than richer representations (such as a 2.5 height map or a 3D voxel grid) in helping the robot to avoid different types of obstacles. To tackle some of the research issues associated with map-ping for robot navigation, we have recently introduced the SkiMap framework [1], which turns out both time and memory efficient thanks to a novel core data structure organized as a Tree of SkipLists and, peculiarly, features a multi-level querying system capable to obtain rapidly representations as diverse as a 3D voxel grid, a 2.5D height map and a 2D occupancy grid.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 3 more Smart Citations

SkiMap++: Real-Time Mapping and Object Recognition for Robotics

Gregorio

Cavallari

Stefano

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

Self Cite

View full text Add to dashboard Cite

Figure 1. Large-scale map reconstructed online by SkiMap++ through a mobile robot equipped with an head-mounted RGB-D camera. Purple spheres represent areas found alongside with reconstruction which are likely to contain object instances. Magnified circles represent outcomes of the final Instance Estimation Algorithm, which is performed in the aforementioned areas only. The whole map is acquired by relying on the robot's own odometry in order to track camera poses over time. AbstractWe introduce SkiMap++, an extension to the recently proposed SkiMap mapping framework for robot navigation [1]. The extension deals with enriching the map with semantic information concerning the presence in the environment of certain objects that may be usefully recognized by the robot, e.g. for the sake of grasping them. More precisely, the map can accommodate information about the spatial locations of certain 3D object features, as determined by matching the visual features extracted from the incoming frames through a random forest learned off-line from a set of object models. Thereby, evidence about the presence of object features is gathered from multiple vantage points alongside with the standard geometric mapping task, so to enable recognizing the objects and estimating their 6 DOF poses. As a result, SkiMap++ can reconstruct the geometry of large scale environments as well as localize some relevant objects therein (Fig.1) in real-time on CPU. As an additional contribution, we present an RGB-D dataset featuring ground-truth camera and object poses, which may be deployed by researchers interested in pursuing SLAM alongside with object recognition, a topic often referred to as Semantic SLAM. 1

show abstract

Section: Frame Integration Modulementioning

confidence: 99%

Section: Frame Integration Modulementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

SkiMap++: Real-Time Mapping and Object Recognition for Robotics

Gregorio

Cavallari

Stefano

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This amount of data is enough for training and comprehensive evaluation of the models and at the same time is feasible to download and process. See Table I for comparison with existing datasets. Multiple algorithms for constructing maps have been proposed [19], [20], [21], some of them are based on deep learning [22], [23], [24]. However benchmarking of these methods is currently complicated due to lack of a suitable dataset.…”

Section: Introductionmentioning

confidence: 99%

DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation

Kirsanov

Konushin

Gaskarov

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate the sequences using realistic home layouts. For that we sample trajectories that simulate motions of a simple home robot, and then render the frames along the trajectories. Each data frame contains a) RGB images generated using physically-based rendering, b) simulated depth measurements, c) simulated IMU readings and d) ground truth occupancy grid of a house. Our dataset serves a wider range of purposes compared to existing datasets and is the first large-scale benchmark focused on the mapping component of SLAM. The dataset is split into train/validation/test parts sampled from different sets of virtual houses. We present benchmarking results for both classical geometry-based [1], [2] and recent learningbased [3] SLAM algorithms, a baseline mapping method [4], semantic segmentation [5] and panoptic segmentation [6]. The dataset and source code for reproducing our experiments will be publicly available at the time of publication.

show abstract