A Hierarchical Framework for Collaborative Probabilistic Semantic Mapping

Yue, Yufeng; Zhao, Chunyang; Li, Ruilin; Yang, Chule; Zhang, Jun; Wen, Mingxing; Wang, Yuanzhe; Wang, Danwei

doi:10.1109/icra40945.2020.9197261

Cited by 31 publications

(23 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, such a particular implementation of the spatial database prevents any other semantic mapping algorithm, that does not feature a copy of such database, to be fairly compared. With a different algorithm, but with a similar results in terms of comparison with other approaches, the work in [26] introduces a hierarchical collaborative probabilistic semantic mapping algorithm that stores information by exploiting a voxel map, where each voxel also features a semantic label (e.g. floor, furniture).…”

Section: Semantic Maps Evaluationmentioning

confidence: 99%

“…In fact, if we consider [5], it is already very difficult to compare the two approaches. Akin [26], also the authors in [3,18] adopt a hierarchical formalization of semantic knowledge. However, the layers of the hierarchies represent different levels of abstraction that intersect but not overlap -including different semantic entities.…”

Section: Semantic Maps Evaluationmentioning

confidence: 99%

“…However, the layers of the hierarchies represent different levels of abstraction that intersect but not overlap -including different semantic entities. For example in [3], the authors insert above the sensory layer an intermediate place layer that keeps record of local nodes to support a topological representation of the environment, which is not present in [26], that directly connects the sensory layer to a segmented representation of semantic objects. Also in these different setups, even though the goal is always to locate and label 3D objects, it becomes nearly impossible to assess the advantages and disadvantages of various semantic knowledge representations when brought into comparison.…”

Section: Semantic Maps Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

RoSmEEry: Robotic Simulated Environment for Evaluation and Benchmarking of Semantic Mapping Algorithms

Kaszuba,

Sabbella,

Suriani

et al. 2021

Preprint

View full text Add to dashboard Cite

Human-robot interaction requires a common understanding of the operational environment, which can be provided by a representation that blends geometric and symbolic knowledge: a semantic map. Through a semantic map the robot can interpret user commands by grounding them to its sensory observations. Semantic mapping is the process that builds such a representation. Despite being fundamental to enable cognition and high-level reasoning in robotics, semantic mapping is a challenging task due to generalization to different scenarios and sensory data types. In fact, it is difficult to obtain a rich and accurate semantic map of the environment and of the objects therein. Moreover, to date, there are no frameworks that allow for a comparison of the performance in building semantic maps for a given environment. To tackle these issues we design RoSmEEry, a novel framework based on the Gazebo simulator, where we introduce an accessible and ready-to-use methodology for a systematic evaluation of semantic mapping algorithms. We release our framework, as an open-source package, with multiple simulation environments with the aim to provide a general set-up to quantitatively measure the performances in acquiring semantic knowledge about the environment.

show abstract

Section: Semantic Maps Evaluationmentioning

confidence: 99%

Section: Semantic Maps Evaluationmentioning

confidence: 99%

Section: Semantic Maps Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

RoSmEEry: Robotic Simulated Environment for Evaluation and Benchmarking of Semantic Mapping Algorithms

Kaszuba,

Sabbella,

Suriani

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other works differ in the deep neural network used (e.g., recurrent neural networks on consecutive frames [60], [9], 3D CNN for point clouds [16]), the map representation employed (point-cloud maps [52], [9] and voxel-based maps [60], [63], [33]), or the type of semantics (instance-level [19], object-level [52], [66], [45], [68] and place-level [51]). More recently, distributed semantic mapping for multi-robots [65], [26] and 3D scene graphs [44] are also trending research topics.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference

Unnikrishnan¹,

Wilson²,

Gan³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model. Existence of dynamic objects in the environment cause artifacts and traces in current mapping algorithms, leading to an inconsistent map posterior. We leverage state-of-the-art semantic segmentation and 3D flow estimation using deep learning to provide measurements for map inference. We develop a continuous (i.e., can be queried at arbitrary resolution) Bayesian model that propagates the scene with flow and infers a 3D semantic occupancy map with better performance than its static counterpart. Experimental results using publicly available data sets show that the proposed framework generalizes its predecessors and improves over direct measurements from deep neural networks consistently.

show abstract

“…LeGO-LOAM [17] separates ground points from the point cloud used in planar features extraction and first step pose optimization. [18] presents a hierarchical semantic mapping framework for collaborative robots or simple robots. SuMa++ [2] exploits semantics to filter dynamic objects in a surfel level and perform a semantic ICP.…”

Section: Introductionmentioning

confidence: 99%

PSF-LO: Parameterized Semantic Features Based Lidar Odometry

Chen

Wang

et al. 2021

2021 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving. The state-of-the-art LO methods generally leverage geometric information to perform point cloud registration. Furthermore, obtaining the point cloud semantic information describing the environment more abundantly will facilitate the registration. We present a novel semantic lidar odometry method based on self-designed parameterized semantic features (PSFs) to achieve low-drift ego-motion estimation for autonomous vehicle in real time. We first use a convolutional neural network-based algorithm to obtain point-wise semantics from the input laser point cloud, and then use semantic labels to separate road, building, traffic sign and pole-like point cloud and fit them separately to obtain corresponding PSFs. A fast PSF-based matching enables us to refine geometric features (GeFs) registration, thereby reducing the impact of blurred submap surface on the accuracy of GeFs matching. Besides, we design an efficient instance-level method to accurately recognize and remove the dynamic objects while retaining static ones in the semantic point cloud, which are beneficial to further improve the accuracy of LO. We evaluate our method, namely PSF-LO, on the public dataset KITTI Odometry Benchmark and rank #1 among semantic lidar methods with an average translational error of 0.82% in the test dataset.

show abstract

A Hierarchical Framework for Collaborative Probabilistic Semantic Mapping

Cited by 31 publications

References 26 publications

RoSmEEry: Robotic Simulated Environment for Evaluation and Benchmarking of Semantic Mapping Algorithms

RoSmEEry: Robotic Simulated Environment for Evaluation and Benchmarking of Semantic Mapping Algorithms

Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference

PSF-LO: Parameterized Semantic Features Based Lidar Odometry

Contact Info

Product

Resources

About