AirDOS: Dynamic SLAM benefits from Articulated Objects

@inproceedings{Qiu2022AirDOSDS,
  title={AirDOS: Dynamic SLAM benefits from Articulated Objects},
  author={Yuheng Qiu and Chen Wang and Wenshan Wang and Mina Henein and Sebastian A. Scherer},
  booktitle={ICRA},
  year={2022}
}
Dynamic Object-aware SLAM (DOS) exploits object-level information to enable robust motion estimation in dynamic environments. Existing methods mainly focus on identifying and excluding dynamic objects from the optimization. In this paper, we show that feature-based visual SLAM systems can also benefit from the presence of dynamic articulated objects by taking advantage of two observations: (1) The 3D structure of each rigid part of articulated object remains consistent over time; (2) The points… 

Figures and Tables from this paper

BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking
TLDR
It is demonstrated that BodySLAM improves estimates of all human body parameters and camera poses when compared to estimating these separately, and introduces a novel human motion model to constrain sequential body postures.
MLO: Multi-Object Tracking and Lidar Odometry in Dynamic Environment
TLDR
The experiment results show that the ego localization accuracy of MLO is better than A-LOAM system in highly dynamic, unstructured, and unknown semantic scenes and the multi-object tracking method with semantic-geometry fusion also has apparent advantages in accuracy and tracking robustness compared with the single method.

References

SHOWING 1-10 OF 35 REFERENCES
VDO-SLAM: A Visual Dynamic Object-aware SLAM System
TLDR
VDO-SLAM is presented, a robust object-aware dynamic SLAM system that exploits semantic information to enable motion estimation of rigid objects in the scene without any prior knowledge of the objects shape or motion models resulting in accurate robot pose and spatio-temporal map estimation.
Dynamic SLAM: The Need For Speed
TLDR
This paper proposes a new feature-based, model-free, object-aware dynamic SLAM algorithm that exploits semantic segmentation to allow estimation of motion of rigid objects in a scene without the need to estimate the object poses or have any prior knowledge of their 3D models.
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects
TLDR
The object graph enables predictions for accurate ICP-based camera to model tracking at each live frame, and efficient active search for new objects in currently undescribed image regions, as well as the generation of an object level scene description with the potential to enable interaction.
DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes
TLDR
DynaSLAM is a visual SLAM system that, building on ORB-SLAM2, adds the capabilities of dynamic object detection and background inpainting, and outperforms the accuracy of standard visualSLAM baselines in highly dynamic scenarios.
Robust Dense Mapping for Large-Scale Dynamic Environments
TLDR
A stereo-based dense mapping algorithm for large-scale dynamic urban environments that simultaneously reconstruct the static background, the moving objects, and the potentially moving but currently stationary objects separately, which is desirable for high-level mobile robotic tasks such as path planning in crowded environments.
CubeSLAM: Monocular 3-D Object SLAM
TLDR
The SLAM method achieves the state-of-the-art monocular camera pose estimation and at the same time, improves the 3-D object detection accuracy.
Simultaneous Localization, Mapping and Moving Object Tracking
TLDR
Based on the SLAM with DATMO framework, practical algorithms are proposed which deal with issues of perception modeling, data association, and moving object detection.
Exploiting Rigid Body Motion for SLAM in Dynamic Environments
TLDR
This paper proposes a technique to integrate the motion of dynamic objects into a Simultaneous Localisation and Mapping (SLAM) algorithm without the need to know a-priori or model the geometry of the object, or even to explicitly estimate the pose of theobject.
Multimotion Visual Odometry (MVO): Simultaneous Estimation of Camera and Third-Party Motions
TLDR
The traditional visual odometry pipeline is extended to estimate the full motion of both a stereo/RGB-D camera and the dynamic scene, and its performance is evaluated on a real-world dynamic dataset with ground truth for all motions from a motion capture system.
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
TLDR
A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation.
...
...