Mobile Robot Algorithms Laboratory
SLAM Constructor for ROS
Project domain
Simultaneous Localization and Mapping (SLAM) methods are essential for mobile robots which are supposed to act in an unknown environment. Despite various algorithms have already been proposed, an algorithm that would robustly solve the problem in the general case and satisfy performance constraints is still a subject of research. Unfortunately, there is no publicly available framework that would provide a common set of components needed to speed up SLAM research (frameworks and toolkits that simplify the development of particular SLAM parts are not taken into account).
Project goals
- Creation of a framework that acts as a constructor of SLAM algorithms (researchers are supposed to connect available components by themselves and add necessary modifications).
- Implementation of a full set of basic components that can be assembled into the most common (fundamental) SLAM algorithms.
- Creation of the infrastructure and tools for debugging and analysis of SLAM algorithms.
- Creation of service for managing SLAM datasets (convertion, storage, provision and so on).
Environment
All software we develop is supposed to be executed on Linux and in Robot Operating System environment. We performed preliminary research on a wide spectrum of existing tools and environments like MTK, MRPT and others, which showed that ROS was the most promising choice.
Roadmap
- Support for components for graph-based SLAM methods.
- Implementation of additional scan matchers for Laser-based SLAMs.
- Support for an extended set of sensors and measurements (3D scans, monocular/stereo cameras).
- Implementation of vergent stereo vision.
- A service for SLAM datasets.
- ROS SLAM Testing Farm: a virtualized, container-based environment for semi-autonomous testing of SLAM algorithms.
Participants
Publications
Multi-Agent SLAM Approaches for Low-Cost Platforms
April 2019
Anton Filatov, Krinkin Kirill
Modern SLAM (Simultaneous Localization and Mapping) algorithms launched on a moving agent are bounded with its computation resources. The consistent way out is to add more computing agents that might explore the environment quicker than one and thus to decrease the load of each agent. This paper presents the state of art in area of Multi-agent SLAM algorithms and describes problems that are faced in front of a developer of such approach. The outstanding problem of Multiagent SLAM - merging of maps built by separate agent during algorithm is also considered in this paper. Moreover the algorithm that extends laser 2D single hypothesis SLAM for multiple agents is introduced with evaluation of its performance.
Mobile Robot Pose Estimation Based on Position/Velocity Sensor Fusion
April 2019
Kirill Krinkin, Artyom Filatov
An autonomous self driving platform receives information about environment using only its onboard sensors. And it seems obvious that using several sensors could provide more certain information with reduced measurement error. But a general question is how to fuse measurements from different kinds of sensors (like a camera and an accelerometer) to get refined data about a platform or world state. This paper presents a theory based on groups that proves a possibility of correctness of error extraction from a moving model. And there are results of application this theory on fusing measurements from two sensors: odometer and scan matcher
Методы сравнения качества 2D-SLAM-алгоритмов
2018
Ар. Ю. Филатов, Ан. Ю. Филатов, К. В. Кринкин, Б. Чен, Д. Молодан
Generator of 2D laser scan based datasets for ROS
2018
Arthur Huletski, Dmitriy Kartashov and Kirill Krinkin
Сравнение современных лазерных алгоритмов SLAM
2018
Ар. Ю. Филатов, Ан. Ю. Филатов, А. Т. Гулецкий, Д. А. Карташов, К. В. Кринкин
VinySLAM: An indoor SLAM method for low-cost platforms based on the Transferable Belief Model
September 2017
Arthur Huletski; Dmitriy Kartashov; Kirill Krinkin
2D SLAM Quality Evaluation Methods
August 2017
An. Filatov, Ar. Filatov, K. Krinkin, B. Chen, D. Molodan