Abstract
Indoor environments have abundant presence of high-level semantic information which can provide a better understanding of the environment for robots to improve the uncertainty in their pose estimate. Although semantic information has proved to be useful, there are several challenges faced by the research community to accurately perceive, extract and utilize such semantic information from the environment. In order to address these challenges, in this paper we present a lightweight and real-time visual semantic SLAM framework running on board aerial robotic platforms. This novel method combines low-level visual/visual-inertial odometry (VO/VIO) along with geometrical information corresponding to planar surfaces extracted from detected semantic objects. Extracting the planar surfaces from selected semantic objects provides enhanced robustness and makes it possible to precisely improve the metric estimates rapidly, simultaneously generalizing to several object instances irrespective of their shape and size. Our graph-based approach can integrate several state of the art VO/VIO algorithms along with the state of the art object detectors in order to estimate the complete 6DoF pose of the robot while simultaneously creating a sparse semantic map of the environment. No prior knowledge of the objects is required, which is a significant advantage over other works. We test our approach on a standard RGB-D dataset comparing its performance with the state of the art SLAM algorithms. We also perform several challenging indoor experiments validating our approach in presence of distinct environmental conditions and furthermore test it on board an aerial robot. Video:https://vimeo.com/368217703Released Code:https://bitbucket.org/hridaybavle/semantic_slam.git.
Highlights
Many indoor autonomous missions related to different applications require the usage of small-size aerial robots, able to navigate around narrow constrained spaces
STANDARD DATASET To validate our approach, we test on standard dataset and compare it with state of the art approaches based on geometric as well as object based Simultaneous Localization and Mapping (SLAM) approaches
1) RGB-D SLAM TUM DATASET This dataset2 ([29]) consists of point cloud data provided from a kinect sensor and a motion capture system for the ground truth data
Summary
Many indoor autonomous missions related to different applications require the usage of small-size aerial robots, able to navigate around narrow constrained spaces. Other state of the art SLAM based techniques, such as [4]–[6], focus on dense 3D mapping of the environment, requiring high end CPU and GPU hardware in order to achieve real-time operation, which is a clear limitation on board an aerial robot with low computational capabilities. Due to the inaccuracies in low-level feature detection and matching, as well as to errors and biases in the IMU measurements (for VIO systems), the VO/VIO estimations of the robot state often accumulate errors over time. We address this by associating the high-level planar surfaces of the detected semantic objects with the previously mapped semantic planes.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
