Tag-based visual-inertial localization of unmanned aerial vehicles in indoor construction environments using an on-manifold extended Kalman filter

Kayhani, Navid; Zhao, Wenda; McCabe, Brenda; Schoellig, Angela P.

doi:10.1016/j.autcon.2021.104112

Cited by 31 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When N e f f < N f f , the particles are resampled by KLD algorithm [30], and the updated particles are introduced into (2) prediction stage for cyclic calculation. Accordingly, the longer the robot platform moves in the map, the more the sensor positioning information is obtained, the more accurate the positioning is.…”

Section: (4) Resamplingmentioning

confidence: 99%

Integrated Indoor Positioning System of Greenhouse Robot Based on UWB/IMU/ODOM/LIDAR

Long

Xiang

Lei

et al. 2022

Sensors

View full text Add to dashboard Cite

Conventional mobile robots employ LIDAR for indoor global positioning and navigation, thus having strict requirements for the ground environment. Under the complicated ground conditions in the greenhouse, the accumulative error of odometer (ODOM) that arises from wheel slip is easy to occur during the long-time operation of the robot, which decreases the accuracy of robot positioning and mapping. To solve the above problem, an integrated positioning system based on UWB (ultra-wideband)/IMU (inertial measurement unit)/ODOM/LIDAR is proposed. First, UWB/IMU/ODOM is integrated by the Extended Kalman Filter (EKF) algorithm to obtain the estimated positioning information. Second, LIDAR is integrated with the established two-dimensional (2D) map by the Adaptive Monte Carlo Localization (AMCL) algorithm to achieve the global positioning of the robot. As indicated by the experiments, the integrated positioning system based on UWB/IMU/ODOM/LIDAR effectively reduced the positioning accumulative error of the robot in the greenhouse environment. At the three moving speeds, including 0.3 m/s, 0.5 m/s, and 0.7 m/s, the maximum lateral error is lower than 0.1 m, and the maximum lateral root mean square error (RMSE) reaches 0.04 m. For global positioning, the RMSEs of the x-axis direction, the y-axis direction, and the overall positioning are estimated as 0.092, 0.069, and 0.079 m, respectively, and the average positioning time of the system is obtained as 72.1 ms. This was sufficient for robot operation in greenhouse situations that need precise positioning and navigation.

show abstract

Section: (4) Resamplingmentioning

confidence: 99%

Integrated Indoor Positioning System of Greenhouse Robot Based on UWB/IMU/ODOM/LIDAR

Long

Xiang

Lei

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Moreover, there exists a multipath effect for the wireless communication signals. The visual location mainly includes SLAM (simultaneous location and mapping) [ 10 ] and location by visual tags [ 11 ]. SLAM can be applied to unknown environments by extracting and matching the texture feature automatically, but the algorithm has a higher computation complexity and its performance is also easily degraded by environmental disturbances.…”

Section: Introductionmentioning

confidence: 99%

“…For the same type of object, however, their texture features are similar, which makes it difficult to discriminate different tags. To manage this problem, special tags are designed by coding the information of ID, coordinate, etc., in the tag to ensure its uniqueness [ 11 ]. On the contrary, the complexity of a QR code requires more time for detection, which even reaches hundreds of milliseconds [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Indoor Location Technology with High Accuracy Using Simple Visual Tags

Gao

2023

Sensors

View full text Add to dashboard Cite

To achieve low-cost and robustness, an indoor location system using simple visual tags is designed by comprehensively considering accuracy and computation complexity. Only the color and shape features are used for tag detection, by which both algorithm complexity and data storage requirement are reduced. To manage the nonunique problem caused by the simple tag features, a fast query and matching method is further presented by using the view field of the camera and the tag azimuth. Then, based on the relationship analysis between the spatial distribution of tags and location error, a pose and position estimation method using the weighted least square algorithm is designed and works together with the interactive algorithm by the designed switching strategy. By using the techniques presented, a favorable balance is achieved between the algorithm complexity and the location accuracy. The simulation and experiment results show that the proposed method can manage the singular problem of the overdetermined equations effectively and attenuate the negative effect of unfavorable label groups. Compared with the ultrawide band technology, the location error is reduced by more than 62%.

show abstract

“…With the development of sensor technologies, indoor localization can be achieved by deploying AprilTag [4], ultrawideband [5] or other signal emitters in buildings. Such methods rely on the distribution of sensors and inherently lack flexibility within large built-up environments.…”

Section: Introductionmentioning

confidence: 99%

Semantic localization on BIM-generated maps using a 3D LiDAR sensor

Yin¹,

Lin²,

Yeoh³

2022

Preprint

View full text Add to dashboard Cite

Conventional sensor-based localization relies on high-precision maps. These maps are generally built using specialized mapping techniques, which involve high labor and computational costs. While in the architectural, engineering and construction industry, building information models (BIMs) are available and can provide informative descriptions of environments. This paper explores an effective way to localize a mobile 3D LiDAR sensor in BIM considering both geometric and semantic properties. Specifically, we first convert original BIM to semantic maps using categories and locations of BIM elements. After that, a coarse-to-fine semantic localization is performed to align laser points to the map via iterative closest point registration. The experimental results show that the semantic localization can track the pose with only scan matching and present centimeter-level errors over 340 meters traveling, thus demonstrating the feasibility of the proposed mapping-free localization framework. The results also show that using semantic information can help reduce localization errors in BIM.

show abstract

Tag-based visual-inertial localization of unmanned aerial vehicles in indoor construction environments using an on-manifold extended Kalman filter

Cited by 31 publications

References 41 publications

Integrated Indoor Positioning System of Greenhouse Robot Based on UWB/IMU/ODOM/LIDAR

Integrated Indoor Positioning System of Greenhouse Robot Based on UWB/IMU/ODOM/LIDAR

Indoor Location Technology with High Accuracy Using Simple Visual Tags

Semantic localization on BIM-generated maps using a 3D LiDAR sensor

Contact Info

Product

Resources

About