Odometer track alignment and precision evaluation method
An odometer and trajectory technology, applied in the field of intelligent robots, can solve the problems affecting the accuracy of odometer evaluation results, and achieve the effect of reasonable evaluation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0087] The real value of the trajectory (Groundtruth) is obtained by the motion capture system (Optitrack), and the trajectory is as follows image 3 (a) and image 3 It is shown by the solid line in (b).
[0088] The estimated trajectory (Estimate) is obtained by the visual inertial odometry, and the trajectory is as follows image 3 (a) and image 3 It is shown by the dotted line in (b).
[0089] Use Umeyama and the method of the present invention to align the estimated trajectory with the real trajectory, and measure the absolute error of the odometer.
[0090] image 3 (a) is a comparison chart between the estimated trajectory aligned with the Umeyama algorithm and the true value, the average absolute error is about 0.797m, image 3 (b) is a comparison chart of the estimated trajectory aligned with the method of the present invention and the true value, and the average absolute error is about 0.883m.
[0091] From image 3 (a) and image 3 From the comparison of (b...
Embodiment 2
[0093] The true value of the trajectory (Groundtruth) is obtained by a high-precision visual-inertial odometry, and the estimated value of the odometry is obtained by using two other different visual odometry calculation methods. The trajectory measurement results are divided into Trajectory1 and Trajectory2, corresponding to image 3 (c) and image 3 Dotted line (..) and dotted line (-.) in (d).
[0094] Umeyama and the method of the present invention are respectively used to align the two groups of trajectories, and calculate the average absolute error of the odometer. The results are shown in the table below:
[0095] Table 1 Absolute error mean value table (unit: m)
[0096]
[0097] When performing multiple trajectories for simultaneous evaluation, use the Umeyama alignment method to align the trajectories, such as image 3 As shown in (c), it is difficult to intuitively see the cumulative error and performance of the two odometers. Use the method of the present in...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More - R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com



