Be your own Benchmark: No-Reference Trajectory Metric on Registered Point Clouds

Kornilova, Anastasiia; Ferrer, Gonzalo

doi:10.1109/ecmr50962.2021.9568822

Cited by 6 publications

(7 citation statements)

References 28 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore no-reference evaluation is used in this work. In particular, Mean Map Entropy (MME) [38] and Mean Plane Variance (MPV) [39] evaluate noise in the aggregated point cloud and Mutually Orthogonal Metric (MOM) [40] correlates reconstruction noise with perturbation in the 3D poses.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Eigen-Factors a Bilevel Optimization for Back-end Plane SLAM of 3D Point Clouds

Ferrer,

Iarosh,

Kornilova

2024

Preprint

View full text Add to dashboard Cite

Modern depth sensors can generate a huge number of 3D points in few seconds to be later processed by Localization and Mapping algorithms.Ideally, these algorithms should handle efficiently large sizes of Point Clouds (PC) under the assumption that using more points implies more information available.The Eigen Factors (EF) is a new algorithm that solves PC SLAM by using planes as the main geometric primitive. To do so, EF exhaustively calculates the error of all points at complexity {\em O(1)}, thanks to the {\em Summation matrix S} of homogeneous points. The solution of EF is a bilevel optimization where the {\em lower-level} problem estimates the plane variables in closed-form, and the {\em upper-level} non-linear problem uses second order optimization to estimate sensor poses (trajectory).We provide a direct analytical solution for the gradient and Hessian based on the homogeneous point-plane constraint. In addition, two variants of the EF are proposed: one pure analytical derivation and a second one approximating the problem to an alternating optimization showing better convergence properties. We evaluate EF and other state-of-the-art plane SLAM back-end algorithms in a synthetic environment, and extended to ICL dataset (RGBD) and LiDAR KITTI datasets. EF demonstrates superior robustness and accuracy of the estimated trajectory and improved map metrics.Code is publicly available at \texttt{https://github.com/prime-slam/EF-plane-SLAM} with python bindings and pip package.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The development is however taken from the homogeneous formulation presented above, one just needs to adjust to this transformation in the gradient and Hessian calculations. Accordingly, the gradient is calculated as in (29), and almost all components of the Hessian remain the same except for (40) now written as…”

Section: Data Centeringmentioning

confidence: 99%

Eigen-Factors a Bilevel Optimization for Back-end Plane SLAM of 3D Point Clouds

Ferrer,

Iarosh,

Kornilova

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Over the last two decades, robotics community started to work on creating common datasets and benchmarks for comparing different algorithms. Even though there are approaches allowing the localization and mapping quality to be assessed without comparing it to ground truth [5], in general, we still need a ground truth trajectory for comparison. Since such a trajectory is not available in principle, as there is no source of information able to provide the real noise-free path of a robot, researchers try to obtain a ground truth trajectory estimatea reference trajectory suitable to assess the quality of localization algorithms.…”

Section: Related Workmentioning

confidence: 99%

Prior Distribution Refinement for Reference Trajectory Estimation With the Monte Carlo-Based Localization Algorithm

Griguletskii

Shipitko²,

Abramov

et al. 2023

IEEE Access

View full text Add to dashboard Cite

A robot localization problem demands a fair comparison of the positioning algorithms. A reference trajectory of the robot's movement is needed to estimate errors and evaluate a quality of the localization. In this article, we propose the Prior Distribution Refinement method for generating a reference trajectory of a mobile robot with the Monte Carlo-based localization system. The proposed approach can be applied for both indoor and outdoor environments of an arbitrary size without the need for expensive position tracking sensors or intervention in the testing infrastructure. The reference trajectory is generated by running the algorithm over a so-called Particles' Transition Graph, obtained from a resampling stage of Monte Carlo localization. The prior distribution of particles is then refined by forward-backward propagation through the graph and exploring the connections between particles. The Viterbi algorithm is applied afterwards to generate a reference trajectory based on refined particles' distribution. We demonstrate that such an approach is capable of generating accurate estimates of a mobile robot's position and orientation with the only requirement of moderate quality of localization system being used as a core algorithm for iterative optimization.

show abstract

“…Therefore no-reference evaluation is used in this work. In particular, Mean Map Entropy (MME) [37] and Mean Plane Variance (MPV) [38] evaluate noise in the aggregated point cloud and Mutually Orthogonal Metric (MOM) [39] correlates reconstruction noise with perturbation in the 3D poses.…”

Section: Related Workmentioning

confidence: 99%

“…For evaluation we consider 100 submaps of length 30 poses, randomly sampled from map 00. To estimate the quality of alignment, no-reference map metrics MME [37], MPV [38] and MOM [39] are used.…”

Section: Lidarmentioning

confidence: 99%

Eigen-Factors: Plane Estimation for Multi-Frame and Time-Continuous Point Cloud Alignment

Ferrer

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Modern depth sensors can generate a huge number of 3D points in few seconds to be latter processed by Localization and Mapping algorithms. Ideally, these algorithms should handle efficiently large sizes of Point Clouds under the assumption that using more points implies more information available. The Eigen Factors (EF) is a new algorithm that solves SLAM by using planes as the main geometric primitive. To do so, EF exhaustively calculates the error of all points at complexity O(1), thanks to the Summation matrix S of homogeneous points.The solution of EF is highly efficient: i) the state variables are only the sensor poses -trajectory, while the plane parameters are estimated previously in closed from and ii) EF alternating optimization uses a Newton-Raphson method by a direct analytical calculation of the gradient and the Hessian, which turns out to be a block diagonal matrix. Since we require to differentiate over eigenvalues and matrix elements, we have developed an intuitive methodology to calculate partial derivatives in the manifold of rigid body transformations SE(3), which could be applied to unrelated problems that require analytical derivatives of certain complexity.We evaluate EF and other state-of-the-art plane SLAM back-end algorithms in a synthetic environment. The evaluation is extended to ICL dataset (RGBD) and LiDAR KITTI dataset. Code is publicly available at https://github.com/prime-slam/EF-plane-SLAM.

show abstract

Be your own Benchmark: No-Reference Trajectory Metric on Registered Point Clouds

Cited by 6 publications

References 28 publications

Eigen-Factors a Bilevel Optimization for Back-end Plane SLAM of 3D Point Clouds

Eigen-Factors a Bilevel Optimization for Back-end Plane SLAM of 3D Point Clouds

Prior Distribution Refinement for Reference Trajectory Estimation With the Monte Carlo-Based Localization Algorithm

Eigen-Factors: Plane Estimation for Multi-Frame and Time-Continuous Point Cloud Alignment

Contact Info

Product

Resources

About