Given sequential point clouds of input frames, DELO applies DGCNN
as backbone encoder to obtain a point-wise feature embedding \(\phi_{\mathcal{Y}}\) and \(\phi_{\mathcal{X}}\). Then it simultaneously aligns the frames using the Partial Optimal
Transport plan for LiDAR Descriptor Matching (POT-LDM), and estimates the Predictive Uncertainty for the Evidential Pose Estimation
(PU-EPE). With the help of PU estimates pose-graphs are refined. (b) This part depicts a sub-map between frame 1 to 300 of KITTI test
sequence-10 with all outputs from DELO.
A neural network for frame-to-frame LiDAR odometry (LO) estimation using Partial Optimal Trasport.
A network component that joitly learns predictive uncertainty (PU) for Evidential Pose Estimation (EPE).
Learned PU helps in classifying under-confident, confident, and over-confident odometry estimation.
The uncertainty quantification (UQ) over the predicted transformations helps in setting boundary conditions for any
downstream pose-based decision making tasks.
Network Architecture
Deep Evidential LiDAR Odometry estimation network is comprised of three components:
Local sharp matching through differentiable partial optimal transport module reduces the matching cost between
the attention maps \(\Phi_{\mathcal{X}}\) and \(\Phi_{\mathcal{Y}}\).
The POT-LDM network component can inherently learn the data
uncertainty (i.e., aleatoric uncertainty), but it cannot automat-
ically learn the model's predictive uncertainty (i.e., epis-
temic uncertainty) [21].
The PU-EPE network component is trained jointly with the POT-LDM
to estimate the model's confidence in the LiDAR odometry predic-
tions at different frames, i.e., \(\mathbf{T}_f , \mathbf{T}_{f+o},
\mathbf{T}_{f+2o}, ..,\) when the frame-gap is \(o\).
The odometry predictions from POT-LDM \([.., \mathbf{T}_f , \mathbf{T}_{f+o}, \mathbf{T}_{f+2o}, . . .]\)
from POT-LDM and the epistemic uncertainty measures\([.., Var [\mu]_{f} , ..]\) from PU-EPE for all frames \(f\) in a
given sub-sequence \(\mathcal{S}\) are all streamed in for pose-graph optimization. We employ
GTSAM
for pose-graph optimization by matching the LO inference with LiDAR sensor rate.
Qualitative Analysis
Quantitative Analysis
Results of different approaches for LiDAR odomety on KITTI
[18] dataset are
quantified by RRE, RTE metrics. The sequences \(07-10\) that are used for
testing or inference, are not seen during training the network of
the supervised approaches [
24,
41,
42,
2
] and ours. Black/Gray:
The best and second best entries are underlined and marked in bold black and
gray colors
+: Denotes the error metrics are reported from from PWCLONet [41]
PWCLO\(^{x}\): The superscript \(x\) means \(x * 1024\) number of
input points are used for PWCLONet [41].
Video
Coming Soon!
Acknowledgement
This work was partially funded by the project DECODE (01IW21001) of the German Federal Ministry of Education and Research (BMBF)
and by the Luxembourg National Research Fund (FNR) under the project reference C21/IS/15965298/ELITE/Aouada.
Citation
If you refer to the results or codes of this work, please cite the following:
@inproceedings{ali2023delo,
title={DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport},
author={Ali, Sk Aziz and Aouada, Djamila and Reis, Gerd and Stricker, Didier},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={4517--4526},
year={2023}
}
@inproceedings{ali2021RPSRNet,
author={Ali, Sk Aziz and Kahraman, Kerem and Reis, Gerd and Stricker, Didier},
booktitle={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
title={RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation},
year={2021},
doi={10.1109/CVPR46437.2021.01290}
}