Tomas Petricek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tomas Petricek has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Karel Zimmermann
Czech Technical University in Prague
4 shared publications - Tomas Svoboda
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic
4 shared publications - Ruslan Agishev
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic
2 shared publications - Vojtech Salansky
Faculty of Electrical Engineering, Czech Technical University
2 shared publications - Daniel Hert
Faculty of Electrical Engineer- ing Czech Technical University in Prague Technicka 2 Prague Czech Republic
1 shared publication - Dominic Baril
Universit Laval, Canada
1 shared publication
Latest Publications
- 20 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (8) , 4681-4688
Self-Supervised Depth Correction of Lidar Measurements From Map Consistency Loss
Depth perception is considered an invaluable source of information in the context of 3D mapping and various robotics applications. However, point cloud maps acquired using consumer-level light detection and ranging sensors (lidars) still suffer from bias related to local surface properties such as measuring beam-to-surface incidence angle. This fact has recently motivated researchers to exploit traditional filters, as well as the deep learning paradigm, in order to suppress the aforementioned depth sensors error while preserving geometric and map consistency details. Despite the effort, depth correction of lidar measurements is still an open challenge mainly due to the lack of clean 3D data that could be used as ground truth. In this letter, we introduce two novel point cloud map consistency losses, which facilitate self-supervised learning on real data of lidar depth correction models. Specifically, the models exploit multiple point cloud measurements of the same scene from different view-points in order to learn to reduce the bias based on the constructed map consistency signal. Complementary to the removal of the bias from the measurements, we demonstrate that the depth correction models help to reduce localization drift.
- 20 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (8) , 4681-4688
Self-Supervised Depth Correction of Lidar Measurements From Map Consistency Loss
Depth perception is considered an invaluable source of information in the context of 3D mapping and various robotics applications. However, point cloud maps acquired using consumer-level light detection and ranging sensors (lidars) still suffer from bias related to local surface properties such as measuring beam-to-surface incidence angle. This fact has recently motivated researchers to exploit traditional filters, as well as the deep learning paradigm, in order to suppress the aforementioned depth sensors error while preserving geometric and map consistency details. Despite the effort, depth correction of lidar measurements is still an open challenge mainly due to the lack of clean 3D data that could be used as ground truth. In this letter, we introduce two novel point cloud map consistency losses, which facilitate self-supervised learning on real data of lidar depth correction models. Specifically, the models exploit multiple point cloud measurements of the same scene from different view-points in order to learn to reduce the bias based on the constructed map consistency signal. Complementary to the removal of the bias from the measurements, we demonstrate that the depth correction models help to reduce localization drift.
- Open Access
- 1 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Field Robotics
- Vol. 2, 1779-1818
System for Multi-Robotic Exploration of Underground Environments CTU-CRAS-NORLAB in the DARPA Subterranean Challenge
- 1 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Field Robotics
- Vol. 2, 1779-1818
Open AccessSystem for Multi-Robotic Exploration of Underground Environments CTU-CRAS-NORLAB in the DARPA Subterranean Challenge
- 1 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 3365-3371
Trajectory Optimization Using Learned Robot-Terrain Interaction Model in Exploration of Large Subterranean Environments
We consider the task of active exploration of large subterranean environments with a ground mobile robot. Our goal is to autonomously explore a large unknown area and to obtain an accurate coverage and localization of objects of interest (artifacts). The exploration is constrained by the restricted operation time in rescue scenarios, as well as a hard rough terrain. To this end, we introduce a novel optimization strategy that respects these constraints by maximizing the environment coverage by onboard sensors while producing feasible trajectories with the help of a learned robot-terrain interaction model. The approach is evaluated in diverse subterranean simulated environments, showing the viability of traversability-aware exploration in challenging scenarios. In addition, we demonstrate that the local trajectory optimization improves global coverage of an environment as well as the overall object detection results.
- 1 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 3365-3371
Trajectory Optimization Using Learned Robot-Terrain Interaction Model in Exploration of Large Subterranean Environments
We consider the task of active exploration of large subterranean environments with a ground mobile robot. Our goal is to autonomously explore a large unknown area and to obtain an accurate coverage and localization of objects of interest (artifacts). The exploration is constrained by the restricted operation time in rescue scenarios, as well as a hard rough terrain. To this end, we introduce a novel optimization strategy that respects these constraints by maximizing the environment coverage by onboard sensors while producing feasible trajectories with the help of a learned robot-terrain interaction model. The approach is evaluated in diverse subterranean simulated environments, showing the viability of traversability-aware exploration in challenging scenarios. In addition, we demonstrate that the local trajectory optimization improves global coverage of an environment as well as the overall object detection results.
- Open Access
- 30 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (3) , 5477-5484
Pose Consistency KKT-Loss for Weakly Supervised Learning of Robot-Terrain Interaction Model
We address the problem of self-supervised learning for predicting the shape of supporting terrain (i.e. the terrain which will provide rigid support for the robot during its traversal) from sparse input measurements. The learning method exploits two types of ground-truth labels: dense 2.5D maps and robot poses, both estimated by a usual SLAM procedure from offline recorded measurements. We show that robot poses are required because straightforward supervised learning from the 3D maps only suffers from: (i) exaggerated height of the supporting terrain caused by terrain flexibility (vegetation, shallow water, snow or sand) and (ii) missing or noisy measurements caused by high spectral absorbance or non-Lambertian reflectance of the measured surface. We address the learning from robot poses by introducing a novel KKT-loss, which emerges as the distance from necessary Karush-Kuhn-Tucker conditions for constrained local optima of a simplified first-principle model of the robot-terrain interaction. We experimentally verify that the proposed weakly supervised learning from ground-truth robot poses boosts the accuracy of predicted support heightmaps and increases the accuracy of estimated robot poses. All experiments are conducted on a dataset captured by a real platform. Both the dataset and codes which replicates experiments in the paper are made publicly available as a part of the submission.
- 30 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (3) , 5477-5484
Open AccessPose Consistency KKT-Loss for Weakly Supervised Learning of Robot-Terrain Interaction Model
We address the problem of self-supervised learning for predicting the shape of supporting terrain (i.e. the terrain which will provide rigid support for the robot during its traversal) from sparse input measurements. The learning method exploits two types of ground-truth labels: dense 2.5D maps and robot poses, both estimated by a usual SLAM procedure from offline recorded measurements. We show that robot poses are required because straightforward supervised learning from the 3D maps only suffers from: (i) exaggerated height of the supporting terrain caused by terrain flexibility (vegetation, shallow water, snow or sand) and (ii) missing or noisy measurements caused by high spectral absorbance or non-Lambertian reflectance of the measured surface. We address the learning from robot poses by introducing a novel KKT-loss, which emerges as the distance from necessary Karush-Kuhn-Tucker conditions for constrained local optima of a simplified first-principle model of the robot-terrain interaction. We experimentally verify that the proposed weakly supervised learning from ground-truth robot poses boosts the accuracy of predicted support heightmaps and increases the accuracy of estimated robot poses. All experiments are conducted on a dataset captured by a real platform. Both the dataset and codes which replicates experiments in the paper are made publicly available as a part of the submission.
- 3 December 2018
- Published by Wiley in Journal of Field Robotics
- Vol. 36 (4) , 696-709
Simultaneous exploration and segmentation for search and rescue
- 3 December 2018
- Published by Wiley in Journal of Field Robotics
- Vol. 36 (4) , 696-709
Simultaneous exploration and segmentation for search and rescue
- Open Access
- 14 November 2017
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 12 (11) , e0187943
Point cloud registration from local feature correspondences—Evaluation on challenging datasets
Registration of laser scans, or point clouds in general, is a crucial step of localization and mapping with mobile robots or in object modeling pipelines. A coarse alignment of the point clouds is generally needed before applying local methods such as the Iterative Closest Point (ICP) algorithm. We propose a feature-based approach to point cloud registration and evaluate the proposed method and its individual components on challenging real-world datasets. For a moderate overlap between the laser scans, the method provides a superior registration accuracy compared to state-of-the-art methods including Generalized ICP, 3D Normal-Distribution Transform, Fast Point-Feature Histograms, and 4-Points Congruent Sets. Compared to the surface normals, the points as the underlying features yield higher performance in both keypoint detection and establishing local reference frames. Moreover, sign disambiguation of the basis vectors proves to be an important aspect in creating repeatable local reference frames. A novel method for sign disambiguation is proposed which yields highly repeatable reference frames.
- 14 November 2017
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 12 (11) , e0187943
Open AccessPoint cloud registration from local feature correspondences—Evaluation on challenging datasets
Registration of laser scans, or point clouds in general, is a crucial step of localization and mapping with mobile robots or in object modeling pipelines. A coarse alignment of the point clouds is generally needed before applying local methods such as the Iterative Closest Point (ICP) algorithm. We propose a feature-based approach to point cloud registration and evaluate the proposed method and its individual components on challenging real-world datasets. For a moderate overlap between the laser scans, the method provides a superior registration accuracy compared to state-of-the-art methods including Generalized ICP, 3D Normal-Distribution Transform, Fast Point-Feature Histograms, and 4-Points Congruent Sets. Compared to the surface normals, the points as the underlying features yield higher performance in both keypoint detection and establishing local reference frames. Moreover, sign disambiguation of the basis vectors proves to be an important aspect in creating repeatable local reference frames. A novel method for sign disambiguation is proposed which yields highly repeatable reference frames.