Krzysztof Ćwian

Mr. Krzysztof Ćwian

Poznan University of Technology
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 May 2021 in Sensors
Verified
Journal Article
Open access
PDF file
KĆKrzysztof Ćwian
Krzysztof Ćwian
MNMichał Nowicki
Michał Nowicki
JWJan Wietrzykowski
Jan Wietrzykowski
PSPiotr Skrzypczyński
Piotr Skrzypczyński
Although visual SLAM (simultaneous localization and mapping) methods obtain very accurate results using optimization of residual errors defined with respect to the matching features, the SLAM systems based on 3-D laser (LiDAR) data commonly employ variants of the iterative closest points algorithm and raw point clouds as the map representation. However, it is possible to extract from point clouds features that are more spatially extended and more meaningful than points: line segments and/or planar patches. In particular, such features provide a natural way to represent human-made environments, such as urban and mixed indoor/outdoor scenes. In this paper, we perform an analysis of the advantages of a LiDAR-based SLAM that employs high-level geometric features in large-scale urban environments. We present a new approach to the LiDAR SLAM that uses planar patches and line segments for map representation and employs factor graph optimization typical to state-of-the-art visual SLAM for the final map and trajectory optimization. The new map structure and matching of features make it possible to implement in our system an efficient loop closure method, which exploits learned descriptors for place recognition and factor graph for optimization. With these improvements, the overall software structure is based on the proven LOAM concept to ensure real-time operation. A series of experiments were performed to compare the proposed solution to the open-source LOAM, considering different approaches to loop closure computation. The results are compared using standard metrics of trajectory accuracy, focusing on the final quality of the estimated trajectory and the consistency of the environment map. With some well-discussed reservations, our results demonstrate the gains due to using the high-level features in the full-optimization approach in the large-scale LiDAR SLAM.

11 March 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MNMateusz Nijak
Mateusz Nijak
PSPiotr Skrzypczyński
Piotr Skrzypczyński
KĆKrzysztof Ćwian
Krzysztof Ćwian
MZMichał Zawada
Michał Zawada
SSSebastian Szymczyk
Sebastian Szymczyk
JWJacek Wojciechowski
Jacek Wojciechowski
The precision of agro-technical operations is one of the main hallmarks of a modern approach to agriculture. However, ensuring the precise application of plant protection products or the performance of mechanical field operations entails significant costs for sophisticated positioning systems. This paper explores the integration of precision positioning based on the global navigation satellite system (GNSS) in agriculture, particularly in fieldwork operations, seeking solutions of moderate cost with sufficient precision. This study examines the impact of GNSSs on automation and robotisation in agriculture, with a focus on intelligent agricultural guidance. It also discusses commercial devices that enable the automatic guidance of self-propelled machinery and the benefits that they provide. This paper investigates GNSS-based precision localisation devices under real field conditions. A comparison of commercial and low-cost GNSS solutions, along with the integration of satellite navigation with advanced visual odometry for improved positioning accuracy, is presented. The research demonstrates that affordable solutions based on the common differential GNSS infrastructure can be applied for accurate localisation under real field conditions. It also underscores the potential of GNSS-based automation and robotisation in transforming agriculture into a more efficient and sustainable industry.

1 June 2019
Verified
Conference Paper
Closed access
TNTomasz Nowak
Tomasz Nowak
MNMichał Nowicki
Michał Nowicki
KĆKrzysztof Ćwian
Krzysztof Ćwian
PSPiotr Skrzypczyński
Piotr Skrzypczyński
Reliable perception and detection of objects are one of the fundamental aspects of vehicle autonomy. Although model-based approaches perform well in the area of planning and control, they often fail when applied to perception due to the open-world nature of problems for autonomous vehicles. Therefore, data-driven approaches to object detection and location are likely to be used in both self-driving cars and advanced driver assistance systems. In particular, the deep neural networks proved to be excellent in detection and classification of objects from images, often achieving super-human performance. However, neural networks applied in intelligent vehicles need to be explainable, providing rationales for their decisions. In this paper, we demonstrate how such an interpretation can be provided for a deep learning system that detects specific objects (charging posts) for driver assistance in an electric bus. The interpretation, achieved by visualization of attention heat maps, has twofold use: it allows us to augment the dataset used for training, improving the results, but it also may be used as a tool when fielding the system with the given bus operator. Explaining which parts of the images triggered the decision helps to eliminate misdetections.

1 October 2021 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
PKPiotr Kicki
Piotr Kicki
TGTomasz Gawron
Tomasz Gawron
KĆKrzysztof Ćwian
Krzysztof Ćwian
MOMete Ozay
Mete Ozay
PSPiotr Skrzypczyński
Piotr Skrzypczyński

13 October 2021 in Sensors
Verified
Journal Article
Open access
PDF file
TNTomasz Nowak
Tomasz Nowak
KĆKrzysztof Ćwian
Krzysztof Ćwian
PSPiotr Skrzypczyński
Piotr Skrzypczyński
This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system.

5 June 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
IEIman Esfandiyar
Iman Esfandiyar
KĆKrzysztof Ćwian
Krzysztof Ćwian
MNMichał Nowicki
Michał Nowicki
PSPiotr Skrzypczyński
Piotr Skrzypczyński
Modern public transportation in urban areas increasingly relies on high-capacity buses. At the same time, the share of electric vehicles is increasing to meet environmental standards. This introduces problems when charging these vehicles from chargers at bus stops, as untrained drivers often find it difficult to execute docking manoeuvres on the charger. A practical solution to this problem requires a suitable advanced driver-assistance system (ADAS), which is a system used to automatise and make safer some of the tasks involved in driving a vehicle. In the considered case, ADAS supports docking to the electric charging station, and thus, it must solve two issues: precise positioning of the bus relative to the charger and motion planning in a constrained space. This paper addresses these issues by employing GNSS-based positioning and optimisation-based planning, resulting in an affordable solution to the ADAS for the docking of electric buses while recharging. We focus on the practical side of the system, showing how the necessary features were attained at a limited hardware and installation cost, also demonstrating an extensive evaluation of the fielded ADAS for an operator of public transportation in the city of Poznań in Poland.