Carlos André Braile Przewodowski Filho

Dr. Carlos André Braile Przewodowski Filho

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
25 March 2024 in Sensors
Verified
Journal Article
Open access
PDF file
LRLuis Rosero
Luis Rosero
IGIago Pacheco Gomes
Iago Pacheco Gomes
JSJúnior Anderson Rodrigues da Silva
Júnior Anderson Rodrigues da Silva
CFCarlos André Braile Przewodowski Filho
Carlos André Braile Przewodowski Filho
DWDenis Fernando Wolf
Denis Fernando Wolf
FOFernando Santos Osorio
Fernando Santos Osorio
Autonomous driving navigation relies on diverse approaches, each with advantages and limitations depending on various factors. For HD maps, modular systems excel, while end-to-end methods dominate mapless scenarios. However, few leverage the strengths of both. This paper innovates by proposing a hybrid architecture that seamlessly integrates modular perception and control modules with data-driven path planning. This innovative design leverages the strengths of both approaches, enabling a clear understanding and debugging of individual components while simultaneously harnessing the learning power of end-to-end approaches. Our proposed architecture achieved first and second place in the 2023 CARLA Autonomous Driving Challenge’s SENSORS and MAP tracks, respectively. These results demonstrate the architecture’s effectiveness in both map-based and mapless navigation. We achieved a driving score of 41.56 and the highest route completion of 86.03 in the MAP track of the CARLA Challenge leaderboard 1, and driving scores of 35.36 and 1.23 in the CARLA Challenge SENSOR track with route completions of 85.01 and 9.55, for, respectively, leaderboard 1 and 2. The results of leaderboard 2 raised the hybrid architecture to the first position, winning the edition of the 2023 CARLA Autonomous Driving Competition.

8 March 2024 in Journal of the Brazilian Computer Society
Verified
Journal Article
Open access
PDF file
CFCarlos André Braile Przewodowski Filho
Carlos André Braile Przewodowski Filho
FOFernando Santos Osorio
Fernando Santos Osorio
VJValdir Grassi Jr.
Valdir Grassi Jr.
Localization is a critical component in autonomous vehicle navigation stacks. While GNSS-only localization cannot be fully reliable and available all the time, localization based on 3D high-definition (HD) maps have to be robust to world changes, which is still a challenging issue. Added to that, in general, HD maps are expensive and difficult to construct and maintain.In this paper, we propose a particle filter-based 2D global pose estimation method that can use the crowdsourced OpenStreetMap (OSM) API, a digital surface map, or both. The main contributions of the proposed approach are: that it is lightweight, does not require the vehicle to map the environment, does not require a GPU (can be used with low-power computing resources), is agnostic to the odometry source, and achieved relatively low position and orientation errors for this localization modality using the KITTI dataset sequences. The proposed method's implementation is open source and is available with the experimental results on our GitHub page.

7 February 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
LRLuis Rosero
Luis Rosero
IGIago Pacheco Gomes
Iago Pacheco Gomes
JSJúnior Anderson Rodrigues Da Silva
Júnior Anderson Rodrigues Da Silva
CFCarlos André Braile Przewodowski Filho
Carlos André Braile Przewodowski Filho
DWDenis Fernando Wolf
Denis Fernando Wolf
FOFernando Santos Osorio
Fernando Santos Osorio
Autonomous driving navigation relies on diverse approaches, each with advantages and limitations depending on various factors. For HD maps, modular systems excel, while end-to-end methods dominate mapless scenarios. However, few leverage the strengths of both. This paper innovates by proposing a hybrid architecture that seamlessly integrates modular perception and control modules with data-driven path planning. This innovative design leverages the strengths of both approaches, enabling a clear understanding and debugging of individual components while simultaneously harnessing the learning power of end-to-end approaches. Our proposed architecture achieved 1st and 2nd place in the 2023 CARLA Autonomous Driving Challenge’s SENSORS and MAP tracks, respectively. These results demonstrate the architecture’s effectiveness in both map-based and mapless navigation.

1 November 2017
Verified
Conference Paper
Closed access
CFCarlos André Braile Przewodowski Filho
Carlos André Braile Przewodowski Filho
FOFernando Santos Osorio
Fernando Santos Osorio
The 3D object recognition is an important research field in robotics. The real world object classification, retrieval, localization and tracking from images (2D or 3D data) are very useful application of computer vision in many areas, for instance, robotics, industry, education, augmented reality and medicine. Locate and recognize 3D objects in the environment can serve to create robust landmarks for robot pose estimation and localization, and can also be very important in telepresence, teleoperation, and grasping tasks. On the other hand, complex networks applications are a growing research field, and their application on computer vision is still a very recent research topic. This work uses complex networks to create shape descriptors for 3D point clouds of objects, and then uses a machine learning algorithm (k-NN) for object classification. Experiments of object classification, considering only the 3D shape, were done using the well known UW-University of Washington RGB-D objects dataset. The results are comparable to the best results of recent methods on the same dataset.

9 July 2019 in Concepts in Magnetic Resonance Part A
Verified
Journal Article
Open access
PDF file
YCYuri A. Costa
Yuri A. Costa
CFCarlos André Braile Przewodowski Filho
Carlos André Braile Przewodowski Filho
GFGabriela A. Flores
Gabriela A. Flores
EREvandro L. L. Rodrigues
Evandro L. L. Rodrigues
FPFernando F. Paiva
Fernando F. Paiva
Current methods for estimation of proton density fat fraction (PDFF) of the liver using magnitude magnetic resonance (MR) imaging face the challenge of correctly estimating it when fat is the dominant molecule; i.e., PDFF is more than 50%. Therefore, the accuracy of the methods is limited to half-range operation. We introduce a method based on neural networks for regression capable of estimating over the full range of fat fractions. We built a neural network based on the angles and distances between the data in the discrete MR signal (ADALIFE), using these as features associated with different PDFFs and as input for the network. Tests were performed using ADALIFE and Multi-interference, a state-of-the-art method to estimate PDFFs, with simulated signals at various signal-to-noise (SNR) values. Results were compared in order to verify repeatability and agreement using Bland-Altman and REC curves. Results for Multi-interference were similar to its in vivo literature, showing the relevance of a simulation. ADALIFE was able to correctly estimate fat fractions up to 100%, breaking the current paradigm for full-range estimation using only offline postprocessing. Within half range, our method outperformed Multi-interference in repeatability and agreement, with narrower limits of agreement and lower expected error at any SNR.

1 October 2019
Verified
Conference Paper
Closed access
CFCarlos André Braile Przewodowski Filho
Carlos André Braile Przewodowski Filho
FOFernando Santos Osorio
Fernando Santos Osorio
Self-driving vehicles' localization approaches are based either on pre-mapped features collected from the environment or on GPS information. While the former depends on remapping the environment constantly with fine precision, the latter requires GPS signal availability and strength at most of the time. On the other hand, computer vision, allied to machine learning, became a valuable resource in the detection of objects on images. These objects can be used as global landmarks that can be useful for autonomous vehicles' localization. In a highway, for instance, signs provide meaningful information for humans that could be potentially useful for localizing a self-driving vehicle as well. Therefore, in this paper, we propose a method based on the Kalman filter that uses odometry and road signs information for localizing the vehicle. We simulated the experiments using Gazebo and performed the Kalman filter prediction using inertial odometry. Comparison was performed between: (i) uncorrected estimation; (ii) corrected estimation using only the velocity provided by simulated speedometer readings ; (iii) corrected estimation using only signs' information; and (iv) corrected estimation using both speedometer readings and signs' information. The results yielded by the experiments show that, in an 8 kilometers non-linear track, the filter is able to perform localization with error in position as low as 100 meters at high prediction frequency (100 Hertz). Furthermore, the code developed in this project is available online.