WGANVO: odometría visual monocular basada en redes adversarias generativas

Cremona, Javier; Uzal, Lucas C.; Pire, Taihú

doi:10.4995/riai.2022.16113

Cited by 2 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [31], the environment is divided into rooms and their category is considered. Visual odometry has been employed in [32].…”

Section: Is Problemmentioning

confidence: 99%

Active robotic search for victims using ensemble deep learning techniques

García-Samartín,

Cruz Ulloa,

del Cerro

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

In recent years, legged quadruped robots have proved to be a valuable support to humans in dealing with Search and Rescue (SAR) operations. These robots can move with great ability in complex terrains, unstructured environments or regions with many obstacles. This work employs the quadruped robot ARTU-R (A1 Rescue Tasks UPM Robot) by Unitree, equipped with an RGB-D camera and a lidar, to perform victim searches in post-disaster scenarios. Exploration is done not by following a pre-planned path (as common methods) but by prioritising the areas most likely to harbour victims. To accomplish that task, both Indirect Search (IS) and Next Best View (NBV) techniques have been used. When ARTU-R gets inside an unstructured and unknown environment, it selects the next exploration point from a series of candidates. This operation is performed by comparing, for each candidate, the distance to reach it, the unexplored space around it and the probability of a victim being in its vicinity. This probability value is obtained using a Random Forest, which processes the information provided by a Convolutional Neural Network (CNN). Unlike other AI techniques, random forests are not black box models; humans can understand their decision-making processes. The system, once integrated, achieves speeds comparable to other state-of-the-art algorithms in terms of exploration, but concerning victim detection, the tests show that the resulting smart exploration generates logical paths --from a human point of view-- and that ARTU-R tends to move first to the regions where victims are present.

show abstract

“…In [31], the environment is divided into rooms and their category is considered. Visual odometry has been employed in [32].…”

Section: Is Problemmentioning

confidence: 99%

Active robotic search for victims using ensemble deep learning techniques

García-Samartín,

Cruz Ulloa,

del Cerro

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Furthermore, replicating the precise color reproduction, as well as the quantity and distribution of objects in simulations, poses significant challenges. Nevertheless, simulators and synthetic datasets are invaluable tools, both as alternatives and complements to real-world data across various fields [13,14]. This is especially evident in the self-driving car sector, in which simulation platforms, like CARLA [15], SYNTHIA [16], and LGSVL [17], are extensively used.…”

Section: Synthetic Datasetmentioning

confidence: 99%

Validating Synthetic Data for Perception in Autonomous Airport Navigation Tasks

de Frutos Carro,

Villalonga,

Cruz

2024

Aerospace

View full text Add to dashboard Cite

Autonomous navigation within airport environments presents significant challenges, mostly due to the scarcity of accessible and labeled data for training autonomous systems. This study introduces an innovative approach to assess the performance of vision-based models trained on synthetic datasets, with the goal of determining whether simulated data can train and validate navigation operations in complex airport environments. The methodology includes a comparative analysis employing image processing techniques and object detection algorithms. A comparative analysis of two different datasets was conducted: a synthetic dataset that mirrors real airport scenarios, generated using the Microsoft Flight Simulator 2020®video game, and a real-world dataset. The results indicate that models trained on a combination of both real and synthetic images perform much better in terms of adaptability and accuracy compared to those trained only on one type of dataset. This analysis makes a significant contribution to the field of autonomous airport navigation and offers a cost-effective and practical solution to overcome the challenges of dataset acquisition and algorithm validation. It is thus believed that this study lays the groundwork for future advancements in the field.

show abstract

WGANVO: odometría visual monocular basada en redes adversarias generativas

Cited by 2 publications

References 33 publications

Active robotic search for victims using ensemble deep learning techniques

Active robotic search for victims using ensemble deep learning techniques

Validating Synthetic Data for Perception in Autonomous Airport Navigation Tasks

Contact Info

Product

Resources

About