Novel Certad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Novel Certad has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Angel Terrones
Department of Electronical Engineering, Universidad Simón Bolívar, Sartenejas, Miranda, Venezuela
3 shared publications- Cristina Olaverri-Monreal
Johannes Kepler University Linz
3 shared publications Dimitar Ralev
Simón Bolívar University, Caracas, Venezuela
3 shared publications- Jose Cappelletto
Universidad Simón Bolívar, Caracas, Venezuela
3 shared publications - Walter Morales-Alvarez
Johannes Kepler University Linz
3 shared publications Elvis Ruiz
2 shared publications
Latest Publications
- 2 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 16 (4) , 6-20
Interaction of Autonomous and Manually Controlled Vehicles Multiscenario Vehicle Interaction Dataset
The acquisition and analysis of high-quality sensor data constitute an essential requirement in shaping the development of fully autonomous driving systems. This process is indispensable for enhancing road safety and ensuring the effectiveness of the technological advancements in the automotive industry. This study introduces the Interaction of Autonomous and Manually Controlled Vehicles (IAMCV) dataset, a novel and extensive dataset focused on intervehicle interactions. The dataset, enriched with a sophisticated array of sensors such as lidar, cameras, inertial measurement unit/Global Positioning System, and vehicle bus data acquisition, provides a comprehensive representation of real-world driving scenarios that include roundabouts, intersections, country roads, and highways, recorded across diverse locations in Germany. Furthermore, the study shows the versatility of the IAMCV dataset through several proof-of-concept use cases. First, an unsupervised trajectory clustering algorithm illustrates the dataset’s capability in categorizing vehicle movements without the need for labeled training data. Second, we compare an online camera calibration method with the Robot Operating System-based standard, using images captured in the dataset. Finally, a preliminary test employing the YOLOv8 object-detection model is conducted, augmented by reflections on the transferability of object detection across various lidar resolutions. These use cases underscore the practical utility of the collected dataset, emphasizing its potential to advance research and innovation in the area of intelligent vehicles.
- 2 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 16 (4) , 6-20
Interaction of Autonomous and Manually Controlled Vehicles Multiscenario Vehicle Interaction Dataset
The acquisition and analysis of high-quality sensor data constitute an essential requirement in shaping the development of fully autonomous driving systems. This process is indispensable for enhancing road safety and ensuring the effectiveness of the technological advancements in the automotive industry. This study introduces the Interaction of Autonomous and Manually Controlled Vehicles (IAMCV) dataset, a novel and extensive dataset focused on intervehicle interactions. The dataset, enriched with a sophisticated array of sensors such as lidar, cameras, inertial measurement unit/Global Positioning System, and vehicle bus data acquisition, provides a comprehensive representation of real-world driving scenarios that include roundabouts, intersections, country roads, and highways, recorded across diverse locations in Germany. Furthermore, the study shows the versatility of the IAMCV dataset through several proof-of-concept use cases. First, an unsupervised trajectory clustering algorithm illustrates the dataset’s capability in categorizing vehicle movements without the need for labeled training data. Second, we compare an online camera calibration method with the Robot Operating System-based standard, using images captured in the dataset. Finally, a preliminary test employing the YOLOv8 object-detection model is conducted, augmented by reflections on the transferability of object detection across various lidar resolutions. These use cases underscore the practical utility of the collected dataset, emphasizing its potential to advance research and innovation in the area of intelligent vehicles.
- Open Access
On Transferability of Driver Observation Models from Simulated to Real Environments in Autonomous Cars
For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground. Yet, when deployed under real driving conditions, such simulator-trained models quickly face the problem of distributional shifts brought about by changing illumination, car model, variations in subject appearances, sensor discrepancies, and other environmental alterations. This paper investigates the viability of transferring video-based driver observation models from simulation to real-world scenarios in autonomous vehicles, given the frequent use of simulation data in this domain due to safety issues. To achieve this, we record a dataset featuring actual autonomous driving conditions and involving seven participants engaged in highly distracting secondary activities. To enable direct SIM to REAL transfer, our dataset was designed in accordance with an existing large-scale simulator dataset used as the training source. We utilize the Inflated 3D ConvNet (I3D) model, a popular choice for driver observation, with Gradient-weighted Class Activation Mapping (Grad-CAM) for detailed analysis of model decision-making. Though the simulator-based model clearly surpasses the random baseline, its recognition quality diminishes, with average accuracy dropping from 85.7% to 46.6%. We also observe strong variations across different behavior classes. This underscores the challenges of model transferability, facilitating our research of more robust driver observation systems capable of dealing with real driving conditions.
Open AccessOn Transferability of Driver Observation Models from Simulated to Real Environments in Autonomous Cars
For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground. Yet, when deployed under real driving conditions, such simulator-trained models quickly face the problem of distributional shifts brought about by changing illumination, car model, variations in subject appearances, sensor discrepancies, and other environmental alterations. This paper investigates the viability of transferring video-based driver observation models from simulation to real-world scenarios in autonomous vehicles, given the frequent use of simulation data in this domain due to safety issues. To achieve this, we record a dataset featuring actual autonomous driving conditions and involving seven participants engaged in highly distracting secondary activities. To enable direct SIM to REAL transfer, our dataset was designed in accordance with an existing large-scale simulator dataset used as the training source. We utilize the Inflated 3D ConvNet (I3D) model, a popular choice for driver observation, with Gradient-weighted Class Activation Mapping (Grad-CAM) for detailed analysis of model decision-making. Though the simulator-based model clearly surpasses the random baseline, its recognition quality diminishes, with average accuracy dropping from 85.7% to 46.6%. We also observe strong variations across different behavior classes. This underscores the challenges of model transferability, facilitating our research of more robust driver observation systems capable of dealing with real driving conditions.
- 1 January 2022
- Published by Springer Nature
- p. 329-336
JKU-ITS Automobile for Research on Autonomous Vehicles
- 1 January 2022
- Published by Springer Nature
- p. 329-336
JKU-ITS Automobile for Research on Autonomous Vehicles
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Autonomous 2D SLAM and 3D mapping of an environment using a single 2D LIDAR and ROS
This paper describes an algorithm that performs an autonomous 3D reconstruction of an environment with a single 2D Laser Imaging Detection and Ranging (LIDAR) sensor, as well as its implementation on a mobile platform using the Robot Operating System (ROS). A ROS node was used to redirect the flow of data that can go to either the 2D Simultaneous Localization And Mapping (SLAM) ROS node or to the 3D Octomap ROS node depending on the operation performed at that moment, with neither of the nodes going out of sync or crashing. The autonomous algorithm is implemented with the State Machines (SMACH) library and it uses ROS interfaces such as services and actions to create a 3D model of the robot's surroundings without prior information or human intervention.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Autonomous 2D SLAM and 3D mapping of an environment using a single 2D LIDAR and ROS
This paper describes an algorithm that performs an autonomous 3D reconstruction of an environment with a single 2D Laser Imaging Detection and Ranging (LIDAR) sensor, as well as its implementation on a mobile platform using the Robot Operating System (ROS). A ROS node was used to redirect the flow of data that can go to either the 2D Simultaneous Localization And Mapping (SLAM) ROS node or to the 3D Octomap ROS node depending on the operation performed at that moment, with neither of the nodes going out of sync or crashing. The autonomous algorithm is implemented with the State Machines (SMACH) library and it uses ROS interfaces such as services and actions to create a 3D model of the robot's surroundings without prior information or human intervention.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Construction, identification and instrumentation of a low cost quadcopter research platform
This paper presents the design of a low cost quadcopter prototype intended as a research platform that allows the study of control algorithms for autonomous flight. The dynamics of this quadcopter were described with a mathematical model, and the prototype's parameters were identified through a series of proposed methods and test-beds. A sensor array that is theoretically capable of estimating the robot's state using only on-board, off-the-shelf sensors, is presented. A procedure for calibrating a 3-axis magnetometer was implemented. Three methods for minimizing the effects of mechanical vibrations on the sensors were compared. At last, the effectiveness of the platform was examined by implementing a state estimator and a simple PID angular controller, and by testing the flight stability of the quadcopter on two test-beds built for this purpose.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Construction, identification and instrumentation of a low cost quadcopter research platform
This paper presents the design of a low cost quadcopter prototype intended as a research platform that allows the study of control algorithms for autonomous flight. The dynamics of this quadcopter were described with a mathematical model, and the prototype's parameters were identified through a series of proposed methods and test-beds. A sensor array that is theoretically capable of estimating the robot's state using only on-board, off-the-shelf sensors, is presented. A procedure for calibrating a 3-axis magnetometer was implemented. Three methods for minimizing the effects of mechanical vibrations on the sensors were compared. At last, the effectiveness of the platform was examined by implementing a state estimator and a simple PID angular controller, and by testing the flight stability of the quadcopter on two test-beds built for this purpose.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 73-78
Trajectory Generation and Tracking Using the AR.Drone 2.0 Quadcopter UAV
Trajectory generation and tracking algorithms were developed using ROS (Robot Operating System) for the AR. Drone 2.0 quad copter. Flight paths were created with cubic polynomials and Bezier curves. A PID controller was implemented to drive the AR. Drone from its current position to the desired coordinate point for the trajectory tracking task. Additionally, a navigation method was implemented using attractive and repulsive artificial potential fields to carry out obstacle-avoidance and goal-reaching tasks. The software was tested using simulations in Gazebo and the real AR. Drone. The drone's global position was estimated using an Extended Kalman Filter and visual landmarks.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 73-78
Trajectory Generation and Tracking Using the AR.Drone 2.0 Quadcopter UAV
Trajectory generation and tracking algorithms were developed using ROS (Robot Operating System) for the AR. Drone 2.0 quad copter. Flight paths were created with cubic polynomials and Bezier curves. A PID controller was implemented to drive the AR. Drone from its current position to the desired coordinate point for the trajectory tracking task. Additionally, a navigation method was implemented using attractive and repulsive artificial potential fields to carry out obstacle-avoidance and goal-reaching tasks. The software was tested using simulations in Gazebo and the real AR. Drone. The drone's global position was estimated using an Extended Kalman Filter and visual landmarks.
- 21 October 2013
- Published by ASME International
Asymptotic Stability Method for PID Controller Tuning in a Backhoe Machine
This paper presents the modeling and study of dynamic behavior of a backhoe machine for tuning of PID controller. The tuning procedure of PID controller is performed, in detailed, for the case of a typical operation, digging a foundation and truck loading. This tuning procedure guarantees the local asymptotic stability in the sense of Lyapunov of origin of the closed-loop equation of PID controller. Besides the tuning procedure requires the knowledge of certain properties of dynamic model, which are dependent on the desired trajectory. Finally it is demonstrated that this tuning procedure proves to be effective, and also robust in the execution of other tasks performed by the backhoe machine.
- 21 October 2013
- Published by ASME International
Asymptotic Stability Method for PID Controller Tuning in a Backhoe Machine
This paper presents the modeling and study of dynamic behavior of a backhoe machine for tuning of PID controller. The tuning procedure of PID controller is performed, in detailed, for the case of a typical operation, digging a foundation and truck loading. This tuning procedure guarantees the local asymptotic stability in the sense of Lyapunov of origin of the closed-loop equation of PID controller. Besides the tuning procedure requires the knowledge of certain properties of dynamic model, which are dependent on the desired trajectory. Finally it is demonstrated that this tuning procedure proves to be effective, and also robust in the execution of other tasks performed by the backhoe machine.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 124-128
Analysis of Oscillators for the Generation of Rhythmic Patterns in Legged Robot Locomotion
This paper presents a study of several oscillators for the generation of rhythmic patterns that are used in the locomotion of legged robots using a central pattern generator (CPG). This work also shows a comparative analysis of these oscillators focused on their implementation as part of the CPG system, based on simulations made using software tools. Three models were implemented and simulated: the Hopf model as an example of a harmonic oscillator, a reflexive oscillator using the Van der Pol oscillator, and the ACPO (amplitude coupled phase oscillator) corresponding to the phase oscillators category. It is established that a phase oscillator is the best choice when working with CPGs offering a simple yet versatile way to connect the limbs.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 124-128
Analysis of Oscillators for the Generation of Rhythmic Patterns in Legged Robot Locomotion
This paper presents a study of several oscillators for the generation of rhythmic patterns that are used in the locomotion of legged robots using a central pattern generator (CPG). This work also shows a comparative analysis of these oscillators focused on their implementation as part of the CPG system, based on simulations made using software tools. Three models were implemented and simulated: the Hopf model as an example of a harmonic oscillator, a reflexive oscillator using the Van der Pol oscillator, and the ACPO (amplitude coupled phase oscillator) corresponding to the phase oscillators category. It is established that a phase oscillator is the best choice when working with CPGs offering a simple yet versatile way to connect the limbs.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 360, 55-60
Development of a Control Platform for the Mobile Robot Roomba Using ROS and a Kinect Sensor
A control scheme for the mobile robot Roomba was developed using ROS (robot operating system), which allowed the control of the robot using velocity vector references. A Kinect sensor was incorporated into the system and also a framework which provides communication with processes in other instances, monitoring and remote control. The system is flexible enough to be replicated in the future in other Roomba robots. With this framework it is possible to control the movement of the robot using velocity vector references generated from the spatial references extracted from de environment using the Kinect sensor.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 360, 55-60
Development of a Control Platform for the Mobile Robot Roomba Using ROS and a Kinect Sensor
A control scheme for the mobile robot Roomba was developed using ROS (robot operating system), which allowed the control of the robot using velocity vector references. A Kinect sensor was incorporated into the system and also a framework which provides communication with processes in other instances, monitoring and remote control. The system is flexible enough to be replicated in the future in other Roomba robots. With this framework it is possible to control the movement of the robot using velocity vector references generated from the spatial references extracted from de environment using the Kinect sensor.