Hector Gutierrez

Dr. Hector Gutierrez

Florida Institute of technology
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
8 May 2019 in Journal of Dynamic Systems, Measurement, and Control
Verified
Journal Article
Open access
PDF file
MPMichael Person
Michael Person
MJMathew Jensen
Mathew Jensen
ASAnthony O. Smith
Anthony O. Smith
Hector GutierrezHector Gutierrez
Hector Gutierrez
In order for autonomous vehicles to safely navigate the road ways, accurate object detection must take place before safe path planning can occur. Currently, general purpose object detection convolutional neural network (CNN) models have the highest detection accuracies of any method. However, there is a gap in the proposed detection frameworks. Specifically, those that provide high detection accuracy necessary for deployment but do not perform inference in realtime, and those that perform inference in realtime but detection accuracy is low. We propose multimodel fusion detection system (MFDS), a sensor fusion system that combines the speed of a fast image detection CNN model along with the accuracy of light detection and range (LiDAR) point cloud data through a decision tree approach. The primary objective is to bridge the tradeoff between performance and accuracy. The motivation for MFDS is to reduce the computational complexity associated with using a CNN model to extract features from an image. To improve efficiency, MFDS extracts complimentary features from the LiDAR point cloud in order to obtain comparable detection accuracy. MFDS is novel by not only using the image detections to aid three-dimensional (3D) LiDAR detection but also using the LiDAR data to jointly bolster the image detections and provide 3D detections. MFDS achieves 3.7% higher accuracy than the base CNN detection model and is able to operate at 10 Hz. Additionally, the memory requirement for MFDS is small enough to fit on the Nvidia Tx1 when deployed on an embedded device.

23 January 2018 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Hector GutierrezHector Gutierrez
Hector Gutierrez
HLHanri Luijten
Hanri Luijten
This paper presents the five degree-of-freedom (5-DOF) control of an electrodynamic MAGLEV suspension with active control of the levitation coils. A sled with built-in permanent magnets moves past an array of fixed coils to generate Lorentz forces that provide lift and guidance. When active control of the levitation coil currents is implemented, multi-DOF trajectory control can be achieved, leading to stable electrodynamic levitation that can actively reject disturbances independently of sled speed. This paper shows successful control of the multi-DOF trajectory of a passive sled by active control of the coil currents, using both a sliding mode controller with nonlinear input mapping from coil currents to levitation forces, and a multi-DOF nonlinear observer. The paper also compares the use of look up tables versus analytical models of the magnetic field density used to estimate the magnetic forces and torques acting on the sled. The performance of the proposed approaches is demonstrated experimentally.

19 July 2023 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
OQOmar Qasem
Omar Qasem
Hector GutierrezHector Gutierrez
Hector Gutierrez
Weinan GaoWeinan Gao
Weinan Gao
In this article, a successive approximation learning framework for adaptive optimal control problems, named hybrid iteration (HI), is presented and validated experimentally. The HI strategy outperforms two well-known adaptive dynamic programming strategies, i.e., policy iteration (PI) and value iteration (VI). Using HI, an approximated optimal control policy is learned without the prior knowledge of an admissible control policy required by PI. At the same time, comparing to VI, the HI algorithm converges to the optimal solution with tremendously less learning iterations and CPU-time. Initially, we present the settings of the data-driven HI for continuous-time nonlinear systems and continuous-time linear systems to learn the optimal control policy without any information of the dynamics of the system. Following that, the proposed HI method is implemented on a nonlinear rotary inverted pendulum, and its online learning performance is validated by learning the optimal control policy using online data. The experimental results reveal the efficacy and practicality of the HI method, and demonstrate its superior online learning performance over the traditional PI and VI methods.

1 April 2018 in International Journal of Heat and Mass Transfer
Verified
Journal Article
Closed access
RBReza Bahadori
Reza Bahadori
Hector GutierrezHector Gutierrez
Hector Gutierrez
SMShashikant Manikonda
Shashikant Manikonda
RMRainer Meinke
Rainer Meinke

12 April 2018 in Nonlinear Dynamics
Verified
Journal Article
Closed access
PDF file
NHnaibao he
naibao he
QGQian Gao
Qian Gao
Hector GutierrezHector Gutierrez
Hector Gutierrez
CJChangsheng Jiang
Changsheng Jiang
YYYifei Yang
Yifei Yang
YBYuchun Bi
Yuchun Bi

9 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
NHNicolas Bautista Holguin
Nicolas Bautista Holguin
Hector GutierrezHector Gutierrez
Hector Gutierrez
JIJohn Inness
John Inness
JRJohn Rakoczy
John Rakoczy
This paper describes the deployment, integration, and demonstration of a Smartphone Video Guidance Sensor (SVGS) as a novel technology for autonomous 6-DOF proximity maneuvers and precision landing of a quadcopter drone. The proposed approach uses a vision-based photogrammetric position and attitude sensor (SVGS) to estimate the position of a landing target after video capture. A visual inertial odometry sensor (VIO) is used to provide position estimates of the UAV in a ground coordinate system during flight on a GPS-denied environment. The integration of both SVGS and VIO sensors enables the accurate updating of position setpoints during landing, providing improved performance compared with VIO-only landing, as shown in landing experiments. The proposed technique also shows significant operational advantages compared with state-of-the-art sensors for indoor landing, such as those based on augmented reality (AR) markers.