Gerardo Flores

L. Arreola, A. Montes de Oca, A. Flores et al.

In this paper, we develop a position estimation system for Unmanned Aerial Vehicles formed by hardware and software. It is based on low-cost devices: GPS, commercial autopilot sensors and dense optical flow algorithm implemented in an onboard microcomputer. Comparative tests were conducted using our approach and the conventional one, where only fusion of GPS and inertial sensors are used. Experiments were conducted using a quadrotor in two flying modes: hovering and trajectory tracking in outdoor environments. Results demonstrate the effectiveness of the proposed approach in comparison with the conventional approaches presented in the vast majority of commercial drones.

A. Flores, A. Montes de Oca, Gerardo Flores

This paper presents a controller for the transition maneuver of a tail-sitter drone. The tail-sitter model considers aerodynamic terms whereas the proposed controller considers the time-scale separation between drone attitude and position dynamics. The controller design is based on Lyapunov approach and linear saturation functions. Simulations experiments demonstrate the effectiveness of the derived theoretical results.

Gerardo Flores, Alejandro Flores, Andrés Montes de Oca

This paper presents a nonlinear control law for the stabilization of a fixed-wing UAV. Such controller solves the path-following problem and the longitudinal control problem in a single control. Furthermore, the control design is performed considering aerodynamics and state information available in the commercial autopilots with the aim of an ease implementation. It is achieved that the closed-loop system is G.A.S. and robust to external disturbances. The difference among the available controllers in the literature is: 1) it depends on available states, hence it is not required extra sensors or observers; and 2) it is possible to achieve any desired airplane state with an ease of implementation, since its design is performed keeping in mind the capability of implementation in any commercial autopilot.

Gerardo Flores, George H. Chen, Tom Pollard et al.

A collection of invited non-archival papers for the Conference on Health, Inference, and Learning (CHIL) 2022. This index is incomplete as some authors of invited non-archival presentations opted not to include their papers in this index.

A. Flores, G. Flores

The control of a tail-sitter aircraft is a challenging task, especially during transition maneuver where the lift and drag forces are highly nonlinear. In this work, we implement a Neural Network (NN) capable of estimate such nonlinearities. Once they are estimated, one can propose a control scheme where these forces can correctly feed-forwarded. Our implementation of the NN has been programmed in C++ on the PX4 Autopilot an open-source autopilot for drones. To ensure that this implementation does not considerably affect the autopilot's performance, the coded NN must be of a light computational load. With the aim to test our approach, we have carried out a series of realistic simulations in the Software in The Loop (SITL) using the PX4 Autopilot. These experiments demonstrate that the implemented NN can be used to estimate the tail-sitter aerodynamic forces, and can be used to improve the control algorithms during all the flight phases of the tail-sitter aircraft: hover, cruise flight, and transition.

Rodolfo Verdín, Germán Ramírez, Carlos Rivera et al.

The tasks that an aerial manipulator can perform are incredibly diverse. However, nowadays the technology is not completely developed to achieve complex tasks autonomously. That's why we propose a human-in-the-loop system that can control a semi-autonomous aerial manipulator to accomplish these kinds of tasks. Furthermore, motivated by the growing trend of virtual reality systems, together with teleoperation, we develop a system composed of: an aerial manipulator model programmed in PX4 and modeled in Gazebo, a virtual reality immersion with an interactive controller, and the interconnection between the aforementioned systems via the Internet. This research is the first part of a broader project. In this part, we present experiments in the software in the loop simulation. The code of this work is liberated on our GitHub page. Also, a video shows the conducted experiments.

Daniela Esparza, Gerardo Flores

Commonly, SLAM algorithms are focused on a static environment, however, there are several scenes where dynamic objects are present. This work presents the STDyn-SLAM an image feature-based SLAM system working on dynamic environments using a series of sub-systems, like optic flow, orb features extraction, visual odometry, and convolutional neural networks to discern moving objects in the scene. The neural network is used to support object detection and segmentation to avoid erroneous maps and wrong system localization. The STDyn-SLAM employs a stereo pair and is developed for outdoor environments. Moreover, the processing time of the proposed system is fast enough to run in real-time as it was demonstrated through the experiments given in real dynamic outdoor environments. Further, we compare our SLAM with state-of-the-art methods achieving promising results.

Alejandro Flores, Gerardo Flores

This paper presents the implementation of a Recurrent Neural Network (RNN) based-controller for the stabilization of the flight transition maneuver (hover-cruise and vice versa) of a tail-sitter UAV. The control strategy is based on attitude and velocity stabilization. For that aim, the RNN is used for the estimation of high nonlinear aerodynamic terms during the transition stage. Then, this estimate is used together with a feedback linearization technique for stabilizing the entire system. Results show convergence of linear velocities and the pitch angle during the transition maneuver. To analyze the performance of our proposed control strategy, we present simulations for the transition from hover to cruise and vice versa.

Sebastián Salazar-Colores, Hugo Alberto-Moreno, César Javier Ortiz-Echeverri et al.

In laparoscopic surgery, the visibility in the image can be severely degraded by the smoke caused by the $CO_2$ injection, and dissection tools, thus reducing the visibility of organs and tissues. This lack of visibility increases the surgery time and even the probability of mistakes conducted by the surgeon, then producing negative consequences on the patient's health. In this paper, a novel computational approach to remove the smoke effects is introduced. The proposed method is based on an image-to-image conditional generative adversarial network in which a dark channel is used as an embedded guide mask. Obtained experimental results are evaluated and compared quantitatively with other desmoking and dehazing state-of-art methods using the metrics of the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) index. Based on these metrics, it is found that the proposed method has improved performance compared to the state-of-the-art. Moreover, the processing time required by our method is 92 frames per second, and thus, it can be applied in a real-time medical system trough an embedded device.

Kun Zhang, Yuan Xue, Gerardo Flores et al.

Time series data are prevalent in electronic health records, mostly in the form of physiological parameters such as vital signs and lab tests. The patterns of these values may be significant indicators of patients' clinical states and there might be patterns that are unknown to clinicians but are highly predictive of some outcomes. Many of these values are also missing which makes it difficult to apply existing methods like decision trees. We propose a recurrent neural network model that reduces overfitting to noisy observations by limiting interactions between features. We analyze its performance on mortality, ICD-9 and AKI prediction from observational values on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset. Our models result in an improvement of 1.1% [p<0.01] in AU-ROC for mortality prediction under the MetaVision subset and 1.0% and 2.2% [p<0.01] respectively for mortality and AKI under the full MIMIC-III dataset compared to existing state-of-the-art interpolation, embedding and decay-based recurrent models.

Michaela Hardt, Alvin Rajkomar, Gerardo Flores et al.

Much work aims to explain a model's prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estimates given an input at each time step. When the estimated risk increases, the goal of the explanation is to attribute the increase to a few relevant inputs from the past. While our formal setup and techniques are general, we carry out an in-depth case study in a clinical setting. The goal here is to alert a clinician when a patient's risk of deterioration rises. The clinician then has to decide whether to intervene and adjust the treatment. Given a potentially long sequence of new events since she last saw the patient, a concise explanation helps her to quickly triage the alert. We develop methods to lift static attribution techniques to the dynamical setting, where we identify and address challenges specific to dynamics. We then experimentally assess the utility of different explanations of clinical alerts through expert evaluation.

Edward Choi, Zhen Xu, Yujia Li et al.

Effective modeling of electronic health records (EHR) is rapidly becoming an important topic in both academia and industry. A recent study showed that using the graphical structure underlying EHR data (e.g. relationship between diagnoses and treatments) improves the performance of prediction tasks such as heart failure prediction. However, EHR data do not always contain complete structure information. Moreover, when it comes to claims data, structure information is completely unavailable to begin with. Under such circumstances, can we still do better than just treating EHR data as a flat-structured bag-of-features? In this paper, we study the possibility of jointly learning the hidden structure of EHR while performing supervised prediction tasks on EHR data. Specifically, we discuss that Transformer is a suitable basis model to learn the hidden EHR structure, and propose Graph Convolutional Transformer, which uses data statistics to guide the structure learning process. The proposed model consistently outperformed previous approaches empirically, on both synthetic data and publicly available EHR data, for various prediction tasks such as graph reconstruction and readmission prediction, indicating that it can serve as an effective general-purpose representation learning algorithm for EHR data.

Sergio Trejo, Karla Martinez, Gerardo Flores

This paper presents a vision-based methodology which makes use of a stereo camera rig and a one dimension LiDAR to estimate free obstacle areas for quadrotor navigation. The presented approach fuses information provided by a depth map from a stereo camera rig, and the sensing distance of the 1D-LiDAR. Once the depth map is filtered with a Weighted Least Squares filter (WLS), the information is fused through a Kalman filter algorithm. To determine if there is a free space large enough for the quadrotor to pass through, our approach marks an area inside the disparity map by using the Kalman Filter output information. The whole process is implemented in an embedded computer Jetson TX2 and coded in the Robotic Operating System (ROS). Experiments demonstrate the effectiveness of our approach.

Luis Arreola, Gesem Gudiño, Gerardo Flores

In this paper, we develop a functional Unmanned Aerial Vehicle (UAV), capable of tracking an object using a Machine Learning-like vision system called Haar feature-based cascade classifier. The image processing is made on-board with a high processor single-board computer. Based on the detected object and its position, the quadrotor must track it in order to be in a centered position and in a safe distance to it. The object in question is a human face; the experiments were conducted in a two-step detection, searching first for the upper-body and then searching for the face inside of the human body detected area. Once the human face is detected the quadrotor must follow it automatically. Experiments were conducted which shows the effectiveness of our mythology; these results are showing in a video.