arXiv subjects

Kevin Brink

Publications and source records attributed to Kevin Brink.

14 recordsLinked to original sources

arXiv2024

Real-time Uncertainty-Aware Motion Planning for Magnetic-based Navigation

Localization in GPS-denied environments is critical for autonomous systems, and traditional methods like SLAM have limitations in generalizability across diverse environments. Magnetic-based navigation (MagNav) offers a robust solution by leveraging the ubiquity and unique anomalies of external magnetic fields. This paper proposes a real-time uncertainty-aware motion planning algorithm for MagNav, using onboard magnetometers and information-driven methodologies to adjust trajectories based on real-time localization confidence. This approach balances the trade-off between finding the shortest or most energy-efficient routes and reducing localization uncertainty, enhancing navigational accuracy and reliability. The novel algorithm integrates an uncertainty-driven framework with magnetic-based localization, creating a real-time adaptive system capable of minimizing localization errors in complex environments. Extensive simulations and real-world experiments validate the method, demonstrating significant reductions in localization uncertainty and the feasibility of real-time implementation. The paper also details the mathematical modeling of uncertainty, the algorithmic foundation of the planning approach, and the practical implications of using magnetic fields for localization. Future work includes incorporating a global path planner to address the local nature of the current guidance law, further enhancing the method's suitability for long-duration operations.

cs.RO↗

arXiv2024

GPU-Accelerated 3D Polygon Visibility Volumes for Synergistic Perception and Navigation

UAV missions often require specific geometric constraints to be satisfied between ground locations and the vehicle location. Such requirements are typical for contexts where line-of-sight must be maintained between the vehicle location and the ground control location and are also important in surveillance applications where the UAV wishes to be able to sense, e.g., with a camera sensor, a specific region within a complex geometric environment. This problem is further complicated when the ground location is generalized to a convex 2D polygonal region. This article describes the theory and implementation of a system which can quickly calculate the 3D volume that encloses all 3D coordinates from which a 2D convex planar region can be entirely viewed; referred to as a visibility volume. The proposed approach computes visibility volumes using a combination of depth map computation using GPU-acceleration and geometric boolean operations. Solutions to this problem require complex 3D geometric analysis techniques that must execute using arbitrary precision arithmetic on a collection of discontinuous and non-analytic surfaces. Post-processing steps incorporate navigational constraints to further restrict the enclosed coordinates to include both visibility and navigation constraints. Integration of sensing visibility constraints with navigational constraints yields a range of navigable space where a vehicle will satisfy both perceptual sensing and navigational needs of the mission. This algorithm then provides a synergistic perception and navigation sensitive solution yielding a volume of coordinates in 3D that satisfy both the mission path and sensing needs.

cs.RO↗

arXiv2023

DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability

Out-of-distribution (OOD) generalization poses a serious challenge for modern deep learning (DL). OOD data consists of test data that is significantly different from the model's training data. DL models that perform well on in-domain test data could struggle on OOD data. Overcoming this discrepancy is essential to the reliable deployment of DL. Proper model calibration decreases the number of spurious connections that are made between model features and class outputs. Hence, calibrated DL can improve OOD generalization by only learning features that are truly indicative of the respective classes. Previous work proposed domain-aware model calibration (DOMINO) to improve DL calibration, but it lacks designs for model generalizability to OOD data. In this work, we propose DOMINO++, a dual-guidance and dynamic domain-aware loss regularization focused on OOD generalizability. DOMINO++ integrates expert-guided and data-guided knowledge in its regularization. Unlike DOMINO which imposed a fixed scaling and regularization rate, DOMINO++ designs a dynamic scaling factor and an adaptive regularization rate. Comprehensive evaluations compare DOMINO++ with DOMINO and the baseline model for head tissue segmentation from magnetic resonance images (MRIs) on OOD data. The OOD data consists of synthetic noisy and rotated datasets, as well as real data using a different MRI scanner from a separate site. DOMINO++'s superior performance demonstrates its potential to improve the trustworthy deployment of DL on real clinical data.

cs.CV↗

arXiv2023

Learning Flight Control Systems from Human Demonstrations and Real-Time Uncertainty-Informed Interventions

This paper describes a methodology for learning flight control systems from human demonstrations and interventions while considering the estimated uncertainty in the learned models. The proposed approach uses human demonstrations to train an initial model via imitation learning and then iteratively, improve its performance by using real-time human interventions. The aim of the interventions is to correct undesired behaviors and adapt the model to changes in the task dynamics. The learned model uncertainty is estimated in real-time via Monte Carlo Dropout and the human supervisor is cued for intervention via an audiovisual signal when this uncertainty exceeds a predefined threshold. This proposed approach is validated in an autonomous quadrotor landing task on both fixed and moving platforms. It is shown that with this algorithm, a human can rapidly teach a flight task to an unmanned aerial vehicle via demonstrating expert trajectories and then adapt the learned model by intervening when the learned controller performs any undesired maneuver, the task changes, and/or the model uncertainty exceeds a threshold

cs.RO↗

arXiv2023

Photometric Correction for Infrared Sensors

Infrared thermography has been widely used in several domains to capture and measure temperature distributions across surfaces and objects. This methodology can be further expanded to 3D applications if the spatial distribution of the temperature distribution is available. Structure from Motion (SfM) is a photometric range imaging technique that makes it possible to obtain 3D renderings from a cloud of 2D images. To explore the possibility of 3D reconstruction via SfM from infrared images, this article proposes a photometric correction model for infrared sensors based on temperature constancy. Photometric correction is accomplished by estimating the scene irradiance as the values from the solution to a differential equation for microbolometer pixel excitation with unknown coefficients and initial conditions. The model was integrated into an SfM framework and experimental evaluations demonstrate the contribution of the photometric correction for improving the estimates of both the camera motion and the scene structure. Further, experiments show that the reconstruction quality from the corrected infrared imagery achieves performance on par with state-of-the-art reconstruction using RGB sensors.

cs.CV↗

arXiv2023

DOMINO: Domain-aware Loss for Deep Learning Calibration

Deep learning has achieved the state-of-the-art performance across medical imaging tasks; however, model calibration is often not considered. Uncalibrated models are potentially dangerous in high-risk applications since the user does not know when they will fail. Therefore, this paper proposes a novel domain-aware loss function to calibrate deep learning models. The proposed loss function applies a class-wise penalty based on the similarity between classes within a given target domain. Thus, the approach improves the calibration while also ensuring that the model makes less risky errors even when incorrect. The code for this software is available at https://github.com/lab-smile/DOMINO.

cs.CV↗

arXiv2022

Incremental cycle bases for cycle-based pose graph optimization

Pose graph optimization is a special case of the simultaneous localization and mapping problem where the only variables to be estimated are pose variables and the only measurements are inter-pose constraints. The vast majority of pose graph optimization techniques are vertex based (variables are robot poses), but recent work has parameterized the pose graph optimization problem in a relative fashion (variables are the transformations between poses) that utilizes a minimum cycle basis to maximize the sparsity of the problem. We explore the construction of a cycle basis in an incremental manner while maximizing the sparsity. We validate an algorithm that constructs a sparse cycle basis incrementally and compare its performance with a minimum cycle basis. Additionally, we present an algorithm to approximate the minimum cycle basis of two graphs that are sparsely connected as is common in multi-agent scenarios. Lastly, the relative parameterization of pose graph optimization has been limited to using rigid body transforms on SE(2) or SE(3) as the constraints between poses. We introduce a methodology to allow for the use of lower-degree-of-freedom measurements in the relative pose graph optimization problem. We provide extensive validation of our algorithms on standard benchmarks, simulated datasets, and custom hardware.

cs.RO↗

arXiv2022

DOMINO: Domain-aware Model Calibration in Medical Image Segmentation

Model calibration measures the agreement between the predicted probability estimates and the true correctness likelihood. Proper model calibration is vital for high-risk applications. Unfortunately, modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. Medical image segmentation particularly suffers from this due to the natural uncertainty of tissue boundaries. This is exasperated by their loss functions, which favor overconfidence in the majority classes. We address these challenges with DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our experiments demonstrate that our DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation. Our results show that our method can consistently achieve better calibration, higher accuracy, and faster inference times than these methods, especially on rarer classes. This performance is attributed to our domain-aware regularization to inform semantic model calibration. These findings show the importance of semantic ties between class labels in building confidence in deep learning models. The framework has the potential to improve the trustworthiness and reliability of generic medical image segmentation models. The code for this article is available at: https://github.com/lab-smile/DOMINO.

eess.IV↗

arXiv2022

Information-Aware Guidance for Magnetic Anomaly based Navigation

In the absence of an absolute positioning system, such as GPS, autonomous vehicles are subject to accumulation of positional error which can interfere with reliable performance. Improved navigational accuracy without GPS enables vehicles to achieve a higher degree of autonomy and reliability, both in terms of decision making and safety. This paper details the use of two navigation systems for autonomous agents using magnetic field anomalies to localize themselves within a map; both techniques use the information content in the environment in distinct ways and are aimed at reducing the localization uncertainty. The first method is based on a nonlinear observability metric of the vehicle model, while the second is an information theory based technique which minimizes the expected entropy of the system. These conditions are used to design guidance laws that minimize the localization uncertainty and are verified both in simulation and hardware experiments are presented for the observability approach.

eess.SY↗

arXiv2022

A summary on the UD Kalman Filter

This document contains a concise and unified reference for one of the existing mechanizations of the UD Kalman filter. The associated matrix algorithms are also included along with the corresponding references.

eess.SY↗

arXiv2022

ROS georegistration: Aerial Multi-spectral Image Simulator for the Robot Operating System

This article describes a software package called ROS georegistration intended for use with the Robot Operating System (ROS) and the Gazebo 3D simulation environment. ROSgeoregistration provides tools for the simulation, test and deployment of aerial georegistration algorithms and is made available with a link provided in the paper. A model creation package is provided which downloads multi-spectral images from the Google Earth Engine database and, if necessary, incorporates these images into a single, possibly very large, reference image. Additionally a Gazebo plugin which uses the real-time sensor pose and image formation model to generate simulated imagery using the specified reference image is provided along with related plugins for UAV relevant data. The novelty of this work is threefold: (1) this is the first system to link the massive multi-spectral imaging database of Google's Earth Engine to the Gazebo simulator, (2) this is the first example of a system that can simulate geospatially and radiometrically accurate imagery from multiple sensor views of the same terrain region, and (3) integration with other UAS tools creates a new holistic UAS simulation environment to support UAS system and subsystem development where real-world testing would generally be prohibitive. Sensed imagery and ground truth registration information is published to client applications which can receive imagery synchronously with telemetry from other payload sensors, e.g., IMU, GPS/GNSS, barometer, and windspeed sensor data. To highlight functionality, we demonstrate ROSgeoregistration for simulating Electro-Optical (EO) and Synthetic Aperture Radar (SAR) image sensors and an example use case for developing and evaluating image-based UAS position feedback, i.e., pose for image-based Guidance Navigation and Control (GNC) applications.

cs.RO↗

arXiv2021

Deployable, Data-Driven Unmanned Vehicle Navigation System in GPS-Denied, Feature-Deficient Environments

This paper presents a novel data-driven navigation system to navigate an Unmanned Vehicle (UV) in GPS-denied, feature-deficient environments such as tunnels, or mines. The method utilizes landmarks that vehicle can deploy and measure range from to enable localization as the vehicle traverses its pre-defined path through the tunnel. A key question that arises in such scenario is to estimate and reduce the number of landmarks that needs to be deployed for localization before the start of the mission, given some information about the environment. The main focus is to keep the maximum position uncertainty at a desired value. In this article, we develop a novel vehicle navigation system in GPS-denied, feature-deficient environment by combining techniques from estimation, machine learning, and mixed-integer convex optimization. This article develops a novel, systematic method to perform localization and navigate the UV through the environment with minimum number of landmarks while maintaining desired localization accuracy. We also present extensive simulation experiments on different scenarios that corroborate the effectiveness of the proposed navigation system.

cs.RO↗

arXiv2021

Volumetric Procedural Models for Shape Representation

This article describes a volumetric approach for procedural shape modeling and a new Procedural Shape Modeling Language (PSML) that facilitates the specification of these models. PSML provides programmers the ability to describe shapes in terms of their 3D elements where each element may be a semantic group of 3D objects, e.g., a brick wall, or an indivisible object, e.g., an individual brick. Modeling shapes in this manner facilitates the creation of models that more closely approximate the organization and structure of their real-world counterparts. As such, users may query these models for volumetric information such as the number, position, orientation and volume of 3D elements which cannot be provided using surface based model-building techniques. PSML also provides a number of new language-specific capabilities that allow for a rich variety of context-sensitive behaviors and post-processing functions. These capabilities include an object-oriented approach for model design, methods for querying the model for component-based information and the ability to access model elements and components to perform Boolean operations on the model parts. PSML is open-source and includes freely available tutorial videos, demonstration code and an integrated development environment to support writing PSML programs.

cs.GR↗

arXiv2020

Cooperative Navigation Using Pairwise Communication with Ranging and Magnetic Anomaly Measurements

The problem of cooperative localization for a small group of Unmanned Aerial Vehicles (UAVs) in a GNSS denied environment is addressed in this paper. The presented approach contains two sequential steps: first, an algorithm called cooperative ranging localization, formulated as an Extended Kalman Filter (EKF), estimates each UAV's relative pose inside the group using inter-vehicle ranging measurements; second, an algorithm named cooperative magnetic localization, formulated as a particle filter, estimates each UAV's global pose through matching the group's magnetic anomaly measurements to a given magnetic anomaly map. In this study, each UAV is assumed to only perform a ranging measurement and data exchange with one other UAV at any point in time. A simulator is developed to evaluate the algorithms with magnetic anomaly maps acquired from airborne geophysical survey. The simulation results show that the average estimated position error of a group of 16 UAVs is approximately 20 meters after flying about 180 kilometers in 1 hour. Sensitivity analysis shows that the algorithms can tolerate large variations of velocity, yaw rate, and magnetic anomaly measurement noises. Additionally, the UAV group shows improved position estimation robustness with both high and low resolution maps as more UAVs are added into the group.

eess.SY↗