arXiv subjects

Ella Atkins

Publications and source records attributed to Ella Atkins.

At least 19 recordsLinked to original sources

arXiv2024

Energy Optimal Traversal Between Hover Waypoints for Lift+Cruise Electric Powered Aircraft

Advanced Air Mobility aircraft require energy efficient flight plans to be economically viable. This paper defines minimum energy direct trajectories between waypoints for Lift+Cruise electric Vertical Take-Off and Landing (eVTOL) aircraft. Energy consumption is optimized over accelerated and cruise flight profiles with consideration of mode transitions. Because eVTOL operations start and end in hover for vertical take-off and landing, hover waypoints are utilized. Energy consumption is modeled as a function of airspeed for each flight mode, providing the basis to prove energy optimality for multi-mode traversal. Wind magnitude and direction dictate feasibility of straight-line traversal because Lift+Cruise aircraft point into the relative wind direction while hovering but also have a maximum heading rate constraint. Energy and power use for an experimentally validated QuadPlane small eVTOL aircraft are characterized with respect to airspeed and acceleration in all flight modes. Optimal QuadPlane traversals are presented. Constraints on acceleration and wind are derived for straight-line QuadPlane traversal. Results show an optimal QuadPlane $500m$ traversal between hover waypoints saves $71\%$ energy compared to pure vertical flight traversal for a representative case study with a direct $4m/s$ crosswind. Energy optimal eVTOL direct trajectory definition with transitions to and from hover is novel to this work. Future work should model three-dimensional flight and wind as well as optimize maneuver primitives when required.

cs.RO↗

arXiv2023

The Michigan Robotics Undergraduate Curriculum: Defining the Discipline of Robotics for Equity and Excellence

The Robotics Major at the University of Michigan was successfully launched in the 2022-23 academic year as an innovative step forward to better serve students, our communities, and our society. Building on our guiding principle of "Robotics with Respect" and our larger Robotics Pathways model, the Michigan Robotics Major was designed to define robotics as a true academic discipline with both equity and excellence as our highest priorities. Understanding that talent is equally distributed but opportunity is not, the Michigan Robotics Major has embraced an adaptable curriculum that is accessible through a diversity of student pathways and enables successful and sustained career-long participation in robotics, AI, and automation professions. The results after our planning efforts (2019-22) and first academic year (2022-23) have been highly encouraging: more than 100 students declared Robotics as their major, completion of the Robotics major by our first two graduates, soaring enrollments in our Robotics classes, thriving partnerships with Historically Black Colleges and Universities. This document provides our original curricular proposal for the Robotics Undergraduate Program at the University of Michigan, submitted to the Michigan Association of State Universities in April 2022 and approved in June 2022. The dissemination of our program design is in the spirit of continued growth for higher education towards realizing equity and excellence. The most recent version of this document is also available on Google Docs through this link: https://ocj.me/robotics_major

cs.RO↗

arXiv2023

Can a Laplace PDE Define Air Corridors through Low-Altitude Airspace?

This paper develops a high-density air corridor traffic flow model for Uncrewed Aircraft System (UAS) operation in urban low altitude airspace. To maximize throughput with safe separation guarantees, we define an airspace spatiotemporal planning problem. For the spatial planning, we propose a multi-floor UAS coordination structure divided into a finite number of air corridors safely wrapping buildings and obstacles. We use the USGS Lidar data to map buildings and in turn generate air corridors by modeling UAS coordination as ideal fluid flow with the streamlines obtained by solving the Laplace partial differential equation (PDE). Proper boundary conditions for the differential equations are imposed to direct air corridors along the floors desired motion direction. For temporal planning, we use 4-dimensional path-finding through the corridor network with A* search to maximize airspace usability given each UAS initial and destination waypoint pair.

eess.SY↗

arXiv2023

Investigation of risk-aware MDP and POMDP contingency management autonomy for UAS

Unmanned aircraft systems (UAS) are being increasingly adopted for various applications. The risk UAS poses to people and property must be kept to acceptable levels. This paper proposes risk-aware contingency management autonomy to prevent an accident in the event of component malfunction, specifically propulsion unit failure and/or battery degradation. The proposed autonomy is modeled as a Markov Decision Process (MDP) whose solution is a contingency management policy that appropriately executes emergency landing, flight termination or continuation of planned flight actions. Motivated by the potential for errors in fault/failure indicators, partial observability of the MDP state space is investigated. The performance of optimal policies is analyzed over varying observability conditions in a high-fidelity simulator. Results indicate that both partially observable MDP (POMDP) and maximum a posteriori MDP policies performed similarly over different state observability criteria, given the nearly deterministic state transition model.

cs.RO↗

arXiv2023

Wind Tunnel Testing and Aerodynamic Characterization of a QuadPlane Uncrewed Aircraft System

Electric Vertical Takeoff and Landing (eVTOL) vehicles will open new opportunities in aviation. This paper describes the design and wind tunnel analysis of an eVTOL uncrewed aircraft system (UAS) prototype with a traditional aircraft wing, tail, and puller motor along with four vertical thrust pusher motors. Vehicle design and construction are summarized. Dynamic thrust from propulsion modules is experimentally determined at different airspeeds over a large sweep of propeller angles of attack. Wind tunnel tests with the vehicle prototype cover a suite of hover, transition and cruise flight conditions. Net aerodynamic forces and moments are distinctly computed and compared for plane, quadrotor and hybrid flight modes. Coefficient-based models are developed. Polynomial curve fits accurately capture observed data over all test configurations. To our knowledge, the presented wind tunnel experimental analysis for a multi-mode eVTOL platform is novel. Increased drag and reduced dynamic thrust likely due to flow interactions will be important to address in future designs.

cs.RO↗

arXiv2022

A Finite-State Fixed-Corridor Model for UAS Traffic Management

This paper proposes a physics-inspired solution for low altitude Unmanned Aircraft System (UAS) Traffic Management (UTM) in urban areas. We decompose UTM into spatial and temporal planning problems. For the spatial planning problem, we use the principles of Eulerian continuum mechanics to safely and optimally allocate finite airspace to a UAS. To this end, the finite airspace is partitioned into planned and unplanned subspaces with unplanned subspace(s) or zone(s) enclosing buildings and restricted no-fly regions. The planned subspace is divided into navigable channels that safely wrap unplanned zone(s). We model the airspace planning problem as a Markov Decision Process (MDP) with states defined based on spatial and temporal airspace features and actions authorizing transitions between safe navigable channels. We apply the proposed traffic management solution to plan safe coordination of small UAS in the airspace above downtown Tucson, Arizona.

eess.SY↗

arXiv2022

Quadrotor Formation Flying Resilient to Abrupt Vehicle Failures via a Fluid Flow Navigation Function

This paper develops and experimentally evaluates a navigation function for quadrotor formation flight that is resilient to abrupt quadrotor failures and other obstacles. The navigation function is based on modeling healthy quadrotors as particles in an ideal fluid flow. We provide three key contributions: (i) A Containment Exclusion Mode (CEM) safety theorem and proof which guarantees safety and formally specifies a minimum safe distance between quadrotors in formation, (ii) A real-time, computationally efficient CEM navigation algorithm, (iii) Simulation and experimental algorithm validation. Simulations were first performed with a team of six virtual quadrotors to demonstrate velocity tracking via dynamic slide speed, maintaining sufficient inter-agent distances, and operating in real-time. Flight tests with a team of two custom quadrotors were performed in an indoor motion capture flight facility, successfully validating that the navigation algorithm can handle non-trivial bounded tracking errors while guaranteeing safety.

cs.RO↗

arXiv2021

Development, Implementation, and Experimental Outdoor Evaluation of Quadcopter Controllers for Computationally Limited Embedded Systems

Quadcopters are increasingly used for applications ranging from hobby to industrial products and services. This paper serves as a tutorial on the design, simulation, implementation, and experimental outdoor testing of digital quadcopter flight controllers, including Explicit Model Predictive Control, Linear Quadratic Regulator, and Proportional Integral Derivative. A quadcopter was flown in an outdoor testing facility and made to track an inclined, circular path at different tangential velocities under ambient wind conditions. Controller performance was evaluated via multiple metrics, such as position tracking error, velocity tracking error, and onboard computation time. Challenges related to the use of computationally limited embedded hardware and flight in an outdoor environment are addressed with proposed solutions.

eess.SY↗

arXiv2021

Coupling Intent and Action for Pedestrian Crossing Behavior Prediction

Accurate prediction of pedestrian crossing behaviors by autonomous vehicles can significantly improve traffic safety. Existing approaches often model pedestrian behaviors using trajectories or poses but do not offer a deeper semantic interpretation of a person's actions or how actions influence a pedestrian's intention to cross in the future. In this work, we follow the neuroscience and psychological literature to define pedestrian crossing behavior as a combination of an unobserved inner will (a probabilistic representation of binary intent of crossing vs. not crossing) and a set of multi-class actions (e.g., walking, standing, etc.). Intent generates actions, and the future actions in turn reflect the intent. We present a novel multi-task network that predicts future pedestrian actions and uses predicted future action as a prior to detect the present intent and action of the pedestrian. We also designed an attention relation network to incorporate external environmental contexts thus further improve intent and action detection performance. We evaluated our approach on two naturalistic driving datasets, PIE and JAAD, and extensive experiments show significantly improved and more explainable results for both intent detection and action prediction over state-of-the-art approaches. Our code is available at: https://github.com/umautobots/pedestrian_intent_action_detection.

cs.CV↗

arXiv2021

Prognostics-Informed Battery Reconfiguration in a Multi-Battery Small UAS Energy System

Batteries have been identified as one most likely small UAS (sUAS) components to fail in flight. sUAS safety will therefore be improved with redundant or backup batteries. This paper presents a prognostics-informed Markov Decision Process (MDP) model for managing multi-battery reconfiguration for sUAS missions. Typical lithium polymer (Lipo) battery properties are experimentally characterized and used in Monte Carlo simulations to establish battery dynamics in sUAS flights of varying duration. Case studies illustrate the trade off between multi-battery system increased complexity/weight and resilience to non-ideal battery performance.

cs.RO↗

arXiv2021

Smart Black Box 2.0: Efficient High-bandwidth Driving Data Collection based on Video Anomalies

Autonomous vehicles require fleet-wide data collection for continuous algorithm development and validation. The Smart Black Box (SBB) intelligent event data recorder has been proposed as a system for prioritized high-bandwidth data capture. This paper extends the SBB by applying anomaly detection and action detection methods for generalized event-of-interest (EOI) detection. An updated SBB pipeline is proposed for the real-time capture of driving video data. A video dataset is constructed to evaluate the SBB on real-world data for the first time. SBB performance is assessed by comparing the compression of normal and anomalous data and by comparing our prioritized data recording with a FIFO strategy. Results show that SBB data compression can increase the anomalous-to-normal memory ratio by ~25%, while the prioritized recording strategy increases the anomalous-to-normal count ratio when compared to a FIFO strategy. We compare the real-world dataset SBB results to a baseline SBB given ground-truth anomaly labels and conclude that improved general EOI detection methods will greatly improve SBB performance.

eess.SP↗

arXiv2020

BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation

Pedestrian trajectory prediction is an essential task in robotic applications such as autonomous driving and robot navigation. State-of-the-art trajectory predictors use a conditional variational autoencoder (CVAE) with recurrent neural networks (RNNs) to encode observed trajectories and decode multi-modal future trajectories. This process can suffer from accumulated errors over long prediction horizons (>=2 seconds). This paper presents BiTraP, a goal-conditioned bi-directional multi-modal trajectory prediction method based on the CVAE. BiTraP estimates the goal (end-point) of trajectories and introduces a novel bi-directional decoder to improve longer-term trajectory prediction accuracy. Extensive experiments show that BiTraP generalizes to both first-person view (FPV) and bird's-eye view (BEV) scenarios and outperforms state-of-the-art results by ~10-50%. We also show that different choices of non-parametric versus parametric target models in the CVAE directly influence the predicted multi-modal trajectory distributions. These results provide guidance on trajectory predictor design for robotic applications such as collision avoidance and navigation systems.

cs.CV↗

arXiv2020

Polylidar3D -- Fast Polygon Extraction from 3D Data

Flat surfaces captured by 3D point clouds are often used for localization, mapping, and modeling. Dense point cloud processing has high computation and memory costs making low-dimensional representations of flat surfaces such as polygons desirable. We present Polylidar3D, a non-convex polygon extraction algorithm which takes as input unorganized 3D point clouds (e.g., LiDAR data), organized point clouds (e.g., range images), or user-provided meshes. Non-convex polygons represent flat surfaces in an environment with interior cutouts representing obstacles or holes. The Polylidar3D front-end transforms input data into a half-edge triangular mesh. This representation provides a common level of input data abstraction for subsequent back-end processing. The Polylidar3D back-end is composed of four core algorithms: mesh smoothing, dominant plane normal estimation, planar segment extraction, and finally polygon extraction. Polylidar3D is shown to be quite fast, making use of CPU multi-threading and GPU acceleration when available. We demonstrate Polylidar3D's versatility and speed with real-world datasets including aerial LiDAR point clouds for rooftop mapping, autonomous driving LiDAR point clouds for road surface detection, and RGBD cameras for indoor floor/wall detection. We also evaluate Polylidar3D on a challenging planar segmentation benchmark dataset. Results consistently show excellent speed and accuracy.

cs.CV↗

arXiv2020

Polylidar -- Polygons from Triangular Meshes

This paper presents Polylidar, an efficient algorithm to extract non-convex polygons from 2D point sets, including interior holes. Plane segmented point clouds can be input into Polylidar to extract their polygonal counterpart, thereby reducing map size and improving visualization. The algorithm begins by triangulating the point set and filtering triangles by user configurable parameters such as triangle edge length. Next, connected triangles are extracted into triangular mesh regions representing the shape of the point set. Finally each region is converted to a polygon through a novel boundary following method which accounts for holes. Real-world and synthetic benchmarks are presented to comparatively evaluate Polylidar speed and accuracy. Results show comparable accuracy and more than four times speedup compared to other concave polygon extraction methods.

cs.CG↗

arXiv2020

When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos

Video anomaly detection (VAD) has been extensively studied. However, research on egocentric traffic videos with dynamic scenes lacks large-scale benchmark datasets as well as effective evaluation metrics. This paper proposes traffic anomaly detection with a \textit{when-where-what} pipeline to detect, localize, and recognize anomalous events from egocentric videos. We introduce a new dataset called Detection of Traffic Anomaly (DoTA) containing 4,677 videos with temporal, spatial, and categorical annotations. A new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA. State-of-the-art methods are benchmarked for two VAD-related tasks.Experimental results show STAUC is an effective VAD metric. To our knowledge, DoTA is the largest traffic anomaly dataset to-date and is the first supporting traffic anomaly studies across when-where-what perspectives. Our code and dataset can be found in: https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly

cs.CV↗

arXiv2019

An Integrative Data-Driven Physics-Inspired Approach to Traffic Congestion Control

This paper offers an integrative data-driven physics-inspired approach to model and control traffic congestion in a resilient and efficient manner. While existing physics-based approaches commonly assign density and flow traffic states by using the Fundamental Diagram, this paper specifies the flow-density relation using past traffic information recorded in a time sliding window with a constant horizon length. With this approach, traffic coordination trends can be consistently learned and incorporated into traffic planning. This paper also models traffic coordination as a probabilistic process and obtains traffic feasibility conditions using linear temporal logic. Model productive control (MPC) is applied to control traffic congestion through the boundary of the traffic network. Therefore, the optimal boundary inflow is assigned as the solution of a constrained quadratic programming problem.

eess.SY↗

arXiv2019

Resilient Continuum Deformation Coordination

This paper applies the principles of continuum mechanics to safely and resiliently coordinate a multi-agent team. A hybrid automation with two operation modes, Homogeneous Deformation Mode (HDM) and Containment Exclusion Mode (CEM), are developed to robustly manage group coordination in the presence of unpredicted agent failures. HDM becomes active when all agents are healthy, where the group coordination is defined by homogeneous transformation coordination functions. By classifying agents as leaders and followers, a desired n-D homogeneous transformation is uniquely related to the desired trajectories of n+1 leaders and acquired by the remaining followers in real-time through local communication. The paper offers a novel approach for leader selection as well as naturally establishing and reestablishing inter-agent communication whenever the agent team enters the HDM. CEM is activated when at least one agent fails to admit group coordination. This paper applies unique features of decentralized homogeneous transformation coordination to quickly detect each arising anomalous situation and excludes failed agent(s) from group coordination of healthy agents. In CEM, agent coordination is treated as an ideal fluid flow where the desired agents' paths are defined along stream lines inspired by fluid flow field theory to circumvent exclusion spaces surrounding failed agent(s).

eess.SY↗

arXiv2019

Nailed It: Autonomous Roofing with a Nailgun-Equipped Octocopter

This paper presents the first demonstration of autonomous roofing with a multicopter. A DJI S1000 octocopter equipped with an off-the-shelf nailgun and an adjustableslope roof mock-up were used. The nailgun was modified to allow triggering from the vehicle and tooltip compression feedback. A mount was designed to adjust the angle to match representative roof slopes. An open-source octocopter autopilot facilitated controller adaptation for the roofing application. A state machine managed autonomous nailing sequences using smooth trajectories designed to apply prescribed contact forces for reliable nail deployment. Experimental results showed that the system is capable of nailing within a required three centimeter gap on the shingle. Extensions to achieve a complete autonomous roofing system are discussed as future work.

cs.RO↗