This paper presents a three-dimensional discrete search path planner for fixed-wing aircraft emergency landing planning that manages state-space complexity by incorporating cost gradients to assure descent flight path angle and runway heading alignment constraints are met. Our approach incorporates steady wind and maximizes margin from flight envelope boundaries to accommodate wind variation in a manner commensurate with a loss of thrust condition. A novel multi-objective cost function that combines gradient-based path guidance and population risk metrics is implemented to efficiently enable discrete search to find a robust solution. The proposed method is demonstrated through use cases with population data for a region of Long Island, New York that highlight our algorithm's effectiveness.

This paper proposes a fluid-flow-inspired solution for low altitude Uncrewed 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 airspace to a UAS. To this end, the finite airspace is partitioned into keep-in and keep-out subspaces with keep-out subspace(s) or zone(s) enclosing buildings and restricted no-fly regions. The keep-in subspace is divided into navigable channels that safely wrap keep-out zone(s). We define the airspace planning problem with a Dynamic Programming (DP) formulation in which states are defined based on spatial and temporal airspace features and actions denote transitions between safe navigable channels. We apply the proposed traffic management solution to enable safe coordination of multiple small UAS at low-altitude airspace populated with buildings of varied footprints and heights.

Aerial manipulation describes a process that includes physical interaction between an unmanned aircraft system (UAS) and its environment. We aim to apply aerial manipulation to sample leaves and small branches from rain forest trees. Current approaches to aerial manipulation involve extended periods of UAS-environment interaction, during which forces and moments can lead to a loss in attitude or position control in underactuated multicopters. By adapting intelligent foot placement strategies found in dynamically stable hopping robots, this work proposes a strategy involving carefully managed intentional collisions between the UAS and its environment. We designed an attitude controller denoted a Velocity Matching controller that aligns a UAS-mounted pogo-stick foot with the center of mass velocity vector during collision approach to maximize UAS ability to recover a hover state after collision. We propose the use of a flight envelope involving altitude and horizontal speed states to assess recoverability prior to initiating each approach to collision. We identify this flight envelope from a simulation study built on a model of flight in Conventional Waypoint Following and Velocity Matching control modes as well as a model of collision response. Experimental flight testing evaluates the simulation-based envelope resulting in an actual envelope that is somewhat smaller but similarly shaped to the envelope identified in simulation.

Video anomaly detection (VAD) has been extensively studied for static cameras but is much more challenging in egocentric driving videos where the scenes are extremely dynamic. This paper proposes an unsupervised method for traffic VAD based on future object localization. The idea is to predict future locations of traffic participants over a short horizon, and then monitor the accuracy and consistency of these predictions as evidence of an anomaly. Inconsistent predictions tend to indicate an anomaly has occurred or is about to occur. To evaluate our method, we introduce a new large-scale benchmark dataset called Detection of Traffic Anomaly (DoTA)containing 4,677 videos with temporal, spatial, and categorical annotations. We also propose a new VAD evaluation metric, called spatial-temporal area under curve (STAUC), and show that it captures how well a model detects both temporal and spatial locations of anomalies unlike existing metrics that focus only on temporal localization. Experimental results show our method outperforms state-of-the-art methods on DoTA in terms of both metrics. We offer rich categorical annotations in DoTA to benchmark video action detection and online action detection methods. The DoTA dataset has been made available at: https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly.

Motivated by the need for simulation tools for testing, verification and validation of autonomous driving systems that operate in traffic consisting of both autonomous and human-driven vehicles, we propose a game-theoretic framework for modeling the interactive behavior of vehicles at uncontrolled intersections. The proposed vehicle interaction model is based on a novel formulation of dynamic games with multiple concurrent leader-follower pairs, induced from common traffic rules. Based on simulation results for various intersection scenarios, we show that the model exhibits reasonable behavior expected in traffic, including the capability of reproducing scenarios extracted from real-world traffic data and reasonable performance in resolving traffic conflicts. The model is further validated based on the level-of-service traffic quality rating system and demonstrates manageable computational complexity compared to traditional multi-player game-theoretic models.

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

The COVID-19 global pandemic has significantly impacted people throughout the United States and the World. While it was initially believed the virus was transmitted from animal to human, person-to-person transmission is now recognized as the main source of community spread. This article integrates data into physics-based models to analyze stability of the rapid COVID-19 growth and to obtain a data-driven model for spread dynamics among the human population. The proposed mass-conservation model is used to learn the parameters of pandemic growth and to predict the growth of total cases, deaths, and recoveries over a finite future time horizon. The proposed finite-time prediction model is validated by finite-time estimation of the total numbers of infected cases, deaths, and recoveries in the United States from March 12, 2020 to December 9, 2020.

Random mobility models (RMMs) capture the random mobility patterns of mobile agents, and have been widely used as the modeling framework for the evaluation and design of mobile networks. All existing RMMs in the literature assume independent movements of mobile agents, which does not hold for unmanned aircraft systems (UASs). In particular, UASs must maintain a safe separation distance to avoid collision. In this paper, we propose a new modeling framework of random mobility models equipped with physical sense-and-avoid protocols to capture the flexible, variable, and uncertain movement patterns of UASs subject to separation safety constraints. For the random direction (RD) RMM equipped with a commonly used sense-and-avoid (S&A) protocol, named sense-and-stop (S&S), we provide its statistical properties including stationary location distribution and stationary inter-vehicle distance distribution, using the Markov analysis. This study provides knowledge on the impact of S&A protocols to critical UAS networking statistics. In addition, we define collision probabilities and airspace capacity concepts for UASs based on the inter-vehicle distance distribution, and derive their closed-form expressions. This analytical framework mathematically bridges local autonomy with global airspace capacity, and allows the impact analysis of local autonomy configurations for effective UAS airspace capacity management.

Before Unmanned Aircraft Systems (UAS) can be widely deployed over complex terrain and urban regions, a methodology is needed to deconflict and track UAS flights. This paper presents a formal geofence definition and a methodology to use geofences to temporally and spatially organize the airspace in support of a UAS Traffic Management (UTM) system. Algorithms are presented to temporally and spatially deconflict requested geofences from existing approved geofences in the UTM system. A case study shows how deconflicted geofences impact UAS flight.

Advances of unmanned aircraft system (UAS) technology have spurred a rapid investment of commercial UAS use in broad public domains, such as cargo transport, agriculture support, emergency response, on-demand communication, and infrastructure health monitoring. Urban unmanned aerial transportation that can transport passengers over short distances is also on the way. With the forthcoming dense operations of UAS particularly over urban regions, ensuring airspace safety becomes an urgent issue.

Autonomous vehicles require reliable and resilient sensor suites and ongoing validation through fleet-wide data collection. This paper proposes a Smart Black Box (SBB) to augment traditional low-bandwidth data logging with value-driven high-bandwidth data capture. The SBB caches short-term histories of data as buffers through a deterministic Mealy machine based on data value and similarity. Compression quality for each frame is determined by optimizing the trade-off between value and storage cost. With finite storage, prioritized data recording discards low-value buffers to make room for new data. This paper formulates SBB compression decision making as a constrained multi-objective optimization problem with novel value metrics and filtering. The SBB has been evaluated on a traffic simulator which generates trajectories containing events of interest (EOIs) and corresponding first-person view videos. SBB compression efficiency is assessed by comparing storage requirements with different compression quality levels and event capture ratios. Performance is evaluated by comparing results with a traditional first-in-first-out (FIFO) recording scheme. Deep learning performance on images recorded at different compression levels is evaluated to illustrate the reproducibility of SBB recorded data.

This paper describes a Markov decision process approach to a robust spacecraft mission control policy that maximizes the expected value of science reward assuming a circular orbit. The control policy that governs mission steps can be computed off-board or onboard depending upon the availability of communication bandwidth and on-board computational resources. This paper considers a sample science mission, where the spacecraft collects data from celestial objects viewable only within a certain orbit true anomaly window. Science data collection requires the spacecraft to slew its instrument(s) toward each target, and continue pointing in the direction of the target while the spacecraft traverses its orbit. Robustness and stochastic optimization of scientific reward, is achieved at the cost of computational complexity. Approximate dynamic programming (ADP) is exploited to reduce the computational time and effort to manageable levels and to treat larger problem sizes. The proposed ADP algorithm partitions the state-space based on true anomaly regions, enabling grouping of adjacent science targets. Results of a simulation case study demonstrate that our proposed ADP approach performs quite well for reasonable ranges of key problem parameters.

Predicting the future location of vehicles is essential for safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous driving. This paper introduces a novel approach to simultaneously predict both the location and scale of target vehicles in the first-person (egocentric) view of an ego-vehicle. We present a multi-stream recurrent neural network (RNN) encoder-decoder model that separately captures both object location and scale and pixel-level observations for future vehicle localization. We show that incorporating dense optical flow improves prediction results significantly since it captures information about motion as well as appearance change. We also find that explicitly modeling future motion of the ego-vehicle improves the prediction accuracy, which could be especially beneficial in intelligent and automated vehicles that have motion planning capability. To evaluate the performance of our approach, we present a new dataset of first-person videos collected from a variety of scenarios at road intersections, which are particularly challenging moments for prediction because vehicle trajectories are diverse and dynamic. Code and dataset have been made available at: https://usa.honda-ri.com/hevi.

Recognizing abnormal events such as traffic violations and accidents in natural driving scenes is essential for successful autonomous driving and advanced driver assistance systems. However, most work on video anomaly detection suffers from two crucial drawbacks. First, they assume cameras are fixed and videos have static backgrounds, which is reasonable for surveillance applications but not for vehicle-mounted cameras. Second, they pose the problem as one-class classification, relying on arduously hand-labeled training datasets that limit recognition to anomaly categories that have been explicitly trained. This paper proposes an unsupervised approach for traffic accident detection in first-person (dashboard-mounted camera) videos. Our major novelty is to detect anomalies by predicting the future locations of traffic participants and then monitoring the prediction accuracy and consistency metrics with three different strategies. We evaluate our approach using a new dataset of diverse traffic accidents, AnAn Accident Detection (A3D), as well as another publicly-available dataset. Experimental results show that our approach outperforms the state-of-the-art. Code and the dataset developed in this work are available at: https:llgithub.comlMoonBtvdltad-IROS2019.

We have recently applied the principles of continuum mechanics to develop a new leader-follower model for the collective motion of a multiagent system (MAS). Agents are modeled as particles of a continuum body that can deform in Rn (n = 1, 2, 3) under a specific class of mappings, called the homogeneous transformation. This paper shows how a desired homogeneous deformation is uniquely specified based on the trajectories chosen by p +1 (p ≤ n) leaders, and it is acquired by the remaining agents, called followers, through local communication. Under this setup, every follower interacts with p + 1 local agents with fixed communication weights that are uniquely determined based on the initial positions of the agents. Although asymptotic convergence of the agents' transient positions to the desired final positions (prescribed by a homogeneous transformation) can be assured by applying the proposed paradigm, follower agents deviate from the desired positions during evolution. The main objective of this paper is to assure that the transient error, the difference between the actual and desired positions of each follower, converges to zero during evolution. For this purpose, each leader chooses a time-dependent polynomial vector of order (h -1) (h ∈ N) for its trajectory connecting two consecutive way points, and each follower applies continuous time or discrete time linear time invariant dynamics to update its state based on the states of p + 1 local agents. The second objective of this paper is to develop a paradigm for the homogeneous deformation of an MAS that is robust to communication failure. For this purpose, we will show how followers can acquire desired positions prescribed by a homogeneous mapping to preserve volumetric ratios under either fixed or switching communication topologies, where there is no restriction on the number of the agents, if every follower communicates with mi ≥ p + 1 local agents. In addition, agents' collective motion can be stably continued even if some followers give up communication with other agents at some time during evolution.

This paper investigates a comfort-based route planner that considers both travel time and ride comfort. We first present a framework of simultaneous road profile estimation and anomaly detection with commonly available vehicle sensors. A jump-diffusion process-based state estimator is developed and used along with a multi-input observer for road profile estimation. The estimation framework is evaluated in an experimental test vehicle and promising performance is demonstrated. Second, three objective comfort metrics are developed based on factors such as travel time, road roughness, road anomaly, and intersection. A comfort-based route planning problem is then formulated with these metrics and an extended Dijkstra's algorithm is exploited to solve the problem. A cloud-based implementation of our comfort-based route planning approach is proposed to facilitate information access and fast computation. Finally, a real-world case study, comfort-based route planning from Ford Research and Innovation Center, Michigan to Ford Rouge Factory Tour, Michigan, is presented to illustrate the efficacy of the proposed route planning framework.

This paper considers a new clustering algorithm for processing time-evolving road anomaly reports. Two cluster categories, main and outlier, are defined to deal with outliers as well as to capture the evolving nature of road anomalies. The Mahalanobis distance is exploited to quantify the similarity between a new report and the existing clusters. The clusters are maintained online and the Woodbury matrix inverse lemma is used for their recursive updates. The proposed clustering algorithm can localize isolated anomalies and compress information for densely distributed anomalies. A simulation is presented to demonstrate the efficacy of the proposed algorithm.

Loss of Control (LOC) is the most common precursor to aircraft accidents. This paper presents a Flight Safety Assessment and Management (FSAM) decision system to reduce in-flight LOC risk. FSAM nominally serves as a monitor to detect conditions that pose LOC risk, automatically activating the appropriate control authority if necessary to prevent LOC and restore a safe operational state. This paper contributes an efficient Markov Decision Process (MDP) formulation for FSAM. The state features capture risk associated with aircraft dynamics, configuration, health, pilot behavior and weather. The reward function trades cost of inaction against the cost of overriding the current control authority. A sparse sampling algorithm obtains a near-optimal solution for the MDP online. This approach enables the FSAM MDP to incorporate dynamically changing flight envelope and environment constraints into decision-making. Case studies based on realworld aviation incidents are presented.

This paper presents a safety-based route planner that exploits vehicle-to-cloud-to-vehicle (V2C2V) connectivity. Time and road risk index (RRI) are considered as metrics to be balanced based on user preference. To evaluate road segment risk, a road and accident database from the highway safety information system is mined with a hybrid neural network model to predict RRI. Real-time factors such as time of day, day of the week, and weather are included as correction factors to the static RRI prediction. With real-time RRI and expected travel time, route planning is formulated as a multiobjective network flow problem and further reduced to a mixed-integer programming problem. A V2C2V implementation of our safety-based route planning approach is proposed to facilitate access to real-time information and computing resources. A real-world case study, route planning through the city of Columbus, Ohio, is presented. Several scenarios illustrate how the "best" route can be adjusted to favor time versus safety metrics.

We propose the application of state-space techniques to develop a novel coupled cyber-physical system (CPS) model and use feedback control to dynamically adjust CPS resource use and performance. We investigate the use of a gain scheduled discrete linear quadratic regulator controller and a forward-propagation Riccati-based controller to handle the discrete-time-varying system. We demonstrate the value of our approach by conducting a disturbance-rejection case study for a small satellite (CubeSat) application in which resources required for attitude control are adjusted in real-time to maximize availability for other computational tasks. We evaluate CPS performance through a set of metrics quantifying physical system error and control effort as well as cyber resource utilization and compare these with traditional fixed-rate optimal control strategies. Results indicate that our proposed coupled CPS model and controller can provide physical system performance similar to fixed-rate optimal control strategies but with less control effort and much less computational utilization.

This paper proposes a novel multi-objective route planning approach within the framework of a Vehicle-to-Cloud-to-Vehicle (V2C2V) architecture. Time and road risk index (RRI) are both considered as metrics. To evaluate road segment risk, an accident database from the Highway Safety Information System (HSIS) is processed to build a comprehensive road risk assessment model. Route planning is formulated as a multi-objective network flow problem and further reduced to a Mixed Integer Programming (MIP) problem. A real-world case study, route planning through the city of Columbus, Ohio, is presented. The Vehicle-to-Cloud-to-Vehicle (V2C2V) based implementation of our safety-based route planning approach is proposed to facilitate access to real-time information and computing resources.

Cyber-physical system (CPS) research aims to integrate physical and computational models in a manner that outperforms a system in which the two models are kept separate. CPSs can be generated by either folding properties of the physics-based system into a discrete modeling paradigm or vice versa. This paper studies the latter by abstracting execution rate of a real-time feedback control task into a continuous state-space form traditionally employed for physics-based systems. We propose coupling the two models in a linear systems framework and study the impact of this coupling applied to a single degree of freedom second-order oscillator as well as an unstable inverted pendulum, both regulated with an appropriately designed linear quadratic regulator (LQR). Our results illustrate the utility of the proposed abstraction and controller design as a means of coregulating cyber and physical states in real time.

This field of target tracking is relatively mature when the camera is stationary but the moving sensor poses uniquely challenging problems because relative to the camera, everything in the scene appears to be moving. This report will present a robust and efficient video stabilization algorithm based on the scale invariant feature transform (SIFT) algorithm and global registration. An important comparison will be made to KLT, a widely used feature based tracker, stabilization algorithms. We will demonstrate KLT's deficiencies and SIFT's advantages when confronted with limited features and 3D structures. Finally an implementation of the overall system with real data provided by UAV's from MRLets Technologies Inc will be described and analyzed.

This paper formulates and illustrates the integration of resource safety verification into a design methodology for development of verified and robust real-time embedded systems. Resource-related concerns are not closely linked with current xUML model-based software development although they are critical for embedded systems. We describe how to integrate resource analysis techniques into the early phase of an xUML-based development cycle. Our hybrid framework for resource safety verification combines static resource analysis and runtime monitoring. A case study based on an embedded controller for satellite simulation, TableSat, illustrates the benefits obtained by incorporating resource verification into design and combining static analysis and runtime monitoring.

Real-time middleware services must guarantee predictable performance under specified load and failure conditions, and ensure graceful degradation when these conditions are violated. Guaranteed predictable performance typically entails reservation of resources and use of admission control. Graceful degradation, on the other hand, requires dynamic reallocation of resources to maximize the application-perceived system utility while coping with unanticipated overload and failures. We propose a model for quality-of-service (QoS) negotiation in building real-time services to meet both of the above requirements. QoS negotiation is shown to 1) outperform "binary" admission control schemes (either guaranteeing the required QoS or rejecting the service request), 2) achieve higher application-perceived system utility, and 3) deal with violations of the load and failure hypotheses. We incorporated the proposed QoS-negotiation model into an example real-time middleware service, called RTPOOL, which manages a distributed pool of shared computing resources (processors) to guarantee timeliness QoS for real-time applications. In order to guarantee timeliness QoS, the resource pool is encapsulated with its own schedulability analysis, admission control, and load-sharing support. This support differs from others in that it adheres to the proposed QoS-negotiation model. The efficacy and power of QoS negotiation are demonstrated for an automated flight control system implemented on a network of PCs running RTPOOL. This system is used to fly an F-16 fighter aircraft modeled using the Aerial Combat (ACM) F-16 Flight Simulator. Experimental results indicate that QoS negotiation, while maintaining real-time guarantees, enables graceful QoS degradation under conditions in which traditional schedulability analysis and admission control schemes fail.