SUMMARYThis paper describes a distributed coordination scheme with local information exchange for multiple vehicle systems. We introduce second-order consensus protocols that take into account motions of the information states and their derivatives, extending first-order protocols from the literature. We also derive necessary and sufficient conditions under which consensus can be reached in the context of unidirectional information exchange topologies. This work takes into account the general case where information flow may be unidirectional due to sensors with limited fields of view or vehicles with directed, power-constrained communication links. Unlike the first-order case, we show that having a (directed) spanning tree is a necessary rather than a sufficient condition for consensus seeking with second-order dynamics. This work focuses on a formal analysis of information exchange topologies that permit second-order consensus. Given its importance to the stability of the coordinated system, an analysis of the consensus term control gains is also presented, specifically the strength of the information states relative to their derivatives. As an illustrative example, consensus protocols are applied to coordinate the movements of multiple mobile robots.

In this paper, a distributed coordination scheme with local interactions is studied for multiple vehicle systems. We introduce a second-order consensus protocol and derive necessary and/or sufficient conditions under which consensus can be reached in the context of uni-directional interaction topologies. The consensus protocol is then applied to achieve altitude alignment among a team of micro air vehicles as an illustrative example. Nomenclature h Altitude, m λ * Autopilot parameters κ * Autopilot parameters Subscript i Variable number Superscript c Command

AbstractÐReal-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 ªbinaryº 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.

Autopilot systems are capable of reliably following flight plans under normal circumstances, but even the most advanced flight-management systems cannot provide robust response to most anomalous events including in-flight failures. This paper describes an emergency flight-management architecture that can be applied to piloted or autonomous aircraft, with focus on the design and implementation of an adaptive flight planner (AFP) that dynamically adjusts its model to compute feasible flight plans in response to events that degrade aircraft performance. A two-step landing-site selection/trajectory generation process defines safe emergency plans in real time for situations that require landing at an alternate airport. A constraint-based search algorithm selects and prioritizes feasible emergency landing sites, then the AFP synthesizes a segmented trajectory to the best site based on postfailure flight dynamics. The AFP architecture is general for any failure situation; however, operational success is guaranteed only with accurate postfailure performance characterization and a trajectory generation strategy that respects degraded flight envelope boundaries. A real-time segmented trajectory planning algorithm and case study results are presented for total loss of thrust failure scenarios. This emergency is surprisingly common and necessitates an immediate approach and landing without a go-around option.

ative control. Theoretical results regarding consensus-seeking under both time invariant and dynamically changing communication topologies are summarized. Several specific applications of consensus algorithms to multivehicle coordination are described.

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 pixellevel 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 arXiv:1809.07408v2 [cs.CV]

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

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 valuedriven high-bandwidth data capture. The SBB caches shortterm 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.