In this paper, we document a design, implementation, and field tests of a vehicle-to-vehicle (V2V) communication-enabled rail collision avoidance system (RCAS) for urban light rail vehicles---trams. The RCAS runs onboard a tram and issues an acoustic warning to a tram driver if a collision with another tram is imminent---no commands to the braking subsystem are issued in the current version. The prediction of an imminent collision with another tram is based on real-time evaluation of predicted trajectories of both trams. The predictions are based on mathematical models of the longitudinal dynamics of the vehicles and real-time estimation of the current motion states (position and velocity). The information about the other tram's predicted trajectory is accessed through V2V communication. We also document the results of verification of the functionality of the proposed RCAS through several field tests with a real tram.
Transit network simulation models are often used for performance and retrospective analysis of urban rail systems, taking advantage of the availability of extensive automated fare collection (AFC) and automated vehicle location (AVL) data. Important inputs to such models, in addition to origin-destination flows, include passenger path choices and train capacity. Train capacity, which has often been overlooked in the literature, is an important input that exhibits a lot of variabilities. The paper proposes a simulation-based optimization (SBO) framework to simultaneously calibrate path choices …
In order to ensure the personal safety of the drivers and passengers of rail transit in plateau environment, the vital signs and train conditions of the drivers and passengers are taken as the research object, and the dynamic relationship between them is studied and analyzed. In this paper, subway drivers under normal operation conditions are taken as research objects to establish the vital signs monitoring and early warning system. The vital signs data of the subway drivers, such as heart rate (HR), respiratory rate (RR), body temperature (T) and blood oxygen saturation (SPO2) of the subway d…
Accurate short-term passenger flow prediction in urban rail transit stations has great benefits for reasonably allocating resources, easing congestion, and reducing operational risks. However, compared with data-rich stations, the passenger flow prediction in newly-operated stations is limited by passenger flow data volume, which would reduce the prediction accuracy and increase the difficulty for station management and operation. Hence, how accurately predicting passenger flow in newly-operated stations with limited data is an urgent problem to be solved. Existing passenger flow prediction ap…
University of Pennsylvania（宾夕法尼亚大学）；University of California, Berkeley（加州大学伯克利分校）；Oregon State University（俄勒冈州立大学）
With increasing urban population, there is global interest in Urban Air Mobility (UAM), where hundreds of autonomous Unmanned Aircraft Systems (UAS) execute missions in the airspace above cities. Unlike traditional human-in-the-loop air traffic management, UAM requires decentralized autonomous approaches that scale for an order of magnitude higher aircraft densities and are applicable to urban settings. We present Learning-to-Fly (L2F), a decentralized on-demand airborne collision avoidance framework for multiple UAS that allows them to independently plan and safely execute missions with spati…
This article examines a symbolic numerical approach to optimize a vehicle's track for autonomous driving and collision avoidance. The new approach uses the classical cost function definition incorporating the essential aspects of the dynamic state of the vehicle as position, orientation, time sampling, and constraints on slip angles of tires. The optimization processes minimize the cost function and simultaneously determine the optimal track by varying steering and breaking amplitudes. The current velocity of the vehicle is limited to a maximal velocity, thus, allowing a stable search of the o…
University of Pennsylvania（宾夕法尼亚大学）；University of California, Berkeley（加州大学伯克利分校）；Oregon State University（俄勒冈州立大学）
Urban Air Mobility, the scenario where hundreds of manned and Unmanned Aircraft System (UAS) carry out a wide variety of missions (e.g. moving humans and goods within the city), is gaining acceptance as a transportation solution of the future. One of the key requirements for this to happen is safely managing the air traffic in these urban airspaces. Due to the expected density of the airspace, this requires fast autonomous solutions that can be deployed online. We propose Learning-'N-Flying (LNF) a multi-UAS Collision Avoidance (CA) framework. It is decentralized, works on-the-fly and allows a…
In this paper, we document design and a prototype implementation of a computational method for an onboard prediction of a breaking distance for a city rail vehicle|a tram. The method is based on an onboard simulation of tram braking dynamics. Inputs to this simulation are the data from a digital map and the estimated (current) position and speed, which are, in turn, estimated by combining a mathematical model of dynamics of a tram with the measurements from a GNSS/GPS receiver, an accelerometer and the data from a digital map. Experiments with real trams verify the functionality, but reliable …
Trajectory Optimization for UAV-Based Medical Delivery with Temporal Logic Constraints and Convex Feasible Set Collision Avoidance
State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Vanke School of Public Health（万科公共卫生学院）；School of Automation（自动化学院）
ARCAS: An Augmented Reality Collision Avoidance System with SLAM-Based Tracking for Enhancing VRU Safety
Department of Civil, Architectural, and Environmental Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校土木、建筑与环境工程系）；School of Architecture, The University of Texas at Austin（德克萨斯大学奥斯汀分校建筑学院）
