An official website of the United States government
Data-driven driving safety assessment is crucial in understanding the insights of traffic accidents caused by dangerous driving behaviors. Meanwhile, quantifying driving safety through well-defined metrics in real-world naturalistic driving data is also an important step for the operational safety assessment of automated vehicles (AV). However, the lack of flexible data acquisition methods and fine-grained datasets has hindered progress in this critical area. In response to this challenge, we propose a novel dataset for driving safety metrics analysis specifically tailored to car-following situations. Leveraging state-of-the-art Artificial Intelligence (AI) technology, we employ drones to capture high-resolution video data at 12 traffic scenes in the Phoenix metropolitan area. After that, we developed advanced computer vision algorithms and semantically annotated maps to extract precise vehicle trajectories and leader-follower relations among vehicles. These components, in conjunction with a set of defined metrics based on our prior work on Operational Safety Assessment (OSA) by the Institute of Automated Mobility (IAM), allow us to conduct a detailed analysis of driving safety. Our results reveal the distribution of these metrics under various real-world car-following scenarios and characterize the impact of different parameters and thresholds in the metrics. By enabling a data-driven approach to address driving safety in car-following scenarios, our work can empower traffic operators and policymakers to make informed decisions and contribute to a safer, more efficient future for road transportation systems.
more »
« less
Containerization Approach for High-Fidelity Terramechanics Simulations
Integrated modeling of vehicle, tire and terrain is a fundamental challenge to be addressed for off-road autonomous navigation. The complexities arise due to lack of tools and techniques to predict the continuously varying terrain and environmental conditions and the resultant non-linearities. The solution to this challenge can now be found in the plethora of data driven modeling and control techniques that have gained traction in the last decade. Data driven modeling and control techniques rely on the system’s repeated interaction with the environment to generate a lot of data and then use a function approximator to fit a model for the physical system with the data. Getting good quality and quantity of data may involve extensive experimentation with the physical system impacting developer’s resource. The process is computationally expensive, and the overhead time required is high.High-fidelity simulators coupled with cloud-based containers can help ease the challenge of data ‘quality’ and ‘quantity’. Project Chrono is a multi-physics simulation engine that provides high-fidelity simulation capabilities with emphasis on flow and terrain modeling. With a host of libraries and APIs for industry accepted tools like MATLAB, Simulink and TensorFlow, Project Chrono proves to be a powerful research bed for data-driven modeling and control development for off-road navigation. Containers are lightweight virtual machines that take away repetitive configurations by setting up a computational environment, including all necessary dependencies and libraries. Docker encapsulates an end-to-end platform solution for heavy computation challenges of deep learning applications and allows fast development and testing. The synergy between the high-fidelity simulator and the compute outsourcing capabilities of cloud-based containers proves to be extremely beneficial for continuous integration and continuous deployment (CI/CD) for data driven modeling and control tasks. In the following work, we containerize a high-fidelity simulator (Project Chrono) to develop and validate data driven modeling and control algorithms for off-road autonomous navigation.
more »
« less
- PAR ID:
- 10489454
- Publisher / Repository:
- SAE Mobilus
- Date Published:
- Format(s):
- Medium: X
- Location:
- Detroit, Michigan, United States
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Ensuring the safety of vulnerable road users (VRUs) such as pedestrians, users of micro-mobility vehicles, and cyclists is imperative for the commercialization of automated vehicles (AVs) in urban traffic scenarios. City traffic intersections are of particular concern due to the precarious situations VRUs often encounter when navigating these locations, primarily because of the unpredictable nature of urban traffic. Earlier work from the Institute of Automated Vehicles (IAM) has developed and evaluated Driving Assessment (DA) metrics for analyzing car following scenarios. In this work, we extend those evaluations to an urban traffic intersection testbed located in downtown Tempe, Arizona. A multimodal infrastructure sensor setup, comprising a high-density, 128-channel LiDAR and a 720p RGB camera, was employed to collect data during the dusk period, with the objective of capturing data during the transition from daylight to night. In this study, we present and empirically assess the benefits of high-density LiDAR in low-light and dark conditions—a persistent challenge in VRU detection when compared to traditional RGB traffic cameras. Robust detection and tracking algorithms were utilized for analyzing VRU-to-vehicle and vehicle-to-vehicle interactions using the LiDAR data. The analysis explores the effectiveness of two DA metrics based on the i.e. Post Encroachment Time (PET) and Minimum Distance Safety Envelope (MDSE) formulations in identifying potentially unsafe scenarios for VRUs at the Tempe intersection. The codebase for the data pipeline, along with the high-density LiDAR dataset, has been open-sourced with the goal of benefiting the AV research community in the development of new methods for ensuring safety at urban traffic intersections.more » « less
-
Abstract We describe a simulation environment that enables the design and testing of control policies for off-road mobility of autonomous agents. The environment is demonstrated in conjunction with the training and assessment of a reinforcement learning policy that uses sensor fusion and interagent communication to enable the movement of mixed convoys of human-driven and autonomous vehicles. Policies learned on rigid terrain are shown to transfer to hard (silt-like) and soft (snow-like) deformable terrains. The environment described performs the following: multivehicle multibody dynamics cosimulation in a time/space-coherent infrastructure that relies on the Message Passing Interface standard for low-latency parallel computing; sensor simulation (e.g., camera, GPU, IMU); simulation of a virtual world that can be altered by the agents present in the simulation; training that uses reinforcement learning to “teach” the autonomous vehicles to drive in an obstacle-riddled course. The software stack described is open source. Relevant movies: Project Chrono. Off-road AV simulations, 20202.more » « less
-
SAE; Transactions (Ed.)Alternative fuels are sought after because they produce lower emissions and sometimes, they have feedstock and production advantages over fossil fuels, but their wear effects on engine components are largely unknown. In this study, the lubricity properties of a Fischer-Tropsch Gas-to-Liquid alternative fuel (Synthetic Paraffinic Kerosene-S8) and of Jet-A fuel were investigated and compared to those of Ultra Low Sulphur Diesel (ULSD). A pin-on-disk tribometer was employed to test wear and friction for a material pair of an AISI 316 steel ball on an AISI 1018 steel disk when lubricated by the fuels in this research work. Advanced digital microscopy was used to compare the wear patterns of the disks. Viscosity and density analysis of the tested fluids were also carried out.Tribometry for the fuel showed that S8 fell between Jet-A and ULSD when friction force was calculated and showed higher wear over time and after each test when compared to that of Jet-A and ULSD. An initially higher running-in friction force of 0.35N to 0.38N was observed for all three tested fluids, and then quasi-steady-state lower values of friction force of .310N for S8, 0.320 N for Jet-A and 0.295N for ULSD (the lowest observed).Wear values obtained by mass loss of the tested AISI 108 steel disks show that Jet-A and the reference fuel ULSD may yield lower wear (which is associated to better lubricity) than that of S8, and microscopy images are consistent with the wear results.more » « less
-
SAE, Transactions (Ed.)An investigation into emissions differences and their correlations with differing combustion characteristics between F24 and Jet-A was conducted. Raw emissions data was taken from a single stage jet engine by a FTIR gas analyzer. Measurements of H2O, CO2, CO, NOx, and total hydrocarbon emissions (THC) were taken at 60K, 65K, and 70K RPM. At 70K RPM Jet-A and F-24 the emissions were similar at approx.: 4% H2O, 3% CO2, 970 PPM CO, 28 PPM NOx. Jet-A THC emissions were approx.: 1200 PPM THC, F24 THC emissions were lower by over 60%. The significantly lower amount of THC emissions for F24 suggests more complete combustion compared to Jet-A.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.4271/2023-01-0105
