Search Results

In this paper we present a project that interfaced the National Advanced Driving Simulator (NADS) with SynChrono, a module of the Project Chrono open source simulation platform, to enable real-time, physics-based simulation of multiple autonomous vehicles (AVs) interacting with manned vehicles. In this setup, a driver at NADS, at the University of Iowa, participates in a traffic scenario that involves AVs that run at the University of Wisconsin-Madison on a cluster supercomputer. The NADS simulator is a driving simulator giving the “most realistic driving simulation experience in the country” [1]. Thanks to its actuators, it can move across its 64-foot by 64-foot bay, rotate and tilt, to emulate vehicle movement and vibrations. In addition, the human driver drives in a full-size cab, surrounded by LED monitors, resulting in an immersive, high fidelity driving simulation experience.

In 2010, 32,855 fatalities and over 2.2 million injuries occurred in automobile crashes, not to mention the immense economic impact on our society. Two of the four most frequent types of crashes are rear-end and lane departure crashes. In 2011, rear-end crashes accounted for approximately 28% of all crashes while lane departure crashes accounted for approximately 9%. This paper documents a study on the NADS-1 driving simulator to support the development of driver behavior modeling. Good models of driver behavior will support the development of algorithms that can detect normal and abnormal behavior, as well as warning systems that can issue useful alerts to the driver. Several scenario events were designed to fill gaps in previous crash research. For example, previous studies at NADS focused on crash events in which the driver was severely distracted immediately before the event. The events in this study included a sample of undistracted drivers.

Distracted driving remains a serious risk to motorists in the US and worldwide. Over 3,000 people were killed in 2013 in the US because of distracted driving; and over 420,000 people were injured. A system that can accurately detect distracted driving would potentially be able to alert drivers, bringing their attention back to the primary driving task and potentially saving lives. This paper documents an effort to develop an algorithm that can detect visual distraction using vehicle-based sensor signals such as steering wheel inputs and lane position. Additionally, the vehicle-based algorithm is compared with a version that includes driving-based signals in the form of head tracking data. The algorithms were developed using machine learning techniques and combine a Random Forest model for instantaneous detection with a Hidden Markov model for time series predictions.

Digital maps are being linked to Advanced Driver Assistance Systems (ADAS) in numerous ways. Digital map data effectively provides a road predictive capability with a quasi-infinite range. We study the use of digital map attribute data in the enhancement of Electronic Stability Control (ESC). An offline study was conducted using real-world steering input records from participants in a prior ESC study at the National Advanced Driving Simulator (NADS). In all cases, the RMS yaw rate error was significantly reduced using the map-enhanced algorithm over the traditional ESC system. Additionally, many cases also showed improvements in other measures, such as lane deviation.

The paper discusses the development of a model for the 2006 BMW 330i for the National Advanced Driving Simulator's (NADS) vehicle dynamics simulation, NADSdyna. The front and rear suspensions are independent strut and link type suspensions modeled using recursive rigid-body dynamics formulations. The suspension springs and shock absorbers are modeled as force elements. The paper includes parameters for front and rear semi-empirical tire models used with NADSdyna. Longitudinal and lateral tire force plots are also included. The NADSdyna model provides state-of-the-art high-fidelity handling dynamics for real-time hardware-in-the-loop simulation. The realism of a particular model depends heavily on how the parameters are obtained from the actual physical system. Complex models do not guarantee high fidelity if the parameters used were not properly measured. Methodologies for determining the parameters are detailed in this paper.

This paper presents an evaluation of a complete vehicle dynamics model for a 2006 BMW 330i to be used for the National Advanced Driving Simulator. Vehicle handling and braking are evaluated and simulation results are compared with experimental field-testing. NADSdyna, the National Advanced Driving Simulator vehicle dynamics software, is used. The BMW evaluation covers vehicle directional dynamics that include steady-state, transient, and frequency domain responses. These evaluations are performed with the DSC (Dynamic Stability and Control) turned off to ensure the principle mechanical properties of the vehicle are properly modeled before enabling the electronic stability system. The evaluation also includes simulation runs with DSC turned on for the J-turn and severe lane change maneuvers.