Search Results

This research focused on developing a methodology for a vehicle dynamics model of a passenger vehicle outfitted with an aftermarket Automated Driving System software package using only literature and track based results. This package consisted of Autoware.AI (Autoware ®) operating on Robot Operating System 1 (ROS™) with C++ and Python ®. Initial focus was understanding the basics of ROS and how to implement test scenarios in Python to characterize the control systems and dynamics of the vehicle. As understanding of the system continued to develop, test scenarios were adapted to better fit system characterization goals with identification of system configuration limits. Trends from on-track testing were identified and paired with first-order linear systems to simulate physical vehicle responses to given command inputs. Sub-models were developed and simulated in MATLAB ® with command inputs from on-track testing.

This paper details the advancements and outcomes of the NEXTCAR (Next-Generation Energy Technologies for Connected and Automated on-Road Vehicles) program, an initiative led by the Advanced Research Projects Agency-Energy (ARPA-E). The program focusses on harnessing the full potential of Connected and Automated Vehicle (CAV) technologies to develop advanced vehicle dynamic and powertrain control technologies (VD&PT). These technologies have shown the capability to reduce energy consumption by 20% in conventional and hybrid electric cars and trucks at automation levels L1-L3 and by 30% L4 fully autonomous vehicles. Such reductions could lead to significant energy savings across the entire U.S. vehicle fleet.

Driver’s license examinations require the driver to perform either a parallel parking or a similar maneuver as part of the on-road evaluation of the driver’s skills. Self-driving vehicles that are allowed to operate on public roads without a driver should also be able to perform such tasks successfully. With this motivation, the S-shaped maneuverability test of the Ohio driver’s license examination is chosen here for automatic execution by a self-driving vehicle with drive-by-wire capability and longitudinal and lateral controls. The Ohio maneuverability test requires the driver to start within an area enclosed by four pylons and the driver is asked to go to the left of the fifth pylon directly in front of the vehicle in a smooth and continuous manner while ending in a parallel direction to the initial one. The driver is then asked to go backwards to the starting location of the vehicle without stopping the vehicle or hitting the pylons.

Automated driving has become a very promising research direction with many successful deployments and the potential to reduce car accidents caused by human error. Automated driving requires automated path planning and tracking with the ability to avoid collisions as its fundamental requirement. Thus, plenty of research has been performed to achieve safe and time efficient path planning and to develop reliable collision avoidance algorithms. This paper uses a data-driven approach to solve the abovementioned fundamental requirement. Consequently, the aim of this paper is to develop Deep Reinforcement Learning (DRL) training pipelines which train end-to-end automated driving agents by utilizing raw sensor data. The raw sensor data is obtained from the Carla autonomous vehicle simulation environment here. The proposed automated driving agent learns how to follow a pre-defined path with reasonable speed automatically.

Deployment of autonomous vehicles requires an extensive evaluation of developed control, perception, and localization algorithms. Therefore, increasing the implemented SAE level of autonomy in road vehicles requires extensive simulations and verifications in a realistic simulation environment before proving ground and public road testing. The level of detail in the simulation environment helps ensure the safety of a real-world implementation and reduces algorithm development cost by allowing developers to complete most of the validation in the simulation environment. Considering sensors like camera, LiDAR, radar, and V2X used in autonomous vehicles, it is essential to create a simulation environment that can provide these sensor simulations as realistically as possible.

With the advent of increasing autonomous vehicles on public roads, the safety of vulnerable road users such as pedestrians, cyclists, etc. has never been more important. These especially include Blind or Visually Impaired (BVI) pedestrians who face difficulty in making confident decisions in road crossings without the help of accessible pedestrian signals (APS). This paper addresses some of the safety measures that can be taken to improve and assess the safety of BVI pedestrians in a controlled environment like a BVI school campus where autonomous vehicles are operated. The majority of research on autonomous vehicle safety does not consider the edge cases of encounters with BVI pedestrians. Based on this motivation, requirements and characteristics of Non-BVI and BVI pedestrians have been stated along with the motion models used to predict their future movements. Existing tools based on Bayesian multi-model filters were used for pedestrian tracking and motion predictions.

This study is focused on exploring the possibilities of using camera and route planner images for autonomous driving in an end-to-mid learning fashion. The overall idea is to clone the humans’ driving behavior, in particular, their use of vision for ‘driving’ and map for ‘navigating’. The notion is that we humans use our vision to ‘drive’ and sometimes, we also use a map such as Google/Apple maps to find direction in order to ‘navigate’. We replicated this notion by using end-to-mid imitation learning. In particular, we imitated human driving behavior by using camera and route planner images for predicting the desired waypoints and by using a dedicated control to follow those predicted waypoints. Besides, this work also places emphasis on using minimal and cheaper sensors such as camera and basic map for autonomous driving rather than expensive sensors such Lidar or HD Maps as we humans do not use such sophisticated sensors for driving.

With the enhancements in vehicle electrification and autonomous vehicles, Traffic systems are also being improved at an accelerated rate to aid the development of improving fuel economy standards. For this to be possible, it is essential that traffic can be accurately modeled and predicted. The existing toolsets are proprietary and expensive and traffic modeling is not a trivial task due to its dependence on various factors such as place, time, and weather. To address these issues, an entirely open-source Software-In-Loop (SIL) fleet-focused traffic modeling toolset has been developed with the ability to take environmental factors with powertrain-in-the-loop into account leveraging Simulation of Urban Mobility (SUMO) and python. The proposed SIL toolset encompasses the creation of a microscopic traffic distribution which accounts for the usual traffic trends of a typical day.

Having connectivity among ground vehicles brings about benefits in fuel economy improvement, traffic mobility enhancement and undesired emission reductions. On the other hand, Unmanned Aerial Vehicles (UAV) have proven to help in getting aerial data to end users in an affordable manner. When UAVs are equipped with cameras, they can get information about the terrain they are flying over. Moreover, using Vehicle-to-Everything (V2X) communication technologies, it is possible to form a communication link between UAVs and the connected ground vehicle networks comprising of Connected and Autonomous vehicles (CAVs). To investigate and exploit the potential benefits and use cases of a broad vehicle network, a microscopic traffic simulator modified previously by our group with the addition of nearby UAVs is used to integrate simulated Connected UAVs flying above a realistic simulation of heterogeneous traffic flow containing both CAVs and non-CAVs.

Autonomous vehicles are expected to change our lives with significant applications like on-demand, shared autonomous taxi operations. Considering that most vehicles in a fleet are parked and hence idle resources when they are not used, shared on-demand services can utilize them much more efficiently. While ride hailing of autonomous vehicles is still very costly due to the initial investment, a shared autonomous vehicle fleet can lower its long-term cost such that it becomes economically feasible. This requires the Shared Autonomous Vehicles (SAV) in the fleet to be in operation as much as possible. Motivated by these applications, this paper presents a simulation environment to model and simulate shared autonomous vehicles in a geo-fenced urban setting.

A key enabler to maximizing the benefits from advanced powertrain technologies is to adopt a systems integration approach and develop optimized controls that consider the propulsion system and vehicle as a whole. This approach becomes essential when incorporating Advanced Driver Assistance Systems (ADAS) and communication technologies, which can provide information on future driving conditions. This may enable the powertrain control system to further improve the vehicle performance and energy efficiency, shifting from an instantaneous optimization of energy consumption to a predictive and “look-ahead” optimization. Benefits from this approach can be realized at all levels of electrification, from conventional combustion engines to hybrid propulsion systems and full electric vehicles, and at all levels of vehicle automation.

The assessment of fuel economy of new vehicles is typically based on regulatory driving cycles, measured in an emissions lab. Although the regulations built around these standardized cycles have strongly contributed to improved fuel efficiency, they are unable to cover the envelope of operating and environmental conditions the vehicle will be subject to when driving in the “real-world”. This discrepancy becomes even more dramatic with the introduction of Connectivity and Automation, which allows for information on future route and traffic conditions to be available to the vehicle and powertrain control system. Furthermore, the huge variability of external conditions, such as vehicle load or driver behavior, can significantly affect the fuel economy on a given route. Such variability poses significant challenges when attempting to compare the performance and fuel economy of different powertrain technologies, vehicle dynamics and powertrain control methods.

Prediction of power efficiency of gear boxes has become an increasingly important research topic since fuel economy requirements for passenger vehicles are more stringent, due to not only fuel cost but also environmental regulations. Under this circumstance, the automotive industry is dedicatedly focusing on developing a highly efficient gear box. Thus, the analysis of power efficiency of gear box should be performed to have a transmission that is highly efficient as much as possible at the beginning of design stage. In this study, a program is developed to analyze the efficiency of an entire gearbox, considering all components’ losses such as gear mesh, wet clutches, bearings, oil pump and so on. The analytical models are based on the formulations of each component power loss model which has been developed and published in many existing papers. The program includes power flow analysis of both a parallel gear-train and a planetary gear-train.

Advances in sensor solutions in the automotive sector make it possible to develop better ADAS and autonomous driving functions. One of the main tasks of highway chauffeur and highway pilot automated driving systems is to keep the vehicle between the lane lines while driving on a pre-defined route. This task can be achieved by using camera and/or GPS to localize the vehicle between the lane lines. However, both sensors have shortcomings in certain scenarios. While the camera does not work when there are no lane lines to be detected, an RTK GPS can localize the vehicle accurately. On the other hand, GPS requires at least 3 satellite connections to be able to localize the vehicle and more satellite connections and real-time over-the-air corrections for lane-level positioning accuracy. If GPS localization fails or is not accurate enough, lane line information from the camera can be used as a backup.

Autonomous vehicle technology has been developing rapidly in recent years. Vehicle parametric uncertainty in the vehicle model, variable time delays in the CAN bus based sensor and actuator command interfaces, changes in vehicle sped, sensitivity to external disturbances like side wind and changes in road friction coefficient are factors that affect autonomous driving systems like they have affected ADAS and active safety systems in the past. This paper presents a robust control architecture for automated driving systems for handling the abovementioned problems. A path tracking control system is chosen as the proof-of-concept demonstration application in this paper. A disturbance observer (DOB) is embedded within the steering to path error automated driving loop to handle uncertain parameters such as vehicle mass, vehicle velocities and road friction coefficient and to reject yaw moment disturbances.

Future SAE Level 4 and Level 5 autonomous vehicles will require novel applications of localization, perception, control and artificial intelligence technology in order to offer innovative and disruptive solutions to current mobility problems. This paper concentrates on low speed autonomous shuttles that are transitioning from being tested in limited traffic, dedicated routes to being deployed as SAE Level 4 automated driving vehicles in urban environments like college campuses and outdoor shopping centers within smart cities. The Ohio State University has designated a small segment in an underserved area of campus as an initial autonomous vehicle (AV) pilot test route for the deployment of low speed autonomous shuttles. This paper presents initial results of ongoing work on developing solutions to the localization and perception challenges of this planned pilot deployment.

This paper describes a systematic approach to identify the best sensor combination by performing sensor placement analysis to detect and isolate clutch stuck-off faults in Automatic Transmissions (AT) based on structural analysis. When an engaged clutch in the AT loses pressure during operation, it is classified as a clutch stuck-off fault. AT can enter in neutral state because of these faults; causing loss of power at wheels. Identifying the sensors to detect and isolate these faults is important in the early stage of the AT development. A universal approach to develop a structural model of an AT is presented based on the kinematic relationships of the planetary gear set elements. Sensor placement analysis is then performed to determine the sensor locations to detect and isolate the clutch stuck-off faults using speed sensors and clutch pressure sensors. The proposed approach is then applied to a 10-Speed AT to demonstrate its effectiveness.

An important part of automotive driving assistance systems and autonomous vehicles is speed optimization and traffic flow adaptation. Vehicle sensors and wireless communication with surrounding vehicles and road infrastructure allow for predictive control strategies taking near-future road and traffic information into consideration to improve fuel economy. For the development of autonomous vehicle speed control algorithms, it is imperative that the controller can be evaluated under different realistic driving and traffic conditions. Evaluation in real-life traffic situations is difficult and experimental methods are necessary where similar driving conditions can be reproduced to compare different control strategies. A traditional approach for evaluating vehicle performance, for example fuel consumption, is to use predefined driving cycles including a speed profile the vehicle should follow.

As the development of autonomous vehicles rapidly advances, the use of convoying/platooning becomes a more widely explored technology option for saving fuel and increasing the efficiency of traffic. In cooperative adaptive cruise control (CACC), the vehicles in a convoy follow each other under adaptive cruise control (ACC) that is augmented by the sharing of preceding vehicle acceleration through the vehicle to vehicle communication in a feedforward control path. In general, the desired velocity optimization for vehicles in the convoy is based on fuel economy optimization, rather than driveability. This paper is a preliminary study on the impact of the desired velocity profile on the driveability characteristics of a convoy of vehicles and the controller gain impact on the driveability. A simple low-level longitudinal model of the vehicle has been used along with a PD type cruise controller and a generic spacing policy for ACC/CACC.

The EcoCAR 2 team at the Ohio State University has designed an extended-range electric vehicle capable of 44 miles all-electric range, which features a 18.9-kWh lithium-ion battery pack with range extending operation in both series and parallel modes made possible by a 1.8-L ethanol (E85) engine and a 6-speed automated manual transmission. This vehicle is designed to reduce fuel consumption, with a utility factor weighted fuel economy of 50 miles per gallon gasoline equivalent (mpgge), while meeting Tier II Bin 5 emissions standards. This report documents the team's refinement work on the vehicle during Year 3 of the competition, including vehicle improvements, control strategy calibration and dynamic vehicle testing, culminating in a 99% buy off vehicle that meets the goals set forth by the team. This effort was made possible through support from the U.S. Department of Energy, General Motors, The Ohio State University, and numerous competition and local sponsors.