Your Selections

Autonomous vehicles
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Committees

Events

Magazine

Series

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Unsettled Topics in Autonomous Vehicle Data Sharing for Verification and Validation Purposes

Caliber Data Labs-Mohsen Khalkhali, Yaser Khalighi
  • Research Report
  • EPR2020007
To be published on 2020-04-15 by SAE International in United States
The race to autonomy has been synonymous with the race to data collection. Autonomous vehicles (AVs) generate terabytes of data per day. Perception engineers use these large datasets to analyze and model the automated driving systems (ADS) that will eventually be put into vehicles that will drive themselves. However, the current industry practices of collecting data by driving on public roads to understand real-world scenarios is not practical and will be unlikely to lead to safe deployment of this technology anytime soon. Estimates show that it could take 400 years for a fleet of 100 AVs to drive enough miles to prove that they are as safe as humans. We, therefore, discuss an unsettled topic of sharing data for verification and validation purposes where – instead of each testing project and organization doing their own tests in isolation and potentially duplicating work – a shared – data culture, business, and technology be developed. This could allow for rapid generation, testing, and sharing of the billions of possible scenarios that are needed to prove practicality and…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Research on Trajectory Planning for Four-wheel Steering Autonomous Vehicle with V2V Communication

Jilin University-Fangwu Ma, Yucheng Shen, Jiahong Nie, Xiyu Li, Yu Yang, Jiawei Wang, Guanpu Wu
  • Technical Paper
  • 2020-01-0114
To be published on 2020-04-14 by SAE International in United States
Lane-changing is a typical traffic scene effecting on road traffic with high request for reliability, robustness and driving comfort to improve the road safety and transportation efficiency. The development and application of connected autonomous vehicles with V2V communication provides more advanced control strategies to research of lane-changing. Meanwhile, Four-wheel steering is an effective way to improve flexibility of vehicle. The front and rear wheels rotate in opposite direction to reduce the turning radius to improve the servo agility operation at the low speed while those rotate in same direction to reduce the probability of the slip accident to improve the stability at the high speed. Hence, this paper established Ackerman front-wheel steering with proportional rear-wheel steering vehicle dynamic model and quasi real lane-changing scenes to analyze the motion constraints of the vehicles. Then, the polynomial function and Sin function were used for the lane-changing trajectory planning and the extended rectangular vehicle model was established to get vehicle collision avoidance condition. Vehicle comfort requirements and lane-changing efficiency were used as the optimization variables of optimization function.…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Alleviating the Magnetic Effects on Magnetometers using Vehicle Kinematics for Yaw Estimation for Autonomous Ground Vehicles

Michigan Technological University-Ahammad Basha Dudekula, Jeffrey D. Naber
  • Technical Paper
  • 2020-01-1025
To be published on 2020-04-14 by SAE International in United States
Autonomous vehicle operation is dependent upon accurate position estimation and thus a major concern of implementing the autonomous navigation is obtaining robust and accurate data from sensors. This is especially true, in case of Inertial Measurement Unit (IMU) sensor data. The IMU consists of a 3-axis gyro, 3-axis accelerometer, and 3-axis magnetometer. The IMU provides vehicle orientation in 3D space in terms of yaw, roll and pitch. Out of which, yaw is a major parameter to control the ground vehicle’s lateral position during navigation. The accelerometer is responsible for attitude (roll-pitch) estimates and magnetometer is responsible for yaw estimates. However, the magnetometer is prone to environmental magnetic disturbances which induce errors in the measurement. The present work focuses on alleviating magnetic disturbances for ground vehicles by fusing the vehicle kinematics information with IMU senor in an Extended Kalman filter (EKF) with the vehicle orientation represented using Quaternions. In addition, the error in rate measurements from gyro sensor gets accumulated as the time progress which results in drift in rate measurements and thus affecting the vehicle…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Autonomous Vehicle Multi-Sensors Localization in Unstructured Environment

FEV North America Inc.-Qusay Alrousan, Hamzeh Alzu'bi, Andrew Pfeil, Tom Tasky
  • Technical Paper
  • 2020-01-1029
To be published on 2020-04-14 by SAE International in United States
Autonomous driving in unstructured environments is a significant challenge due to the inconsistency of important information for localization such as lane markings. To reduce the uncertainty of vehicle localization in such environments, sensor fusion of LiDAR, Radar, Camera, GPS/IMU, and Odometry sensors is utilized. This paper discusses a hybrid localization technique developed using: LiDAR based Simultaneous Localization and Mapping (SLAM), GPS/IMU and Odometry data, and object lists from Radar and Camera sensors. An Extended Kalman Filter (EKF) is utilized to fuse data from all sensors in two phases. In the preliminary stage, the SLAM-based vehicle coordinates are fused with the GPS-based positioning. The output of this stage is then fused with the objects-based localization. This approach was successfully tested on FEV’s Smart Vehicle Demonstrator at FEV’s HQ representing a complicated test environment with dynamic and static objects. The test results show that multi-sensor fusion improves the vehicle’s localization compared to GPS or LiDAR alone.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Energy Efficient Maneuvering of Connected and Automated Vehicles

Southwest Research Institute-Sankar Rengarajan, Scott Hotz, Jayant Sarlashkar, Stanislav Gankov, Piyush Bhagdikar, Michael C. Gross, Charles Hirsch
  • Technical Paper
  • 2020-01-0583
To be published on 2020-04-14 by SAE International in United States
Onboard sensing and external connectivity using Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I) and Vehicle-to-Everything (V2X) technologies will allow a vehicle to "know" its future operating conditions with some degree of certainty, greatly narrowing prior information gaps. The increased development of such Connected and Automated Vehicle (CAV) systems, currently used mostly for safety and driver convenience, presents new opportunities to improve the energy efficiency of individual vehicles. The NEXTCAR program is one such initiative by the Advanced Research Projects Agency – Energy (ARPA-E) to developed advanced vehicle dynamics and powertrain control technologies that leverage such connected information streams. Southwest Research Institute (SwRI) in collaboration with Toyota and University of Michigan is currently working on improving energy consumption of a Toyota Prius Prime 2017 by 20%. This paper provides an overview of the various algorithms that have been developed to achieve the energy consumption target. A breakdown of how individual algorithms contribute to the overall target is presented. The team built a specialized test-bed called CAV dynamometer that integrates a traffic simulator and a hub dynamometer for testing the…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Cooperative Mandatory Lane Change for Connected Vehicles on Signalized Intersection Roads

Clemson University-Zhiyuan Du, Bin Xu, Pierluigi Pisu
  • Technical Paper
  • 2020-01-0889
To be published on 2020-04-14 by SAE International in United States
This paper presents a hierarchical control architecture to coordinate a group of connected vehicles on signalized intersection roads, where the vehicles are allowed change lane to follow a prescribed path. The hierarchical control strategy consists of two levels of controllers. The higher level controller acts as a centralized controller, while the lower level controller implemented in each individual car is designed as decentralized controller. In the hierarchical control architecture, the centralized intersection controller estimates the target velocity for each approaching connected vehicle to avoid red light stop based on the signal phase and timing (SPAT) information. Each connected vehicle as a decentralized controller utilizes Model Predictive Control (MPC) to track the target velocity in a fuel efficient manner. The main objective is this paper is to consider mandatory lane changing. As in the realistic scenarios, vehicles are not necessary required to drive in single lane. More specifically, they more likely change their lanes prior to signals. Hence, the vehicle decentralized controllers are prepared to cooperate with the vehicle which has mandatory lane change request (host…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Vehicle Velocity Prediction Using Artificial Neural Network and Effect of Real World Signals on Prediction Window.

Colorado State University-Aaron Rabinowitz, Thomas Bradley
Western Michigan University-Tushar Gaikwad, Farhang Motallebiaraghi, Zachary Asher, Alvis Fong, Rick Meyer
  • Technical Paper
  • 2020-01-0729
To be published on 2020-04-14 by SAE International in United States
Prediction of vehicle velocity is important since it can realize improvements in the fuel economy/energy efficiency, drivability and safety. Velocity prediction has been addressed in many publications. Several references considered deterministic and stochastic approaches such as Markov chain, autoregressive models, and artificial neural networks. There are numerous new sensor and signal technologies like vehicle-to-vehicle and vehicle-to-infrastructure communication that can be used to obtain inclusive datasets. Using these inclusive datasets of sensors in deep neural networks, high accuracy velocity predictions can be achieved. This research builds upon previous findings that Long Short-Term Memory (LSTM) deep neural networks provide the highest velocity prediction fidelity. We developed LSTM deep neural network which uses different groups of datasets collected in Fort Collins. Synchronous data was gathered using a test vehicle equipped with sensors to measure ego vehicle position and velocity, ADAS-derived near-neighbor relative position and velocity, and infrastructure-level transit time and signal phase and timing. Effect of different group of datasets on forward velocity prediction window of 10, 15, 20 and 30 seconds is studied. Developed algorithm is tested…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Dynamic Object Map based architecture for robust CVS systems.

Hyundai Motor Group-Syed Mahmud
University of Central Florida-Rodolfo Valiente, Arash Raftari, Mahdi Zaman, Yaser Pourmohammadi Fallah
  • Technical Paper
  • 2020-01-0084
To be published on 2020-04-14 by SAE International in United States
Connected and Autonomous Vehicles (CAV) rely on information obtained from sensors and communication to make decisions. In a Cooperative Vehicle Safety (CVS) system, information from remote vehicles (RV) is available at the host vehicle (HV) through the wireless network. Safety applications such as crash warning algorithms use this information to estimate the RV and HV states. However, this information is uncertain and sparse due to communication losses, limitations of communication protocols in high congestion scenarios, and perception errors caused by sensor limitations. In this paper we present a novel approach to improve the robustness of the CVS systems, by proposing an architecture that divide application and information/perception subsystems. This architecture is enabled by a Dynamic Object Map (DOM) middle layer which uses the received data from HV local sensors and integrates it with the data received through wireless communication to track RVs and create a real-time dynamic map of HV’s surrounding. The architecture is validated with simulations and in a real environment using a remote vehicle emulator (RVE), which allows the joint study of the…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

In-Situ Measurement of Component Efficiency in Connected and Automated Hybrid-Electric Vehicles

Southwest Research Institute-Peter Lobato, Kyle Jonson, Sankar Rengarajan, Jayant Sarlashkar
  • Technical Paper
  • 2020-01-1284
To be published on 2020-04-14 by SAE International in United States
Connected and automated driving technology is known to improve real-world vehicle efficiency by considering information about the vehicle’s environment such as traffic conditions, traffic lights or road grade. This study shows how the powertrain of a hybrid-electric vehicle realizes those efficiency benefits by developing methods to directly measure transient real-time efficiency and power losses of the vehicle’s powertrain components through chassis-dynamometer testing. This study is a follow-on to SAE Technical Paper 2019-01-0116, Test Methodology to Quantify and Analyze Energy Consumption of Connected and Automated Vehicles, to understand the sources of efficiency gains resulting from connected and automated vehicle driving. A 2017 Toyota Prius Prime was instrumented to collect power measurements throughout its powertrain and driven over a specific driving schedule on a chassis dynamometer. The same driving schedule was then modified to simulate a connected and automated vehicle driving profile, and the sources of vehicle efficiency improvements are analyzed. While conventional powertrain components typically only have two sources and sinks of power, e.g. an input and output shaft, the components of modern hybrid-electric vehicles are…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

The Design of Safe-Reliable-Optimal Performance for Automated Driving Systems on Multiple Lanes with Merging Features

Honda Motor Co., Ltd.-Kaijiang Yu
  • Technical Paper
  • 2020-01-0122
To be published on 2020-04-14 by SAE International in United States
Safety function for automated driving systems including advanced driver assistance systems and autonomous vehicle systems is very important. Inside safety function, predictive judge sub-function should be designed with the consideration of more and more penetration of automated driving vehicles. This paper presents the design on multiple lanes with merging features based on the author's previous Patent JP2019-147944. In the author's previous work (Model Predictive Control for Hybrid Electric Vehicle Platooning Using Slope Information-Published on IEEE transactions on Intelligent Transportation Systems), a model predictive control framework was designed. Due to the difficulty to detail the sub-safety function deeply with merging features, few works are found to deal with sensor platforms focusing on rear side, and situations of merging lane side with the consideration of relative relation variations with other vehicles and road border markers. However, performance enhancement is needed assuring 100% safety-reliability-optimality and single-objectivity. Also, the detailed platform of on-board sensors including side and rear view is needed to deal with false negative operations and false positive operations. The optimal operation line model of human factors…