Your Selections

Machine learning
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Events

Magazine

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

Development of a Camera-based Driver State Monitoring System for Cost-Effective Embedded Solution

Hitachi America, Ltd.-Xunfei Zhou, Tobias Wingert, Maximilian Sauer, Subrata Kundu
  • Technical Paper
  • 2020-01-1210
To be published on 2020-04-14 by SAE International in United States
To prevent the severe consequences of unsafe driving behaviors, it is crucial to monitor and analyze the state of the driver. Developing an effective driver state monitoring (DSM) systems is particularly challenging due to limited computation capabilities of embedded systems in automobiles and the need for finishing processing in real-time. However, most of the existing research work was conducted in a lab environment with expensive equipment while lacking in-car benchmarking and validation. In this paper, a DSM system that estimates driver's alertness and drowsiness level as well as performs emotion detection built with a cost-effective embedded system is presented. The proposed system consists of a mono camera that captures driver's facial image in real-time and a machine learning based detection algorithm that detects facial landmark points and use that information to infer driver's state. In the detection module, driver's distraction level is evaluated by estimating head-pose through solving a perspective-n-point problem, drowsiness level is estimated by processing eyelid related parameters extracted from facial keypoints data, and two approaches were investigated for emotion recognition with performance…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Data-driven framework for fuel efficiency improvement in extended range electric vehicle used in package delivery applications

University of Minnesota-Pengyue Wang, William Northrop
  • Technical Paper
  • 2020-01-0589
To be published on 2020-04-14 by SAE International in United States
Extended-range electric vehicles (EREVs) are a potential solution for fossil fuel usage mitigation and on-road emissions reduction. EREVs can be shown to yield significant fuel economy improvements when the proper energy management strategies (EMSs) are employed. However, many in-use EREVs achieve only moderate fuel reduction compared to conventional vehicles due to the fact that their EMS is far from optimal. This paper focuses on rule-based optimization methods to improve the fuel efficiency of EREV last-mile delivery vehicles equipped with two-way Vehicle-to-Could (V2C) connectivity. The method uses previous vehicle data collected on actual delivery routes and a machine learning method to improve the fuel economy of future routes. The paper first introduces the main challenges of the project such as inherent uncertainty in human driver behavior and in the roadway environment. Then, the framework of our practical physics-model guided data-driven approach is introduced. For vehicles with small amounts of previous data, a Bayesian method is used to adjust a control parameter in the EMS offline for each vehicle with introduced prior information derived from large numbers…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Safety assurance concepts for automated driving systems

University of Melbourne-Stuart Ballingall, Majid Sarvi, Peter Sweatman
  • Technical Paper
  • 2020-01-0727
To be published on 2020-04-14 by SAE International in United States
Automated Driving Systems (ADSs) for road vehicles are being developed that can perform the entire dynamic driving task without a human driver in the loop. However, current regulatory frameworks for assuring vehicle safety may restrict the deployment of ADSs that can use machine learning to modify their functionality while in service. A review was undertaken to identify and assess key initiatives and research relevant to the safety assurance of adaptive safety-critical systems that use machine learning, and to highlight assurance concepts that could benefit from further research. The primary objective was to produce findings and recommendations that can inform policy and regulatory reform relating to ADS safety assurance. Due to the almost infinite number and combination of scenarios that an ADS could encounter, the review found much support for concepts that involve the use of simulation data as virtual evidence of safety compliance, with suggestions of a need to assure simulation tools and models. Real-world behavioural competency testing was also commonly proposed, although noting this concept has its limitations. The concept of whole-of-life assurance was…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Predictive gearbox oil temperature using Machine Learning techniques

Electronics Engineering-Varaprasad Gandi
Tata Elxsi, Ltd.-Mithun Manalikandy, Rajesh Koduri
  • Technical Paper
  • 2020-01-0731
To be published on 2020-04-14 by SAE International in United States
Gearbox failure is the most common failure, which is being detected in vehicles, turbines and other applications. It is not possible to detect every fault manually because gearbox failure depends on various factors like gearbox oil temperature, uncertain driving patterns, engine components and other various gearbox parameters. In recent decades, a lot of research has been done in detecting gearbox failure and various methods and techniques have been proposed to predict failure and also to reduce maintenance and failure costs. To predict the behaviour of the gearbox, robust and efficient algorithms are required. In this work, an effective and accurate algorithm to predict gearbox failure after analysing various symptoms arising on gearbox oil temperature is proposed. Gearbox oil temperature variations are caused by different factors like viscosity, water saturation, dielectric constant and conductivity. Diverse machine learning models such as Support Vector Machine, Random forest and Logistic Regression algorithms from the dataset obtained from gearbox real-time observations are leveraged in this analysis. This paper aims to use sensor data for monitoring oil temperature for fault detection.…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Control Model of Automated Driving Systems based on SOTIF Evaluation

PATAC-Mengge Guo, Shiliang Shang, Cui Haifeng
Shanghai Jiao Tong University-Kaijiong Zhang, Weishun Deng, Xi Zhang, Fan Yu
  • Technical Paper
  • 2020-01-1214
To be published on 2020-04-14 by SAE International in United States
In partially automated and conditionally automated vehicles, part of the work of human drivers is replaced by the system, and the main source of safety risks is no longer system failures, but non-failure risks caused by insufficient system function design. The absence of unreasonable risk due to hazards resulting from functional insufficiencies of the intended functionality or by reasonably foreseeable misuse by persons, is referred to as the Safety Of The Intended Functionality (SOTIF). Drivers have the responsibility to supervise the automated driving system. When they don't agree with the operation behavior of the system, they will interfere with the instructions. However, this may lead to potential risks. In order to discover the causes of human misuse, this paper takes the trust feeling between the driver and the automated driving system as the starting point, and based on the collected data of track test, establishes the evaluation index -- confidence degree to show the trust feeling between the driver and the automated system. Confidence degree is a comprehensive interpretation of the driver's physiological and psychological…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Comparison of CNN and LSTM for modeling virtual sensors in an engine

Chalmers University of Technology-Mauro Bellone, Yiannis Karayiannidis
Volvo AB Volvo Penta-Ethan Faghani
  • Technical Paper
  • 2020-01-0735
To be published on 2020-04-14 by SAE International in United States
Automotive industry makes extensive use of virtual models to increase the efficiency during the development stage. The complexity of such virtual models increases as the complexity of the process that they describe, and for this reason new methods for their development are constantly evaluated. Among many others, data-driven techniques and machine learning offer promising results, creating deep neural networks that map input-output relations. This works aims at evaluating the performance of different neural network architectures for the estimation of engine status and gas emissions. More specifically, Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) will be evaluated in terms of performance, using different techniques to increase the model generalization. During the learning stage data from different engine cycles are fed to the neural network. To evaluate model generalization the network is then tested over new, previously unseen, engine cycles. Results show that our model over-performs a state of the art models, the best performance was found from the LSTM model with 2.40%, 2.80% and 18.19% error for flow fuel, NOx and soot sensor respectively.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Heterogeneous Machine Learning on High Performance Computing for End to End Driving of Autonomous Vehicles

National Renewable Energy Laboratory-Xiangyu Zhang, Peter Graf
Oak Ridge National Laboratory-Robert Patton, Shang Gao, Spencer Paulissen, Nicholas Haas, Brian Jewell
  • Technical Paper
  • 2020-01-0739
To be published on 2020-04-14 by SAE International in United States
Current artificial intelligence techniques for end to end driving of autonomous vehicles typically rely on a single form of learning or training processes along with a corresponding dataset or simulation environment. Relatively speaking, success has been shown for a variety of learning modalities in which it can be shown that the machine can successfully “drive” a vehicle. However, the realm of real-world driving extends significantly beyond the realm of limited test environments for machine training. This creates an enormous gap in capability between these two realms. With their superior neural network structures and learning capabilities, humans can be easily trained within a short period of time to proceed from limited test environments to real world driving. For machines though, this gap is guarded by at least two challenges: 1) machine learning techniques remain brittle and unable to generalize to a wide range of scenarios, and 2) effective training data that enhances generalization and generates the desired driving behavior. Further, each challenge can be computationally intensive on its own thereby exasperating the gap. Moreover, is has…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Using Reinforcement Learning and Simulation to Develop Autonomous Vehicle Control Strategies

Amazon Web Services-Sahika Genc, Premkumar Rangarajan
PolySync Technologies-Anthony Navarro
  • Technical Paper
  • 2020-01-0737
To be published on 2020-04-14 by SAE International in United States
While machine learning in autonomous vehicles development has increased significantly in the past few years, the use of reinforcement learning (RL) methods has only recently been applied. Convolutional neural networks (CNNs) became common for their powerful object detection and identification and even provided end-to-end control of an autonomous vehicle. However, one of the requirements of a CNN is a large amount of labeled data to inform the neural network. While data is becoming more accessible, these networks are still sensitive to the format and collection environment which makes the use of others’ data more difficult. In contrast, RL develops solutions in a simulation environment by trial and error without labeled data. Our research expands upon previous research in RL and proximal policy optimization (PPO) and the application of these algorithms to 1/18th scale cars by expanding the application of this control strategy to a full-sized passenger vehicle. By using this method of unsupervised learning, our research demonstrates the ability to learn new control strategies while in a simulation environment without the need for large amounts…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

RouteE: A Vehicle Energy Consumption Prediction Engine

National Renewable Energy Laboratory-Jacob Holden, Nicholas Reinicke, Jeff Cappellucci
  • Technical Paper
  • 2020-01-0939
To be published on 2020-04-14 by SAE International in United States
The emergence of Connected and Automated Vehicles and Smart Cities technologies create the opportunity for new mobility mode and routing decision tools, among many others. In order to achieve maximal mobility and minimal energy consumption, it is critical to understand the energy cost of decisions and optimize accordingly. The Route Energy Prediction model (RouteE) enables accurate estimation of energy consumption for a variety of vehicle types over trips or sub-trips where detailed drive cycle data is unavailable. Applications include vehicle route selection, energy accounting/optimization in transportation simulation, and corridor energy analyses, among others. The software is an open-source Python package that includes a variety of pre-trained models from the National Renewable Energy Laboratory (NREL). However, RouteE also enables users to train custom models using their own datasets, making it a robust and valuable tool for both fast calculations and rigorous, data-rich research efforts. The pre-trained RouteE models are trained using NREL’s Future Automotive Systems Technology Simulator (FASTSim) paired with approximately 1 million miles of drive cycle data from the Transportation Secure Data Center (TSDC) resulting…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Nonlinear Control of a Ground Vehicle using Data-Driven Dynamic Models

Texas A&M University-Samir Hassen, Kenny Chour, Andrew Weaver, Swaminathan Gopalswamy
  • Technical Paper
  • 2020-01-0171
To be published on 2020-04-14 by SAE International in United States
As autonomous vehicles continue to grow in popularity, it is imperative for engineers to gain greater understanding of vehicle modeling and controls under different situations. Most research has been conducted on on-road ground vehicles, yet off-road ground vehicles which also serve vital roles in society have not enjoyed the same attention. The dynamics for off-road vehicles are far more complex due to different terrain conditions and 3D motion. Thus, modeling for control applications is difficult. A potential solution may be the incorporation of empirical data for modeling purposes, which is inspired by recent machine learning advances, but requires less computation. This thesis proposal presents results for empirical modeling of an off-road ground vehicle, Polaris XP 900. As a first step, data was collected for 2D planar motion by obtaining several velocity step responses. Multivariable polynomial surface fits were performed for the step responses. Sliding mode control layered on top of pure pursuit guidance is then used to drive the vehicle for waypoint following, using the empirical model. Simulation and experimental results show that the vehicle…