Search Results

Computer modelling, virtual prototyping and simulation is widely used in the automotive industry to optimize the development process. While the use of CAE is widespread, on its own it lacks the ability to provide observable acoustics or tactile vibrations for decision makers to assess, and hence optimize the customer experience. Subjective assessment using Driver-in-Loop simulators to experience data has been shown to improve the quality of vehicles and reduce development time and uncertainty. Efficient development processes require a seamless interface from detailed CAE simulation to subjective evaluations suitable for high level decision makers. In the context of perceived vehicle vibration, the need for a bridge between complex CAE data and realistic subjective evaluation of tactile response is most compelling. A suite of VI-grade noise and vibration simulators have been developed to meet this challenge.

Authors : Thomas ANTOINE, Christophe THEVENARD, Pierrick BOTTA, Jerome DESTREE, Alain Le Quenven Future noise emission limits for passenger car are going to lower levels by 2024 (Third phase of R51-03, with a limit of 68dBA for the pass by noise) –Social cost of noise for France in 2021, shows clearly that the dominant source of noise pollution is indeed road traffic (81 Bn€ for a total of 146 Bn€) This R51 regulation is meant to lower the noise pollution from road traffic, however when looking closer to the sound source and their contributions, in particular the tire/road noise interaction, the environmental efficiency of this regulation is questionable. Indeed: Tire/Road interaction involves tires characteristics, that are constrained by an array of specification for energy efficiency, safety (wet grip, braking, etc…) and it has been proven that there is a physical limit to what could be expected from the tire as far as tire/road interaction noise is concerned.

Quantum computing and its applications are emerging rapidly, driving excitement and extensive interest across all industry sectors, from finance to pharmaceuticals. The automotive industry is no different. Quantum computing can bring significant advantages to the way we commute, whether through the development of new materials and catalysts using quantum chemistry or improved route optimization. Quantum computing may be as important as the invention of driverless vehicles. Emergence of Quantum Computing Technologies in Automotive Applications: Opportunities and Future Use Cases attempts to explain quantum technology and its various advantages for the automotive industry. While many of the applications presented are still nascent, they may become mainstream in a decade or so. Click here to access the full SAE EDGETM Research Report portfolio.

The Particle Number–Portable Emission Measurement System (PN-PEMS) came into force with Euro VI Phase E regulations starting January 1, 2022. However, positive ignition (PI) engines must comply from January 1, 2024. The delay was due to the unavailability of the PN-PEMS system that could withstand high concentrations of water typically present in the tailpipe (TP) of CNG vehicles, which was detrimental to the PN-PEMS systems. Thus, this study was designed to evaluate the condensation particle counter (CPC)-based PN-PEMS measurement capabilities that was upgraded to endure high concentration of water. The PN-PEMS measurement of solid particle number (SPN23) greater than 23 nm was compared against the laboratory-grade PN systems in four phases. Each phase differs based upon the PN-PEMS and PN system location and measurements were made from three different CNG engines. In the first phase, systems measured the diluted exhaust through constant volume sampler (CVS) tunnel.

The safety and reliability of ground vehicles is a motivating factor for periodic maintenance which includes fluids, lubrication, cleaning, repairs, and general observation of key subsystems. The scheduling of maintenance activities can occur at different rates such as daily, weekly, or perhaps operating time based on collected historical data and general guidelines. The availability of a digital twin (DT), which offers a virtual representation of the vehicle behavior, enables virtual system simulations for different operating cycles to explore the dynamic behavior. When field operating fleet data can be integrated with the digital twin estimates, then this supplemental information can be combined with the existing maintenance plan to provide a more comprehensive approach. In this paper, a digital twin with a statistical based predictive maintenance strategy is investigated for a wheeled military ground vehicle.

It is an important factor in electric vehicles to show customers how much they can drive with the energy of the remaining battery. If the remaining mileage is not accurate, electric vehicle drivers will have no choice but have to feel anxious about the mileage. Additionally, the potential customers have range anxiety when they consider Electric Vehicles. If the remaining mileage to drive is wrong, drivers may not be able to get to the charging station and may not be able to drive because the battery runs out. It is important to show the remaining available driving range exactly for drivers. The previous study proposed an advanced model by predicting the remaining mileage based on actual driving data and based on reflecting the pattern of customers who drive regularly. The Bayesian linear regression model was right model in previous study.

Roundabouts are one of the most complex traffic environments in urban roads, and a key challenge for intelligent driving decision-making. Deep reinforcement learning, as an emerging solution for intelligent driving decisions, has the advantage of avoiding complex algorithm design and sustainable iteration. For the decision difficulty in roundabout scenarios, this paper proposes an artificial potential field based Soft Actor-Critic (APF-SAC) algorithm. Firstly, based on the Carla simulator and Gym framework, a reinforcement learning simulation system for roundabout driving is built. Secondly, to reduce reinforcement learning exploration difficulty, global path planning and path smoothing algorithms are designed to generate and optimize the path to guide the agent.

For intelligent vehicles, a robust perception system relies on training datasets with a large variety of scenes. The architecture of federated learning allows for efficient collaborative model iteration while ensuring privacy and security by leveraging data from multiple parties. However, the local data from different participants is often not independent and identically distributed, significantly affecting the training effectiveness of autonomous driving perception models in the context of federated learning. Unlike the well-studied issues of label distribution discrepancies in previous work, we focus on the challenges posed by scene heterogeneity in the context of federated learning for intelligent vehicles and the inadequacy of a single scene for training multi-task perception models. In this paper, we propose a federated learning-based perception model training system.

With economic development and the increasing number of vehicles in cities, urban transport systems have become an important issue in urban development. Efficient traffic signal control is a key part of achieving intelligent transport. Reinforcement learning methods show great potential in solving complex traffic signal control problems with multidimensional states and actions. Most of the existing work has applied reinforcement learning algorithms to intelligently control traffic signals. In this paper, we investigate the agent-based reinforcement learning approach for the intelligent control of ramp entrances and exits of urban arterial roads, and propose the Proximal Policy Optimization (PPO) algorithm for traffic signal control. We compare the method controlled by the improved PPO algorithm with the no-control method.

During the vehicle lifecycle, customers are able to directly perceive the outer panel stiffness of vehicles in various environmental conditions. The outer panel stiffness is an important factor for customers to perceive the robustness of the vehicle. In the real test of outer panel stiffness after prototype production, evaluators manually press the outer panel in advance to identify vulnerable areas to be tested and evaluate the performance only in those area. However, when developing the outer panel stiffness performance using FEA (Finite Element Analysis) before releasing the drawing, it is not possible to filter out these areas, so the entire outer panel must be evaluated. This requires a significant amount of computing resources and manpower. In this study, an approach utilizing artificial intelligence was proposed to streamline the outer panel stiffness analysis and improve development reliability.

With the development of internet technology and autonomous vehicles (AVs), the multimodal transportation and distribution model based on AVs will be a typical application paradigm in the smart city scenario. Before AVs carry out logistics distribution, it is necessary to plan a reasonable distribution path based on each customer point, and this is also known as Vehicle Routing Problem (VRP). Unlike traditional VRP, the urban logistics distribution process based on multimodal transportation mode will use a set of different types of AVs, mainly including autonomous ground vehicles and unmanned aerial vehicles (UAVs). It is worth pointing out that there is currently no research on combining the planning of AVs distribution paths with the trajectory planning of UAVs. To address this issue, this article establishes a bilevel programming model. The upper-level model aims to plan the optimal delivery plan for AVs, while the lower-level model aims to plan a driving trajectory for UAVs.

Validation plays a crucial role in any Electronic Development process. This is true in the development of any automotive Electronic Control Unit (ECU) that utilizes the Automotive V process. From Research and Development (R&D) to End of Line (EOL), every automotive module goes through a plethora of Hardware (HW) and Software (SW) testing. This testing is tedious, time consuming, and inefficient. The purpose of this paper is to show a way to streamline validation in any part of the automotive V process using Python as a driving force to automate and control Hardware-in-the-loop (HIL) / Model-in-the-loop (MIL) / Software-in-the-loop (SIL) validation. The paper will propose and outline a framework to control test equipment, such as power supplies and oscilloscopes, load boxes, and external HW. The framework includes the ability to control CAN communication signals and messages.

This paper introduces reduced-order modeling techniques with Artificial Intelligence (AI) for Model-Based Development (MBD). In vehicle development, detailed physical models are replaced by reduced-order models (ROM) to expedite simulations. With recent advancements in AI-based reduced-order modeling, it is expected that modeling work will become more efficient, leading to reduced simulation times. However, the range of simulations (Model-in-the-Loop Simulation - MILS, Hardware-in-the-Loop Simulation - HILS, bench-system) compatible with ROM is limited. To overcome this limitation, this study leverages the ONNX format (Open Neural Network Exchange), a universally supported format among machine learning frameworks, and the Functional Mock-up Interface (FMI), a standard interface format for simulation tools, to enable general-purpose embedded technology with ROM. This study employs a vehicle model in engine surge simulations to validate AI-based reduced-order modeling for MBD.

Verification and validation (V&V) of autonomous vehicles (AVs) is a challenging task. AVs must be thoroughly tested, to ensure their safe functionality in complex traffic situations including rare but safety-relevant events. Furthermore, AVs must mitigate risks and hazards that result from functional insufficiencies, as described in the Safety of the Intended Functionality (SOTIF) standard. SOTIF analysis includes iterative identification of driving scenarios that are not only unsafe, but also unknown. However, identifying SOTIF’s unknown-unsafe scenarios is an open challenge. In this paper we proposed a systematic optimization-based approach for identification of unknown-unsafe scenarios. The proposed approach consists of three main steps including data collection, feature extraction and optimization towards unknown unsafe scenarios.

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.

To develop safe vehicles, system development must be performed in compliance with functional safety. Functional safety considers situations where failures could make a vehicle unsafe, and it requires the inclusion of mechanisms to detect and mitigate these failures, even though they may not always be detected with 100% certainty — referred as diagnostic coverage (DC). Therefore, some faults, called residual faults, might go undetected. In the realm of functional safety from a communication perspective, industry standards define nine distinct fault modes. The detection of these faults is crucial, especially in the widely used AUTOSAR automotive operating system. AUTOSAR E2E (End-to-End Communication Protection) serves as a communication fault detection mechanism utilizing three mechanisms: counters, timers, and Cyclic Redundancy Check (CRC) to address the nine fault modes. Especially, determining the DC for CRC can be challenging and often requires a conservative evaluation approach.

The current automotive industry has a growing demand for real-time transmission to support reliable communication and for key technologies. The Time-Sensitive Networking (TSN) working group introduced standards for reliable communication in time-critical systems, including shaping mechanisms for bounded transmission latency. Among these shaping mechanisms, Cyclic Queuing and Forwarding (CQF) and frame preemption provide deterministic guarantees for frame transmission. However, despite some current studies on the performance analysis of CQF and frame preemption, they also need to consider the potential effects of their combined usage on frame transmission. Furthermore, there is a need for more research that addresses the impact of parameter configuration on frame transmission under different situations and shaping mechanisms, especially in the case of mechanism combination.

Over the past decade, significant progress has been made in developing algorithms and improving hardware for automated driving. However, conducting research and deploying advanced algorithms on automated vehicles for testing and validation remains costly, especially for academia. This paper presents the efforts of our research team to integrate the newest version of the open-source Autoware software with the commercially available DataSpeed Drive-by-Wire (DBW) system, resulting in the creation of a versatile and robust automated vehicle research platform. Autoware, an open-source software stack based on the 2nd generation Robot Operating System (ROS2), has gained prominence in the automated vehicle research community for its comprehensive suite of perception, planning, and control modules. The DataSpeed DBW system directly communicates with the vehicle's CAN bus and provides precise vehicle control capabilities.

The SAE AutoDrive Challenge II is a four-year collegiate competition dedicated to developing a Level 4 autonomous vehicle by 2025. In January 2023, the participating teams each received a Chevy Bolt EUV. Within a span of five months, the second phase of the competition took place in Ann Arbor, MI. The authors of this contribution, who participated in this event as team Wisconsin Autonomous representing the University of Wisconsin–Madison, secured second place in static events and third place in dynamic events. This has been accomplished by reducing reliance on the actual vehicle platform and instead leveraging physical analogs and simulation. This paper outlines the software and hardware infrastructure of the competing vehicle, touching on issues pertaining sensors, hardware, and the software architecture employed on the autonomous vehicle. We discuss the LiDAR-camera fusion approach for object detection and the three-tier route planning and following systems.

Most of the Automated Driving Systems (ADS) technology development is targeting urban areas; there is still much to learn about how ADS will impact rural transportation. The DriveOhio team deployed level-3 ADS-equipped prototype vehicles in rural Ohio with the goal of discovering technical challenges for ADS deployment in such environments. However, before the deployment on public roads, it was essential to test the ADS-equipped vehicle for their safety limitations. At Transportation Research Center Inc. (TRC Inc.) proving grounds, we tested one such prototype system on a closed test track with soft targets and robotic platforms as surrogates for other road users. This paper presents an approach to safely conduct testing for ADS prototype and assess its readiness for public road deployment. The main goal of this testing was to identify a safe Operational Design Domain (ODD) of this system by gaining better understanding of the limitations of the system.