This SAE Recommended Practice establishes uniform test procedures for friction based parking brake components used in conjunction with hydraulic service braked vehicles with a gross vehicle weight rating greater than 4500 kg (10 000 lb). The components covered in this document are the primary actuation and the foundation park brake. Various peripheral devices such as application dashboard switches or indicators are not included. These test procedures include the following: a Brake Related Tests 1 Brake Functional Performance 2 Brake Dynamic Torque Performance 3 Brake Corrosion Resistance 4 Brake Endurance with Torque 5 Brake Endurance without Torque 6 Vibration Resistance 7 Brake Ultimate Static Load 8 Brake Lining Wear Adjuster Function b Actuation Related Tests 1 Mechanical Actuator Functional Performance 2 Mechanical Actuator Endurance 3 Mechanical Actuator Quick Release 4 Mechanical Actuator Ultimate Load 5 Spring Apply Actuator Functional Performance 6 Spring Apply Actuator

Truck and Bus Hydraulic Brake Committee

SCV Chassis Performance Optimization through Parametric Beam Modelling & Simulation

2021-28-018310/01/2021

In automotive product development, design and development of the chassis plays an important role since all the internal and external loads pass through the vehicle chassis. Durability, NVH, Dynamics as well as overall vehicle performance is dependent on the chassis structure. Even though passenger vehicle chassis has a ladder frame or a monocoque construction, small commercial vehicle chassis is a hybrid chassis with the cabin welded to the ladder frame. As mileage is critical for sale of SCVs, making a light-weight chassis is also important. This creates a trade-off between the performance and weight which needs to be optimized. In this study, a parametric beam model of the ladder frame & the cabin of the vehicle is created in COMSOL Multiphysics. The structure has been parameterized into the long member & crossmember geometry and sections. The model calculates the first 12 natural frequencies, global stiffness, and weight. It has been validated and further used for optimization study

THANAPATI, ALOK Ranjan, Bhalerao, Mihir, Deshmukh, Chandrakant, Krishnan, Hareesh

Brake Groan Noise Investigation and Optimization Strategy for Passenger Vehicles

2021-26-030109/22/2021

Groan is a low frequency noise generated when moderate brake pressure is applied between the surfaces of the brake disc and the brake pad at a low-speed condition. Brake groan is often very intense and can cause large numbers of customer complaints. During a groan noise event, vehicle structure and suspension components are excited by the brake system and result in a violent event that can be heard and felt during brake application. The cause of noise is friction variation of stick-slip phenomenon between friction material and disc. This paper discusses the approach for prediction and mitigation of brake groan noise for passenger vehicles having disc brakes. To identify the brake groan noise frequency, vehicle testing with operating condition for reproducing the groan noise is carried out and also impact frequency response analysis is performed to identify natural frequency of each chassis component like brake, suspension stud, lower control arm, knuckle etc. The finite element corner

Doundkar, Vikas, Iqbal, Shoaib

A Comparative Study of Cradle and Sub Frame Type Powertrain Mounting System on Electric Vehicle

2021-01-102208/31/2021

The growing demand of fuel and cost saving on vehicle, today’s vehicle manufacturer are working on various weight reduction initiative in EV. Lighter weight vehicle have bigger challenges to meet NVH requirement. There are two types of EV called modified and adopted EV’s are commonly in use. The sub frame type of EV system comes under the category of modified EV. In this paper, a mounting system is studied and compared for a cradle type EV as well as sub frame or saddle type EV. MATLAB based optimization tools are used for parameter optimization. The focus is put on the optimization of mounting system location and stiffness for energy optimization, CoG and TRA-EA optimization. The best engine mounting system is compared and adopted based on simulation. 12 DOF studied to address high frequency resonance issues for a sub frame type EV. Finally robustness of the system is checked based on various simulation and optimization.

Deshmukh, Sagar, Hazra, Sandip

Representing SUV as a 2D Beam Carrying Spring-Mass Systems to Compute Powertrain Bounce Mode

2021-01-111608/31/2021

Accurate prediction of in-vehicle powertrain bounce mode is necessary to ensure optimum responses are achieved at driver’s touch points during 4post shake or rough road shake events. But, during the early stages of vehicle development, building a detailed vehicle finite element (FE) model is not possible and often powertrain bounce modes are computed assuming the powertrain to be a stand-alone unit. Studies conducted on FE models of a large SUV with body on frame architecture showed that the stand-alone approach overestimates the powertrain bounce mode. Consequently, there is a need for a simplified version of vehicle model which can be built early on to compute powertrain modes. Previously, representing all the major components as rigid entities, simplified unibody vehicle models have been built to compute powertrain modes. But such an approach would be inaccurate here, for a vehicle with body on frame architecture due to the flexible nature of the frame (even at low frequencies). To

Maddali, Ramakanth, Mogal, Akbar Baig, Haider, Syed

Prediction of Driver Drowsiness Level Using Recurrent Neural Networks and Multi-Time-Scale Fusion

2021-01-090904/06/2021

There is accumulating evidence that drowsy driving is one of the leading causes of vehicle crashes and accidents worldwide. Consequently, automotive manufacturers started to develop in-vehicle drowsiness detection devices. However, due to the limited computation resources and the complexity of the vehicular environment, the existing products' performance is limited. Moreover, the vast majority of the commercialized products focus on monitoring the subject's current drowsiness level, whereas predicting drowsiness level in advance to avoid future risks is overlooked. In this research, a multi-time-scale fusion approach is proposed where prediction results from both long-term and short-term Recurrent Neural Networks (RNN) were combined to predict a person's drowsiness level. Our results indicate that the proposed fusion strategies can successfully capture both the short-term microsleep-related features and long-term sleepiness features and improve the drowsiness prediction performance

Zhou, Xunfei, Kundu, Subrata

Multi-Modal Neural Feature Fusion for Pose Estimation and Scene Perception of Intelligent Vehicle

2021-01-018804/06/2021

The main challenge for future autonomous vehicles is to identify their location and body pose in real time during driving, that is, “where am I? and how will I go?”. We address the problems of pose estimation and scene perception from continuous visual frames in intelligent vehicle. Recent advanced technology in the domain of deep learning proposes to train some learning models for vehicle’s series detection tasks in a supervised or unsupervised manner, which has numerous advances over traditional approaches, mainly reflected in the absence of manual calibration and synchronization of the camera and IMU. In the paper, we propose a novel approach for pose estimation and scene recognition with a deep fusion of multi-modal neural features in the manner of unsupervised. Firstly, low-cost camera and IMU are used to extract original visual and inertial data, then the visual and inertial encoders are utilized to encoder the feature of the two modes. Then, a Long Short-Term Memory (LSTM) takes

Zhou, Aiguo, Li, Zhenyu, Pu, Jiakun, Yu, Jiangyang, Wei, Ronghui, Dong, Zhenbiao

Speed Analysis from Video: A Method for Determining a Range in the Calculations

2021-01-088704/06/2021

This paper introduces a method for calculating vehicle speed and uncertainty range in speed from video footage. The method considers uncertainty in two areas; the uncertainty in locating the vehicle’s position and the uncertainty in time interval between them. An abacus style timing light was built to determine the frame time and uncertainty of time between frames of three different cameras. The first camera had a constant frame rate, the second camera had minor frame rate variability and the third had more significant frame rate variability. Video of an instrumented vehicle traveling at different, but known, speeds was recorded by all three cameras. Photogrammetry was conducted to determine a best fit for the vehicle positions. Deviation from that best fit position that still produced an acceptable range was also explored. Video metadata reported by iNPUT-ACE and Mediainfo was incorporated into the study. When photogrammetry was used to determine a vehicle’s position and speed from

Beauchamp, Gray, Pentecost, David, Koch, Daniel, Hashemian, Alireza, Marr, James, Cordero, Rheana

Calculation and Optimization Methods for the Dynamic Performances of a Power-Train-Subframe Mounting System

2021-01-065804/06/2021

A dynamic performance calculating model for a powertrain-subframe mounting system (PSMS) is presented. Calculation methods for determining the dynamic displacements of a powertrain center of gravity (CG), the dynamic displacements of a subframe CG and the dynamic reaction forces of each mount in a PSMS under ground and motor shake excitation are developed in this paper. An optimization procedure based on the genetic algorithm and SQP is developed for reducing resonance peaks of the reaction forces at mounts. A generic PSMS with three powertrain-subframe mounts and four subframe-body mounts is used to validate the optimization method. The optimization results demonstrate that the results using the optimization procedure can effectively reduce the reaction forces at mounts.

Fang, Zhiyuan, Zhen, Ran, Li, Ruilong

Felling Head Terminology and Nomenclature

J1272_202103 (Current)

03/01/2021

This SAE Standard is intended to describe the basic types of felling heads, including those with bunching capabilities, that are attachments to a self-propelled machine. Only the major components that are necessary to describe the functions of the felling head, and to apply the principles of the standard are included. Illustrations used are not intended to include all existing felling heads or to describe any particular manufacturer’s variation.

MTC4, Forestry and Logging Equipment

Nissan's 2021 Rogue is a COVID beater

21AUTP02_1402/01/2021

Nissan staff truly pulled out the stops to get the all-new 2021 Rogue into the market during the global pandemic. Rogue is the company's best-selling product in North America, by far - a testament to a well-considered overall package that designers, engineers and product planners have steadily evolved and improved since the model's launch in 2007. Now in its third generation (coded T33), the latest Rogue is underpinned by Nissan's C/D-segment architecture that shares more geometries with Sentra, itself a vastly upgraded and improved vehicle for 2021. “Last March, I was reviewing our program schedules and it looked like everything was going to get delayed due to Covid,” said Chris Reed, executive VP of R&D at Nissan Technical Center in Farmington, Mich. “At this time, we had delays in other programs due to a ‘development overload’ situation between suppliers and prototypes. The hatches were being battened down.

Brooke, Lindsay

Analysis of Dashcam Video for Determination of Vehicle Speed

2020-01-087704/14/2020

Using dashcam video footage to extract reliable vehicle speed data can be challenging when the only available image stream comes from a camera whose optical parameters are unknown. One means of overcoming such difficulties uses visible landmarks and features within the video frame whose dimensions can be independently measured. While good results have been obtained by others using a Total Station or LiDAR to physically measure locations for such purposes, this approach could prove difficult if a site of interest is inaccessible (e.g. on a busy highway that cannot be shut down) or if relevent features of the target location have changed (e.g. due to construction or even restriping of lanes lines). As an alternative to direct scene measurement, it is proposed that measurement of features visible in overhead satellite images be used to dimension relevant features visible in the video. In this work, videos from individual dashcams and phone-based cameras were used to calculate average

Leifer, Jack, Marquez, Alvaro

Enhancement of Longitudinal Energy Absorption Efficiency in FMVSS 301

2020-01-122504/14/2020

While active safety has become a focus of attention, passive safety protocols are still being updated, and evaluation standards are becoming stringent worldwide. This paper focused on FMVSS 301, the North American regulation for rear impacts. Due to an offset impact with deformable barrier, it is challenging to control bending modes of rear frames. Furthermore, there is a considerable difference in load paths to the left and right frames, and the amount of bending deformation experienced by the frame on the non-collision-side, which does not directly contact with the barrier, is low. The purpose of this research was to enhance rear-frame energy absorption efficiency in such collisions. To achieve this goal, this research focused on enhancement of deformation mode of the rear frames, and also minimizing the difference in their input loads. For the enhancement of deformation mode, the number and arrangement of collapse points were optimized, and multi-stage bending mode with a high level

Hasegawa, Atsushi, Fujii, Takayuki, Matsuura, Norikazu, Shimizu, Tomohiro

Chassis Lightweighting Hole Placement with Weldline Evaluation

2020-01-049304/14/2020

Vehicle weight driven design comes amid rising higher fuel efficiency standard, and must meet the criteria - pass Proving ground test events that is equivalent customer usage. CAE Fatigue analysis for proving ground (CFP) is behind a success push to digitally simulate vehicle durability performance in high fidelity. The need for vehicle weight reduction often arises late in vehicle development phases when CAE Methods, time, and tangible cost effective opportunities are limited or non-existent. It is necessary to deploy a new CAE Method to identify opportunities for light-weighting hole placement in Chassis structures to deliver a cost effective light-weighting opportunity with no impact on fatigue life. The successful application of this methodology is on truck frame, which is key structural parts for vehicle chassis to support body and suspension and powertrain. By means of artificially adjusting the magnitude of load time history and material fatigue properties S-N curve, fatigue

Song, Gavin

Study on the Quantitative Relationship between Static Stiffness and Modal Parameters of an Aluminum Space Frame

10-04-02-000701/27/2020

In this article, the quantitative relationship between the static stiffness, lightweight factor, and modal parameters of an aluminum space frame was investigated. Modal theory calculation and finite element method were employed in the analysis. Fifty modal parameters were extracted from the finite element model of the frame to calculate the bending stiffness, torsional stiffness, and lightweight factor of the frame. The deviations of the bending stiffness, torsional stiffness, and lightweight factor obtained from the modal theory and the finite element theory were found to be 0.91%, 1.72%, and 1.71%, respectively. It indicates that these two methods have similar accuracy. It was confirmed that the sum of each order modal compliance could be used to calculate the static compliance of the aluminum space frame. The first-order bending mode was found to be the corresponding mode order, which made the largest contribution to the bending stiffness. This method is also applicable for

Wang, Zhenhu, Xia, Erli, Chen, Ziming, Xue, Zhigang, Li, Luoxing

Simulation of Ice Particle Breakup and Ingestion into the Honeywell Uncertified Research Engine (HURE)

2019-01-196506/10/2019

Numerical solutions have been generated which simulate flow inside an aircraft engine flying at altitude through an ice crystal cloud. The geometry used for this study is the Honeywell Uncertified Research Engine (HURE) which was recently tested in the NASA Propulsion Systems Laboratory (PSL) in January 2018. The simulations were carried out at predicted operating points with a potential risk of ice accretion. The extent of the simulation is from upstream of the engine inlet to downstream past the strut in the core and bypass. The flow solution is produced using GlennHT, a NASA in-house code. A mixing plane approximation is used upstream and downstream of the fan. The use of the mixing plane allows for steady state solutions in the relative frame. The flow solution is then passed on to LEWICE3D for particle trajectory, impact and breakup prediction. The LEWICE3D code also uses a mixing plane approximation at the boundaries upstream and downstream of the fan. A distribution of particle

Rigby, David L., Wright, William, Flegel, Ashlie, King, Michael

Structure-Borne Prediction on a Tire-Suspension Assembly Using Experimental Invariant Spindle Forces

2019-01-154106/05/2019

Road induced noise is getting more and more significant in context of the electrification of the powertrain. The automotive industry is seeking for technologies to predict the contribution of vehicle components upfront, early in the development process. Classical Transfer Path Analysis (TPA) is a well-established technique that successfully identifies the transmission paths of noise and vibration from different excitation sources to the target responses. But it has a drawback: it requires the physical availability of the full vehicle. To achieve shorter development cycles, to avoid costly time-consuming design iterations and due to the limited availability of prototypes, engineers derived a method that addresses these requirements. Component-based TPA is a relatively new structure borne substructuring approach that allows to characterize the source excitation by a set of equivalent loads (blocked forces) independently from the receiver structure and to predict its behavior when coupled

Ortega Almirón, Jesús, Bianciardi, Fabio, Corbeels, Patrick

Jeep revives its pickup mojo with 2020 Gladiator

19AUTP05_1505/01/2019

Get ready for the fractionalization of the U.S.'s raucous pickup-truck market. Launching what's surely one of the year's most-anticipated and potentially significant new models, Jeep engineers and planners insist they went out of their way to ensure the 2020 Gladiator was developed as a genuine pickup and not “a Wrangler with a bed.” But everyone knows Jeep would've been crazy to stray too far from the radiant demand for the new JL-generation Wrangler, so excuse us if the Gladiator does, well, at least look like just that: a 4-door Wrangler Unlimited-with a bed.

Visnic, Bill

Assembly 4.0 - Flexibly Picked Up, Precisely Mounted

2019-01-135503/19/2019

Component deviations between as-designed and as-built as a result of deformations in the production process lead to significant cost increasing during assembly. After quality inspection, components are provisionally preassembled to determine their matching accuracy. Components with an acceptable tolerance range are then assembled. Otherwise costly reworks are required. Subsequently, the preassembly process is repeated until acceptable assembly tolerances are achieved. To avoid this time-consuming and costly process loop, a flexible mounting frame coupled with a real-time measuring system is used to optimize the assembly process. The flexible mounting frame can be applied for many applications where components are to be aligned and mounted. This flexible mounting frame allows the realization of exact shape and acceptable position tolerances. The mounting frame consists of telescopic carbon fiber reinforced polymer (CFRP) tubes, linear actuators and suctions grippers. Linear actuators

Bock, Matthias, Kleineberg, Markus

Automatic Drilling and Fastening System for Large Aircraft Doors

2019-01-134603/19/2019

Electroimpact has developed a system for drilling and fastening of cargo door structures which efficiently addresses many of the manufacturing challenges that such parts present. Challenges to door automation include 1) the presence of an inner skin that must be processed, in addition to the outer skin, and 2) a stiff frame structure, which makes the clamping and drilling processes that are typical to automated fastening machines very unforgiving of any errors in workpiece positioning. In this case, the manufacturing cell was to be installed in an existing facility with very limited ceiling height, further complicating the system and process design. New methods were devised to solve these problems, and the solutions found will likely have utility in future applications.

Bigoney, Burton

Design of a Wing for Formula One Category Airplanes

2019-01-133703/19/2019

This paper describes the design of an International Formula One (IF1) racing airplane wing. The first step consists in the simulation of the airplane flying on the race track to obtain details about the condition in which the wing needs to be designed and optimized. The paper describes the details and formulation used to perform this simulation using parametric flight paths and a point model dynamic model. A scheme analytically obtains the control laws for the simulation with Frenet-Serret frames over the parametric flight path. Two different airplanes, with different power levels, are simulated on a typical IF1 race track to determine the range of lift coefficient in which the wing must be designed. Based on this lift coefficient range, a set of four new airfoils are designed based on the NLF0414-F airfoil. Their usage over the wing span is determined, using nonlinear lifting line method to assure that during races the wing operates inside the laminar drag bucket. Finally, this paper

Andrade de Oliveira, Paulo Henriques Iscold

FCA debuts new Ram Heavy Duty pickups

19AUTP03_1603/01/2019

FCA's Ram truck division unveiled its new 2019 Heavy Duty (HD) pickup truck lineup at the 2019 North American International Auto Show (NAIAS). The new HD pickups feature the slick interiors and tech from Ram's new 1500 line, significant powertrain and chassis upgrades and all-new front and rear sheetmetal. The Ram HD lineup will face off against Chevy's new HD pickup offerings and Ford's established F-Series and includes 2500/3500 capacities in regular, crew and mega-cab configurations. Since it's a heavy-duty truck launch, Ram is of course touting new capability figures for its HD lineup, which retains its basic cab architecture, but sees nearly every other part of its chassis upgraded. A new 6.7-liter turbo-diesel producing 1,000 lb·ft of torque-the first HD pickup to break the fourfigure torque-output barrier-combines with a redone frame that's now 98.5% high-strength steel to provide what Ram claims are class-leading figures of 35,100-lb (15,921-kg) towing and 7,680-lb (3,565-kg

Seredynski, Paul

Investigation of Cabin Noise while Accelerating on Low Mu Track through Simulation Approach Using Full Vehicle ADAMS/Car Model

2019-26-017901/09/2019

Cabin noise is a significant product quality criteria which enables the customers for product differentiation. There are various sources of cabin noise such as wind, structures(panels), engine, suspension, tire and roads. During product development phase, extensive tests has been conducted to improve vehicle dynamics behavior on various climatic conditions. One such test is accelerating vehicle on low mu or icy surface. While performing acceleration manoeuvre (tractions) on a low mu tracks, Cabin noise with source identified from front underbody & low tractive torque build up is reported. This undesirable behavior may occur due to following reason (1) Excitation of coupled modes between suspension and powertrain which induces torque fluctuation. (2) Transmissibility of various subsystem can be the reason for above problem statement. (3) Poorly chosen tire compounds and design leads to fluctuation in torque. A detailed simulation based study using ADAMS/CAR has been performed to assess

Singh, Vivek, Prasad, Tej, Srivastava, Harshit

A Mitigation Strategy for Steering Wobble Phenomenon in Passenger Vehicle

2019-26-018301/09/2019

Vehicles have a wide range of resonance band due to design nature & characteristics of its aggregates. First order, vehicle speed dependent, wheel disturbance due to wheel imbalances can result in excitation of different vehicle aggregates. Steering wobble refers specifically to first order road wheel excitation effects, in frequency range of 10-16 Hz, that manifest themselves as significant steering wheel torsional vibrations at highway speeds i.e. at the range of 80 km/h to 120 km/h on smooth roads. The tire, being an elastic body analogous to an array of radial springs, may exhibit variations in stiffness about its circumference; hence, it may vibrate at different frequencies due to wheel imbalance. This paper introduces dynamic steering wobble analysis methodology either using vehicle speed at Discrete (individual speeds) or by Sweep (low to high speed) method to investigate steering wobble in the virtual environment using the full vehicle MBD model. It is also suggested prior to

Pattathil, Arunmohan, Soherwardi, Omer, Iqbal, Shoaib

ED-247 (VISTAS) Gateway for Hybrid Test Systems

2018-01-194910/30/2018

Testing a full Aircraft System that includes several on-board computers, physical I/O, and communication buses requires connecting the system to adequate test benches to stimulate or monitor the I/O in a suitable manner. Next generation benches are controlled by test scenarios that reproduce flight situations that occur in a real aircraft. In many situations, it makes sense to replace one or several real computers with a virtual device. Basically, a software representation of the equipment running on a PC helps achieving Verification & Validation (V&V) tasks, even when the real systems are not all available yet. This type of setup, which combines real and virtualized systems, is called a hybrid test system. The required high level of fidelity requires that the next generation bench handles avionic I/O and buses on virtual equipment. ED-247 EUROCAE standard, also called VISTAS, which was recently brought to a mature state allows for this. The main idea behind this approach is to

Hildenbrand, Yannick

Visionary's Take: How a Vision Becomes a Company (Part 1 of 2)

1239310/17/2018

Can you become a visionary or are you born one? How does a visionary capture an opportunity and makes it a successful business? Are engineers more qualified to solve technical problems or run companies? SAE's "The Visionary's Take" addresses these and many other questions, by talking directly with those who have dared to tackle difficult engineering problems and create real-life products out of their experience. In these short episodes, Daniel Hutchinson, Founder and CTO of PostProcess Technologies talks about his experience in creating a brand-new company in the already competitive world of additive manufacturing, and specifically focusing on post-printing. Founded in 2014, PostProcess Technologies developed a unique triad of software, hardware and chemistry that works together to make the process of removing supports and surface finishing easier to deal with. This is the phase where mistakes can ruin a great manufacturing run: parts can break when their support is removed, for

Visionary's Take: How a Vision Becomes a Company (Part 2 of 2)

1239210/17/2018

Device for Measuring Efforts Generated by Tire in Steering Conditions

2018-36-011109/03/2018

Currently, large companies as well as universities have increased the studies into vehicular dynamic behavior, mainly in order to improve driver and passenger safety. Simulations with complete model vehicle have been used for these studies. The tire is one of the most important vehicular component as the only connection with the ground and responsible for transmitting all vertical, longitudinal and lateral forces, consequenetly it is the main component on the model vehicle, being crucial for the correlation between computer simulations results and field tests, This paper presents a methodology, development and construction of a device to obtain lateral forces in any combination of toe and camber angles for different conditions of normal load, the tests can be performed on any type of ground, whether dry or wet. The tire datas used as reference were obtained through an experimental test using “Flat Trac” equipment. Based on these data, the components used to measuare the tire force

Chicuta, Walace, Afonso, Bruno, Bortolussi, Roberto, Delijaicov, Sergio

Pre-Shaping Bursty Transmissions under IEEE802.1Q as a Simple and Efficient QoS Mechanism

2018-01-075604/03/2018

The automotive industry is swiftly moving toward Ethernet as the high-speed communication network for in-vehicle communication. There is nonetheless a need for protocols that go beyond what standard Ethernet has to offer in order to provide additional quality of service (QoS) to demanding applications such as advanced driver-assistance systems (ADAS) or audio/video streaming. The main protocols currently considered for that purpose are IEEE802.1Q, audio video bridging (AVB) with the credit-based shaper (CBS) mechanism (IEEE802.1Qav), and time-sensitive networking (TSN) with its time-aware shaper (TAS) (IEEE802.1Qbv). AVB/CBS and TSN/TAS both provide efficient QoS mechanisms, and they can be used in a combined manner, which offers many possibilities to the designer. Their use however requires dedicated hardware and software components and clock synchronization in the case of TAS. Previous studies have also shown that the efficiency of these protocols depends much on the application at

Villanueva, Josetxo, Migge, Jorn, Boyer, Marc, Navet, Nicolas

Scene Structure Classification as Preprocessing for Feature-Based Visual Odometry

2018-01-061004/03/2018

Cameras and image processing hardware are rapidly evolving technologies, which enable real-time applications for passenger cars, ground robots, and aerial vehicles. Visual odometry (VO) algorithms estimate vehicle position and orientation changes from the moving camera images. For ground vehicles, such as cars, indoor robots, and planetary rovers, VO can augment movement estimation from rotary wheel encoders. Feature-based VO relies on detecting feature points, such as corners or edges, in image frames as the vehicle moves. These points are tracked over frames and, as a group, estimate motion. Not all detected points are tracked since not all are found in the next frame. Even tracked features may not be correct since a feature point may map to an incorrect nearby feature point. This can depend on the driving scenario, which can include driving at high speed or in the rain or snow. This article investigates the effect of image structural content on the performance of feature tracking

Rawashdeh, Nathir A., Aladem, Mohamed, Baek, Stan, Rawashdeh, Samir A.

2021-12-29.TEST LiDAR Based Sensor Verification

2018-01-0043

04/03/2018

In the world of automated driving, sensing accuracy is of the utmost importance, and proving that your sensors can do the job is serious business. This is where ground-truth labeling has an important role in Autoliv’s validation process. Currently, annotating ground-truth data is a tedious and manual effort, involving finding the important events of interest and using the human eye to determine objects from LiDAR point cloud images. We present a workflow we developed in MATLAB to alleviate some of the pains associated with labeling point cloud data from a LiDAR sensor and the advantages that the workflow provides to the labeler. We discuss the capabilities of a tool we developed to assist users in visualizing, navigating, and annotating objects in point cloud data, tracking these objects through time over multiple frames, and then using the labeled data for developing machine learning based classifiers. We describe how the output of the labeling process is used to train deep neural

Jayaraman, Arvind, Kurtz, Nathan, Ragunathan, Balakumar, Aldrich, Ryan