Criteria

Text:
Topic:
Display:

Results

Viewing 91 to 120 of 11129
2017-03-28
Technical Paper
2017-01-1400
Keyu Qian, Gangfeng Tan, Renjie Zhou, Binyu Mei, Wanyang XIA
Abstract Downhill mountain roads are the accident prone sections because of their complexity and variety. Drivers rely more on driving experience and it is very easy to cause traffic accidents due to the negligence or the judgment failure. Traditional active safety systems, such as ABS, having subjecting to the driver's visual feedback, can’t fully guarantee the downhill driving safety in complex terrain environments. To enhance the safety of vehicles in the downhill, this study combines the characteristics of vehicle dynamics and the geographic information. Thus, through which the drivers could obtain the safety speed specified for his/her vehicle in the given downhill terrains and operate in advance to reduce traffic accidents due to driver's judgment failure and avoid the brake overheating and enhance the safety of vehicles in the downhill.
2017-03-28
Technical Paper
2017-01-1399
Bin Wu, Xichan Zhu, Jianping Shen, Xuejun Cang, Lin li
Abstract A driver steering model for emergency lane change based on the China naturalistic driving data is proposed in this paper. The steering characteristic of three phases is analyzed. Using the steering primitive fitting by Gaussian function, the steering behaviors in collision avoidance and lateral movement phases can be described, and the stabilization steering principle of yaw rate null is found. Based on the steering characteristic, the near and far aim point used in steering phases is analyzed. Using the near and far aim point correction model, a driver steering model for emergency lane change is established. The research results show that the driver emergency steering model proposed in this paper performs well when explaining realistic steering behavior, and this model can be used in developing the ADAS system.
2017-03-28
Journal Article
2017-01-1472
Niels Pasligh, Robert Schilling, Marian Bulla
Abstract Rivets, especially self-piercing rivets (SPR), are a primary joining technology used in aluminum bodied vehicles. SPR are mechanical joining elements used to connect sheets to create a body in white (BiW) structure. To ensure the structural performance of a vehicle in crash load cases it is necessary to describe physical occurring failure modes under overloading conditions in simulations. One failure mode which needs to be predicted precisely by a crash simulation is joint separation. Within crash simulations a detailed analysis of a SPR joint would require a very high computational effort. The conflict between a detailed SPR joint and a macroscopic vehicle model needs to be solved by developing an approach that can handle an accurate macroscopic prediction of SPR behavior with a defined strength level with less computational effort. One approach is using a cohesive material model for a SPR connection.
2017-03-28
Technical Paper
2017-01-1471
Xiao Luo, Wenjing Du, Hao Li, Peiyu LI, Chunsheng Ma, Shucai Xu, Jinhuan Zhang
Abstract Occupant restraint systems are developed based on some baseline experiments. While these experiments can only represent small part of various accident modes, the current procedure for utilizing the restraint systems may not provide the optimum protection in the majority of accident modes. This study presents an approach to predict occupant injury responses before the collision happens, so that the occupant restraint system, equipped with a motorized pretensioner, can be adjusted to the optimal parameters aiming at the imminent vehicle-to-vehicle frontal crash. The approach in this study takes advantage of the information from pre-crash systems, such as the time to collision, the relative velocity, the frontal overlap, the size of the vehicle in the front and so on. In this paper, the vehicle containing these pre-crash features will be referred to as ego vehicle. The information acquired and the basic crash test results can be integrated to predict a simplified crash pulse.
2017-03-28
Technical Paper
2017-01-1473
Ling Zheng, Yinan Gao, Zhenfei Zhan, Yinong Li
Abstract Several surrogate models such as response surface model and radial basis function and Kriging models are developed to speed the optimization design of vehicle body and improve the vehicle crashworthiness. The error analysis is used to investigate the accuracy of different surrogate models. Furthermore, the Kriging model is used to fit the model of B-pillar acceleration and foot well intrusion. The response surface model is used to fit the model of the entire vehicle mass. These models are further used to calculate the acceleration response in B-pillar, foot well intrusion and vehicle mass instead of the finite element model in the optimization design of vehicle crashworthiness. A multi-objective optimization problem is formulated in order to improve vehicle safety performance and keep its light weight. The particle swarm method is used to solve the proposed multi-objective optimization problem.
2017-03-28
Technical Paper
2017-01-1474
Raed E. El-Jawahri, Agnes Kim, Dean Jaradi, Rich Ruthinowski, Kevin Siasoco, Cortney Stancato, Para Weerappuli
Abstract Sled tests simulating full-frontal rigid barrier impact were conducted using the Hybrid III 5th female and the 50th male anthropomorphic test devices (ATDs). The ATDs were positioned in the outboard rear seat of a generic small car environment. Two belt configurations were used: 1) a standard belt with no load limiter or pre-tensioner and 2) a seatbelt with a 4.5 kN load-limiting retractor with a stop function and a retractor pre-tensioner (LL-PT). In the current study, the LL-PT belt system reduced the peak responses of both ATDs. Probabilities of serious-to-fatal injuries (AIS3+), based on the ATDs peak responses, were calculated using the risk curves in NHTSA’s December 2015 Request for Comments (RFC) proposing changes to the United States New Car Assessment Program (US-NCAP). Those probabilities were compared to the injury rates (IRs) observed in the field on point estimate basis.
2017-03-28
Journal Article
2017-01-1465
William R. Bussone, Joseph Olberding, Michael Prange
Abstract SAE J211 provides no definitive specification as to the appropriate procedures for filtering angular rate sensor data prior to differentiation into angular acceleration data, especially for impact data. Accordingly, a 3-2-2-2 array (nine-accelerometer-package or NAP) of linear accelerometers and a triaxial angular rate sensor were mounted into a Hybrid III 50th-percentile-male ATD headform and compared in a variety of impact events and multibody simulations. Appropriate low-pass digital filter cutoff frequencies for differentiating the angular rate sensor data into angular accelerations were sought via residual analysis in accordance with current SAE J211 guidelines.
2017-03-28
Technical Paper
2017-01-1466
Claudia De La Torre, Ravi Tangirala, Michael Guerrero, Andreas Sprick
Abstract Studies in the EU and the USA found higher deformation and occupant injuries in frontal crashes when the vehicle was loaded outboard (frontal crashes with a small overlap). Due to that, in 2012 the IIHS began to evaluate the small overlap front crashworthiness in order to solve this problem.A set of small overlap tests were carried out at IDIADA’s (Institute of Applied Automotive Research ) passive safety laboratory and the importance of identifying the forces applied in each structural element involved in small overlap crash were determined. One of the most important structural elements in the small overlap test is the wheel. Its interaction in a small overlap crash can modify the vehicle interaction at the crash, which at the laboratory the interaction is with a barrier. That interaction has a big influence at the vehicle development and design strategy.
2017-03-28
Technical Paper
2017-01-1468
Do Hoi KIm
Previous work identified a relationship between vehicle drop and dummy injury under the high-speed frontal impact condition [1]. The results showed that vehicle drop greater than 60mm made the dummy injury worse. Moreover, that work identified the front side member as the crucial part affecting the vehicle drop. In this study, the body structure mechanism was studied to reduce vehicle drop by controlling the front side member, shotgun, and A-pillar. By analyzing full vehicles, it was recognized that the arch shape of the front side member was very important. Furthermore, if the top of the arch shape of front side member, shotgun, and A-pillar were connected well, then the body deformation energy could lift the lower part of A-pillar, effectively reducing vehicle drop. This structure design concept is named “Body Lift Structure” (BLS). The BLS was applied to B and C segment platforms. Additionally, a “Ring” shape was defined by the front side member, dash panel, and A-pillar.
2017-03-28
Technical Paper
2017-01-1460
Nitesh Jadhav, Linda Zhao, Senthilkumar Mahadevan, Bill Sherwood, Krishnakanth Aekbote, Dilip Bhalsod
Abstract The Pelvis-Thorax Side Air Bag (PTSAB) is a typical restraint countermeasure offered for protection of occupants in the vehicle during side impact tests. Currently, the dynamic performance of PTSAB for occupant injury assessment in side impact is limited to full-vehicle evaluation and sled testing, with limited capability in computer aided engineering (CAE). The widely used CAE method for PTSAB is a flat bag with uniform pressure. The flat PTSAB model with uniform pressure has limitations because of its inability to capture airbag deployment during gap closure which results in reduced accuracy while predicting occupant responses. Hence there is a need to develop CAE capability to enhance the accuracy of prediction of occupant responses to meet performance targets in regulatory and public domain side impact tests. This paper describes a new CAE methodology for assessment of PTSAB in side impact.
2017-03-28
Technical Paper
2017-01-1462
Haiyan Li, Xin Jin, Hongfei Zhao, Shihai Cui, Binhui Jiang, King H. Yang
Abstract Computational human body models, especially detailed finite element models are suitable for investigation of human body kinematic responses and injury mechanism. A real-world lateral vehicle-tree impact accident was reconstructed by using finite element method according to the accident description in the CIREN database. At first, a baseline vehicle FE model was modified and validated according to the NCAP lateral impact test. The interaction between the car and the tree in the accident was simulated using LS-Dyna software. Parameters that affect the simulation results, such as the initial pre-crash speed, impact direction, and the initial impact location on the vehicle, were analyzed. The parameters were determined by matching the simulated vehicle body deformations and kinematics to the accident reports.
2017-03-28
Journal Article
2017-01-1463
Xianping Du, Feng Zhu, Clifford C. Chou
Abstract A new design methodology based on data mining theory has been proposed and used in the vehicle crashworthiness design. The method allows exploring the big dataset of crash simulations to discover the underlying complicated relationships between response and design variables, and derive design rules based on the structural response to make decisions towards the component design. An S-shaped beam is used as an example to demonstrate the performance of this method. A large amount of simulations are conducted and the results form a big dataset. The dataset is then mined to build a decision tree. Based on the decision tree, the interrelationship among the geometric design variables are revealed, and then the design rules are derived to produce the design cases with good energy absorbing capacity. The accuracy of this method is verified by comparing the data mining model prediction and simulation data.
2017-03-28
Technical Paper
2017-01-1457
Jingwen Hu, Nichole Ritchie Orton, Rebekah Gruber, Ryan Hoover, Kevin Tribbett, Jonathan Rupp, Dave Clark, Risa Scherer, Matthew Reed
Abstract Among all the vehicle rollover test procedures, the SAE J2114 dolly rollover test is the most widely used. However, it requires the test vehicle to be seated on a dolly with a 23° initial angle, which makes it difficult to test a vehicle over 5,000 kg without a dolly design change, and repeatability is often a concern. In the current study, we developed and implemented a new dynamic rollover test methodology that can be used for evaluating crashworthiness and occupant protection without requiring an initial vehicle angle. To do that, a custom cart was designed to carry the test vehicle laterally down a track. The cart incorporates two ramps under the testing vehicle’s trailing-side tires. In a test, the cart with the vehicle travels at the desired test speed and is stopped by a track-mounted curb.
2017-03-28
Technical Paper
2017-01-1453
Sudip Sankar Bhattacharjee, Shahuraj Mane, Harsha Kusnoorkar, Sean Hwang, Matt Niesluchowski
Abstract Pedestrian protection assessment methods require multiple head impact tests on a vehicle’s hood and other front end parts. Hood surfaces are often lifted up by using pyrotechnic devices to create more deformation space prior to pedestrian head impact. Assessment methods for vehicles equipped with pyrotechnic devices must also validate that the hood deployment occurs prior to head impact event. Estimation of pedestrian head impact time, thus, becomes a critical requirement for performance validation of deployable hood systems. In absence of standardized physical pedestrian models, Euro NCAP recommends a list of virtual pedestrian models that could be used by vehicle manufacturers, with vehicle FEA (Finite Element Analysis) models, to predict the potential head impact time along the vehicle front end profile. FEA simulated contact time is used as target for performance validation of sensor and pyrotechnic deployable systems.
2017-03-28
Technical Paper
2017-01-1458
Tack Lam, B. Johan Ivarsson
Abstract Disc herniations in the spine are commonly associated with degenerative changes, and the prevalence increases with increasing age. With increasing number of older people on U.S. roads, we can expect an increase in clinical findings of disc herniations in occupants involved in rear impacts. Whether these findings suggest a causal relationship is the subject of this study. We examined the reported occurrence of all spine injuries in the National Automotive Sampling System - Crashworthiness Data System (NASS-CDS) database from 1993 to 2014. There were over 4,000 occupants that fit the inclusion criteria. The findings in this study showed that, in the weighted data of 2.9 million occupants, the most common spine injury is an acute muscle strain of the neck, followed by strain of the low back. The delta-V of a rear impact is a reliable indicator of the rate of acute cervical strain in occupants exposed to such impacts.
2017-03-28
Technical Paper
2017-01-1446
Allen Charles Bosio, Paul Marable, Marcus Ward, Bradley Staines
Abstract A dual-chambered passenger airbag was developed for the 2011 USNCAP to minimize neck loading for the belted 5th female dummy while restraining the unbelted 50th dummy for FMVSS208. This unique, patented design adaptively controlled venting between chambers based on occupant stature. A patented pressure-responsive vent on the second chamber permitted aspiration into the second chamber before a delayed outflow to the environment. The delayed flow through the pressure-responsive vent from the second chamber acted like a pressure-limiting membrane vent to advantageously reduce the injury assessment values for the HIC and the Nij for the 5th female dummy.
2017-03-28
Technical Paper
2017-01-1448
Kevin Pline, Derek Board, Nirmal Muralidharan, Srinivasan Sundararajan, Eric Eiswerth, Katie Salciccioli
Abstract Ford Motor Company introduced the automotive industry’s first second row inflatable seatbelt system in 2011. The system is currently available in the outboard seating positions of the second row of several Ford and Lincoln models. An important consideration for this system is the interaction with child restraint systems (CRS) when it is used to install a CRS or used in conjunction with belt position booster. A novel test methodology to assess the interaction of CRS with Ford and Lincoln inflatable seatbelts through frontal impact sled tests is explained. Details of test methods including construction of additional fixtures and hardware are highlighted. This procedure is designed to enable test labs capable of running Federal Motor Vehicle Safety Standard (FMVSS) 213 testing to adapt this test method, with minimal fabrication, by utilizing existing test benches.
2017-03-28
Journal Article
2017-01-1450
Daniel Perez-Rapela, Jason Forman, Haeyoung Jeon, Jeff Crandall
Abstract Current state-of-the-art vehicles implement pedestrian protection features that rely on pedestrian detection sensors and algorithms to trigger when impacting a pedestrian. During the development phase, the vehicle must “learn” to discriminate pedestrians from the rest of potential impacting objects. Part of the training data used in this process is often obtained in physical tests utilizing legform impactors whose external biofidelity is still to be evaluated. This study uses THUMS as a reference to assess the external biofidelity of the most commonly used impactors (Flex-PLI, PDI-1 and PDI-2). This biofidelity assessment was performed by finite element simulation measuring the bumper beam forces exerted by each surrogate on a sedan and a SUV. The bumper beam was divided in 50 mm sections to capture the force distribution in both vehicles. This study, unlike most of the pedestrian-related literature, examines different impact locations and velocities.
2017-03-28
Journal Article
2017-01-1445
Kevin Pline, Derek Board, Nirmal Muralidharan, Srinivasan Sundararajan, Eric Eiswerth, Katie Salciccioli, Noelle Baker
Abstract Ford Motor Company introduced the inflatable seatbelt system in 2011 and the system is now available in the second row of several Ford and Lincoln models. An important consideration is the interaction of the inflatable seatbelt system with child restraint systems (CRS). A comprehensive series of frontal impact sled tests, using a standardized test method, was conducted to compare the performance of rear-facing-only CRS installed using an inflatable seatbelt to the same CRS installed using a standard seatbelt. CRS models from several manufacturers in the North American market were tested both with and without their bases. CRABI 12 month old or Hybrid III 3 year old anthropomorphic test devices (ATD) were restrained in the CRS. The assessment included the ability to achieve a satisfactory installation with the inflatable seatbelt, comparisons of ATD and CRS kinematics, CRS system integrity, and comparisons of ATD responses.
2017-03-28
Technical Paper
2017-01-1439
John C. Steiner, Christopher Armstrong, Tyler Kress, Tom Walli, Ralph J. Gallagher, Justin Ngo, Andres Silva
Abstract The use of the United States’ Global Positioning System (GPS) to assist with the management of large commercial fleets using telematics is becoming commonplace. Telematics generally refers to the use of wireless devices to transmit data in real time back to an organization. When tied to the GPS system telematics can be used to track fleet vehicle movements, and other parameters. GPS tracking can assist in developing more efficient and safe operations by refining and streamlining routing and operations. GPS based fleet telematics data is also useful for reducing unnecessary engine idle times and minimizing fuel consumption. Driver performance and policy adherence can be monitored, for example by transmitting data regarding seatbelt usage when there is vehicle movement. Despite the advantages for fleet management, there are limitations in the logged data for position and speed that may affect the utility of the system for analysis and reconstruction of traffic collisions.
2017-03-28
Technical Paper
2017-01-1438
Felix Lee, Peter Xing, Mike Yang, Janice Lee, Craig Wilkinson, Gunter P. Siegmund
Abstract The repeatability and accuracy of front and rear speed changes reported by Toyota’s Airbag Control Modules (ACMs) have been previously characterized for low-severity collisions simulated on a linear sled. The goals of the present study are (i) to determine the accuracy and repeatability of Toyota ACMs in mid-severity crashes, and (ii) to validate the assumption that ACMs function similarly for idealized sled pulses and full-scale vehicle-to-barrier and vehicle-to-vehicle crashes. We exposed three Toyota Corollas to a series of full-scale aligned frontal and rear-end crash tests with speed changes (ΔV) of 4 to 12 km/h. We then characterized the response of another 16 isolated Toyota ACMs from three vehicle models (Corolla, Prius and Camry) and 3 generations (Gen 1, 2 and 3) using idealized sled pulses and replicated vehicle-to-vehicle and vehicle-to-barrier pulses in both frontal and rear-end crashes (ΔV = 9 to 17 km/h).
2017-03-28
Technical Paper
2017-01-1433
Enrique Bonugli, Joseph Cormier, Matthew Reilly, Lars Reinhart
The purpose of this study was to determine the frictional properties between the exterior surface of a motorcycle helmet and ‘typical’ roadway surfaces. Motorcycle helmet impacts into asphalt and concrete surfaces were compared to abrasive papers currently recommended by government helmet safety standards and widely used by researchers in the field of oblique motorcycle helmet impact testing. A guided freefall test fixture was utilized to obtain nominal impact velocities of 5, 7 and 9 m/s. The impacting surfaces were mounted to an angled anvil to simulate an off-centered oblique collision. Helmeted Hybrid III ATD head accelerations and impact forces were measured for each test. The study was limited to a single helmet model and impact angle (30 degrees). Analysis of the normal and tangential forces imparted to the contact surface indicated that the frictional properties of abrasive papers differ from asphalt and concrete in magnitude, duration and onset.
2017-03-28
Technical Paper
2017-01-1437
William Bortles, Sean McDonough, Connor Smith, Michael Stogsdill
Abstract The data obtained from event data recorders found in airbag control modules, powertrain control modules and rollover sensors in passenger vehicles has been validated and used to reconstruct crashes for years. Recently, a third-party system has been introduced that allows crash investigators and reconstructionists to access, preserve and analyze data from infotainment and telematics systems found in passenger vehicles. The infotainment and telematics systems in select vehicles retain information and event data from cellular telephones and other devices connected to the vehicle, vehicle events and navigation data in the form of tracklogs. These tracklogs provide a time history of a vehicle’s geolocation that may be useful in investigating an incident involving an automobile or reconstructing a crash. This paper presents an introduction to the type of data that may be retained and the methods for performing data acquisitions.
2017-03-28
Technical Paper
2017-01-1436
Edward Fatzinger, Jon Landerville
Abstract Various electronic control units from Kawasaki Ninja 300 motorcycles were tested in-situ in order to heuristically examine the capabilities and behavior of the event data recorders (EDR). The relevant hexadecimal data was downloaded from the ECU and translated using known and historically proven applications. The hexadecimal translations were then confirmed using data acquisition systems as well as the Kawasaki Diagnostic Software (KDS). Numerous tests were performed to establish the algorithms which cause the EDR to record data. It was determined that the EDR recording “trigger” was caused by the activation of the tip-over sensor, which in turn shuts the engine off. In addition, specific conditions must be met with regards to the rear wheel rotation prior to engine shut-down.
2017-03-28
Journal Article
2017-01-0118
Yang Wang, Ankit Goila, Rahul Shetty, Mahdi Heydari, Ambarish Desai, Hanlong Yang
Regarding safety, obstacle avoidance has been considered as one of the most important features among ADAS systems for ground vehicles. However, the implementation of obstacle avoidance functions to commercial vehicles are still under progress. In this paper, we demonstrate a complete process of obstacle avoidance strategy for unmanned ground vehicle and implement the strategy on the self-developed Arduino based RC Car. In this process, the sensor LIDAR was used to detect the obstacles on the fore-path. Based on the measured LIDAR data, an optimized path is automatically generated with accommodation of current car position, obstacle locations, car operation capability and global environmental restrictions. The path planning is updated in real time while new or changing obstacles being detected. This algorithm is validated by the simulation results with the RC car. The comparison will be discussed at the end of this paper.
2017-03-28
Technical Paper
2017-01-0113
Vaclav Jirovsky
Abstract Today's vehicles are being more often equipped with systems, which are autonomously influencing the vehicle behavior. More systems of the kind and even fully autonomous vehicles in regular traffic are expected by OEMs in Europe around year 2025. Driving is highly multitasking activity and human errors emerge in situations, when he is unable to process and understand the essential amount of information. Future autonomous systems very often rely on some type of inter-vehicular communication. This shall provide the vehicle with higher amount of information, than driver uses in his decision making process. Therefore, currently used 1-D quantity TTC (time-to-collision) will become inadequate. Regardless the vehicle is driven by human or robot, it’s always necessary to know, whether and which reaction is necessary to perform. Adaptable autonomous vehicle systems will need to analyze the driver’s situation awareness level.
2017-03-28
Technical Paper
2017-01-0116
Ankit Goila, Ambarish Desai, Feng Dang, Jian Dong, Rahul Shetty, Rakesh Babu Kailasa, Mahdi Heydari, Yang Wang, Yue Sun, Manikanta Jonnalagadda, Mohammed Alhasan, Hanlong Yang, Katherine R. Lastoskie
ADAS features development involves multidisciplinary technical fields, as well as extensive variety of different sensors and actuators, therefore the early design process requires much more resources and time to collaborate and implement. This paper will demonstrate an alternative way of developing prototype ADAS concept features by using remote control car with low cost hobby type of controllers, such as Arduino Due and Raspberry Pi. Camera and a one-beam type Lidar are implemented together with Raspberry Pi. OpenCV free open source software is also used for developing lane detection and object recognition. In this paper, we demonstrate that low cost frame work can be used for the high level concept algorithm architecture, development, and potential operation, as well as high level base testing of various features and functionalities. The developed RC vehicle can be used as a prototype of the early design phase as well as a functional safety testing bench.
2017-03-28
Journal Article
2017-01-0112
Mingming Zhao, Hongyan Wang, Junyi Chen, Xiao Xu, Yutong He
Abstract Rear-end accident is one of the most important collision modes in China, which often leads to severe accident consequences due to the high collision velocity. Autonomous Emergency Braking (AEB) system could perform emergency brake automatically in dangerous situation and mitigate the consequence. This study focused on the analysis of the rear-end accidents in China in order to discuss about the parameters of Time–to-Collision (TTC) and the comprehensive evaluation of typical AEB. A sample of 84 accidents was in-depth investigated and reconstructed, providing a comprehensive set of data describing the pre-crash matrix. Each accident in this sample is modeled numerically by the simulation tool PC-Crash. In parallel, a model representing the function of an AEB system has been established. This AEB system applies partial braking when the TTC ≤ TTC1 and full braking when the TTC ≤ TTC2.
2017-03-28
Technical Paper
2017-01-0110
Hao Sun, Weiwen Deng, Chen Su, Jian Wu
Abstract The ability to recognize traffic vehicles’ lane change maneuver lays the foundation for predicting their long-term trajectories in real-time, which is a key component for Advanced Driver Assistance Systems (ADAS) and autonomous automobiles. Learning-based approach is powerful and efficient, such approach has been used to solve maneuver recognition problems of the ego vehicles on conventional researches. However, since the parameters and driving states of the traffic vehicles are hardly observed by exteroceptive sensors, the performance of traditional methods cannot be guaranteed. In this paper, a novel approach using multi-class probability estimates and Bayesian inference model is proposed for traffic vehicle lane change maneuver recognition. The multi-class recognition problem is first decomposed into three binary problems under error correcting output codes (ECOC) framework.
2017-03-28
Technical Paper
2017-01-0096
Valentin Soloiu, Bernard Ibru, Thomas Beyerl, Tyler Naes, Charvi Popat, Cassandra Sommer, Brittany Williams
Abstract An important aspect of an autonomous vehicle system, aside from the crucial features of path following and obstacle detection, is the ability to accurately and effectively recognize visual cues present on the roads, such as traffic lanes, signs and lights. This ability is important because very few vehicles are autonomously driven, and must integrate with conventionally operated vehicles. An enhanced infrastructure has yet to be available solely for autonomous vehicles to more easily navigate lanes and intersections non-visually. Recognizing these cues efficiently can be a complicated task as it not only involves constantly gathering visual information from the vehicle’s surroundings, but also requires accurate real time processing. Ambiguity of traffic control signals challenges even the most advanced computer decision making algorithms. The vehicle then must keep a predetermined position within its travel lane based on its interpretation of its surroundings.
Viewing 91 to 120 of 11129