Driving Tasks Research Articles

Development of an Agricultural Robot Platform for Autonomous Driving Tasks in Weeding Operations

Development of an Agricultural Robot Platform for Autonomous Driving Tasks in Weeding Operations

Evaluation of Visual Risk Perception of Automated Driving Tasks by Analyzing Gaze Pattern Dispersion

Evaluation of Visual Risk Perception of Automated Driving Tasks by Analyzing Gaze Pattern Dispersion

Facilitating Autonomous Driving Tasks with Large Language Models

Facilitating Autonomous Driving Tasks with Large Language Models

Determining the Arrangement and Cooperative Operating Control of Two Industrial Robots During Wire Driving Tasks Considering Torque Margin and Manipulability Characteristics

Determining the Arrangement and Cooperative Operating Control of Two Industrial Robots During Wire Driving Tasks Considering Torque Margin and Manipulability Characteristics

End-to-End Learning with Memory Models for Complex Autonomous Driving Tasks in Indoor Environments

The interest in autonomous vehicles has increased exponentially in recent years. While Lidar is a proven autonomous driving technology, end-to-end learning approaches have become popular as computer performance has improved. A fully end-to-end method—NVIDIA’s PilotNet has shown its ability to predict speed and steering angle with only camera images. This method achieved the Lidar-based methods’ performance in simple driving tasks. However, a significant drawback was no past spatiotemporal information, imposing an error-sensitive performance, especially in complex driving tasks. Spurred by this deficiency, this paper introduces two novel models: CNN + LSTM and CNN3D, aiming for complex autonomous driving tasks in indoor environments.

Classification of Driver Distraction Risk Levels: Based on Driver’s Gaze and Secondary Driving Tasks

Driver distraction is one of the significant causes of traffic accidents. To improve the accuracy of accident occurrence prediction under driver distraction and to provide graded warnings, it is necessary to classify the level of driver distraction. Based on naturalistic driving study data, distraction risk levels are classified using the driver’s gaze and secondary driving tasks in this paper. The classification results are then combined with road environment factors for accident occurrence prediction. Two ways are suggested to classify driver distraction risk levels in this study: one is to divide it into three levels based on the driver’s gaze and the AttenD algorithm, and the other is to divide it into six levels based on secondary driving tasks and odds ratio. Random Forest, AdaBoost, and XGBoost are used to predict accident occurrence by combining the classification results, driver characteristics, and road environment factors. The results show that the classification of distraction risk levels helps improve the model prediction accuracy. The classification based on the driver’s gaze is better than that based on secondary driving tasks. The classification method can be applied to accident risk prediction and further driving risk warning.

Relationships between Driver Errors and Delay Discounting in a Simulated Driving Task.

The majority of vehicle accidents are attributable to driver error, such as substance use, distractions, fatigue, speeding, and driving experience. Many of these driver errors are also associated with delay discounting, where individuals that excessively devalue a reward are more likely to use substances such as alcohol, cigarettes, and cocaine, and text-while-driving. The current study sought to examine a more direct association between delay discounting and driver error by providing 50 participants with a series of simulated driving tasks, along with measuring their delay discounting rates. A median-split for delay discounting rates showed that participants with high-delay discounting rates made significantly more total errors for simple driving tasks (e.g., braking and one-lane change) early during the simulation, relative to participants with low-delay discounting rates. On the other hand, high-delay discounting participants continued to make more total errors for a more complicated two-lane change driving task after multiple trials, relative to low-delay discounting participants. These results support the idea that delay discounting is a transdisease process that can significantly negatively affect a large range of health-related behaviors, including driver errors. Treatment implications for reducing driver errors are discussed.

Physiological Characteristics and Nonparametric Test for Master-Slave Driving Task’s Mental Workload Evaluation in Mountain Area Highway at Night

With the rapid development of advanced mobile intelligent terminals, driving tasks are diverse, and new traffic safety problems occur. We propose a new research on physiological characteristics and nonparametric tests for the master-slave driving task, especially for evaluation of drivers’ mental workload in mountain area highway in nighttime scenario. First, we establish the experimental platform based driving simulator and design the master-slave driving task. Second, based on the physiological data and subjective evaluation for mental workload, we use statistical methods to composite the physical changes evolution analysis in a driving simulator. Finally, we finished nonparametric test of the drivers’ psychological load and road test. The results show that in compassion with the daytime scenario, drivers should pay much effort to driving skills and risk identification in the nighttime scenario. Thus, in the same driving condition, drivers should bear the higher level of mental workload, and it has been subjected to even greater pressures and intensity of emotions.

Driving performance under alcohol in simulated representative driving tasks: an alcohol calibration study for impairments related to medicinal drugs.

Comparing drug-induced driving impairments with the effects of benchmark blood alcohol concentrations (BACs) is an approved approach to determine the clinical relevance of findings for traffic safety. The present study aimed to collect alcohol calibration data to validate findings of clinical trials that were derived from a representative test course in a dynamic driving simulator. The driving performance of 24 healthy volunteers under placebo and with 0.05% and 0.08% BACs was measured in a double-blind, randomized, crossover design. Trained investigators assessed the subjects’ driving performance and registered their driving errors. Various driving parameters that were recorded during the simulation were also analyzed. Generally, the participants performed worse on the test course (P < 0.05 for the investigators’ assessment) under the influence of alcohol. Consistent with the relevant literature, lane-keeping performance parameters were sensitive to the investigated BACs. There were significant differences between the alcohol and placebo conditions in most of the parameters analyzed. However, the total number of errors was the only parameter discriminating significantly between all three BAC conditions. In conclusion, data show that the present experimental setup is suitable for future psychopharmacological research. Thereby, for each drug to be investigated, we recommend to assess a profile of various parameters that address different levels of driving. On the basis of this performance profile, the total number of driving errors is recommended as the primary endpoint. However, this overall endpoint should be completed by a specifically sensitive parameter that is chosen depending on the effect known to be induced by the tested drug.

Comparison of Caffeine and Music as Fatigue Countermeasures in Simulated Driving Tasks

Driver fatigue is a leading cause of traffic accidents. Appropriate fatigue countermeasures can help drivers prevent operational errors and improve road safety. A review of the literature has suggested that consuming caffeine and listening to music are two commonly adopted fatigue countermeasures. This paper examines effects of the two fatigue countermeasures on subjective fatigue levels and driving performance. Differences between the two methods are also investigated. Twenty participants completed three 120-minute control, caffeine, and music sessions at the same time on three days. Subjective fatigue levels were quantified using a subjective driver fatigue score, and driving performance was measured using 16 parameters related to vehicle control ability. Initially, there were no significant differences in subjective fatigue and driving performance among three sessions. The final subjective driver fatigue score for caffeine and music sessions was significantly lower than control sessions, suggesting both inhibited subjective fatigue increase. The increment in driving performance parameters for caffeine sessions was significantly less than control and music sessions, but not significantly different between control and music sessions. Caffeine is more effective than music in inhibiting driving performance deterioration; because caffeine stimulates the central nervous system; on the other hand, music only reduces boredom and may introduce additional distraction to the driver.

The Electrocortical Correlates of Daydreaming During Simulated Driving Tasks

Driver inattention is one of the leading causes of traffic crashes. In comparison to the extensive body of research examining the attention principles that govern distraction by external stimuli, the topic of attention and distraction by daydreaming has been relatively understudied. This work used a self-caught method to examine EEG and driving behavioral correlates of daydreaming during simulated driving tasks. Participants were asked to report any time they found themselves thinking something unrelated to the driving tasks. Measures of EEG and driving behaviors were compared prior to and after each daydreaming. Results showed that three EEG band ratios, beta/(alpha+theta), beta/alpha, and beta/theta were able to discriminate daydreaming from attentive driving, and the beta/alpha band ratio outperformed the other two indices. The power band activities of EEG observed from parietal lobe sites (Pz, P3, and P4) were more sensitive to reflect subtle changes in daydreaming. The current findings suggested that these EEG band ratios could be used for early detection of daydreaming in real driving.

Subjective Fatigue and Performance Variation Correlation During Simulated Driving Tasks

During prolonged driving tasks, fatigue increases and driving performance becomes impaired. To investigate variation of driver fatigue and driving performance, 14 driving simulator test subjects were asked to complete a questionnaire designed to subjectively quantify fatigue levels. Driver fatigue was estimated in several aspects such as ability to drive safely, drowsiness, and physical fatigue symptoms. Quantitative driving performance was evaluated by measuring steering wheel, lateral position, and speed control parameters. The results showed significant increase in subjective driver fatigue and driving performance impairment following simulated driving sessions. Based on questionnaire scores, a driver fatigue indicator was developed. Analysis of this indicator revealed that subjective fatigue increased rapidly during the first 45 minute session, and more gradually during the remaining two sessions. Short breaks between sessions resulted in temporary fatigue recovery. Increased standard deviations for steering wheel rate, lateral velocity, and average speed indicated similar quantitative driving performance impairment. Comparison of subjective scores with standard deviation of acceleration indicates a possible relationship between the increased subjective fatigue and impaired driving performance.

The Use of ACT-R to Develop an Attention Model for Simple Driving Tasks

The Use of ACT-R to Develop an Attention Model for Simple Driving Tasks

A Comparative Study of Two Wayfinding Aids With Simulated Driving Tasks—GPS and a Dual-Scale Exploration Aid

Global Positioning System (GPS) is currently the most often used wayfinding aid for driving. Yet GPS is originally designed to provide a driving guide rather than to help users gain spatial knowledge. Accordingly, GPS might be less usable in situations where spatial knowledge is required. This study experimentally compared two wayfinding aids using simulated driving tasks in a virtual environment: a simulated GPS and a dual-scale exploration aid (DSEA). The DSEA, which provides two levels of details—both detailed and contextual information—was proposed to support participants in finding and selecting routes by themselves. The results show that although DSEA was less helpful in leading participants to their destination and corresponded to more turning errors in simulated driving, it was more useful for the corresponding participants to establish spatial awareness and a cognitive map. The influence of participants' spatial ability test score on wayfinding performance was measured and discussed. The proposed DSEA design and experimental results show some indications for designing new wayfinding aids aimed at reducing wayfinding errors and constructing cognitive maps while still providing easy navigation.

Muscle Activity of Upper Limbs During Bimanual Driving Tasks

Muscle Activity of Upper Limbs During Bimanual Driving Tasks

Behavioral and Cardiovascular Responses to Frustration During Simulated Driving Tasks in Young Adults With and Without Attention Disorder Symptoms

Objective: The present study examined the role of negative emotions on driving performance in relation to ADHD, by comparing young adults scoring high on measures of ADHD (n = 20) with a control group (n = 22). Method: The authors used cardiorespiratory physiological measures, simulated driving behavior, and self-report to examine how participants with high and low ADHD symptoms responded to frustration and to determine how frustration affected simulated driving performance. Results: Groups did not differ in operational driving skills, but participants with high ADHD symptoms reported more frustration and exhibited more impairment at the tactical level of driving performance than the controls. There was significant suppression of respiratory sinus arrhythmia from resting baseline during tasks, but it did not differ between groups during driving. Conclusion: This article proposes that remedial driver training for ADHD populations should focus more on the control of negative emotions rather than on attention or fundamental driving skills. (J. of Att. Dis. 2012; 16(6) 478-490)

On the Research of Control and Sequence Dynamics of Driving Tasks: Tools and Prospects.

Event Abstract Back to Event On the Research of Control and Sequence Dynamics of Driving Tasks: Tools and Prospects. Inaki Rano1*, Sebastian Noth1, Gregor Schöner1 and Johann Edelbrunner2 1 Ruhr-Universitaet-Bochum, Germany 2 NISYS GmbH, Germany Big research efforts nowadays focus on modeling human drivers in order to improve safety and achieve smooth traffic flows. While dynamic models exist for driving tasks at the control level, models for lane keeping, car following and lane change, at the tactical level, the sequencing of these tasks is commonly performed as static finite state machines [Song et al, 2000]. Our aim is to bring light to the sequencing dynamics of the tactical level of human driving. This is a challenging task that requires accurate models of the control level tasks as performed by humans. This poster presents the tools and methods we will use to obtain complete models of human driving behavior. While most of the models are obtained from data where the human driver interacts with simulated drivers, we propose a multi-driver configuration to obtain more realistic driver interaction. We set up a multi-driver laboratory with ten independent cabins and implemented a realistic multi-driver simulator where all the drivers interact while driving on the same simulated road. All vehicle and environment state data relevant to model a driver behavior can be stored, the global status of the simulated cars can be monitored on-line through the local network and instructions can be delivered to individual drivers. Therefore, our simulator allows us to establish or force specific traffic situations, that could be impermissible in real life, while still having human drivers involved to gather relevant control and sequencing data sets. Based on these data sets and using state of the art control level models we plan to develop a methodology to build human-like driver models that can be used for testing and validating Advanced Driving Assistance Systems (ADAS). Once the control level is fully identified we will design and carry out experiments to model the sequence and decision dynamics in normal driving situations [Pellecchia et al, 2005]. Early experiments on car following control have been already performed and we are experimenting with a driver model for steering control that includes sensoriomotor aspects of human driving [Sentouh et al, 2009]. References A. Pellecchia, C. Igel, J. Edelbrunner and G. Schöner. “Making Driver Modeling Attractive” IEEE Intelligent Systems, pp 8-12. 2005. C. Sentouh, P Chevrel, F. Mars and F. Claveau. “A Sensoriomotor Driver Model for Steering Control”. Proceedings of the 2009 IEEE International Conference on Systems, Man and Cybernetics. 2009. B. Song, D. Delorme and J. VanderWerf. “Cognitive and Hybrid Model of Human Driver”. Proceedings of the IEEE Intelligent Vehicles Symposium 2000. Keywords: data analysis, driving modeling, machine learning Conference: BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011, Freiburg, Germany, 4 Oct - 6 Oct, 2011. Presentation Type: Poster Topic: data analysis and machine learning (please use "data analysis and machine learning" as keyword) Citation: Rano I, Noth S, Schöner G and Edelbrunner J (2011). On the Research of Control and Sequence Dynamics of Driving Tasks: Tools and Prospects.. Front. Comput. Neurosci. Conference Abstract: BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011. doi: 10.3389/conf.fncom.2011.53.00075 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 23 Aug 2011; Published Online: 04 Oct 2011. * Correspondence: Dr. Inaki Rano, Ruhr-Universitaet-Bochum, Bochum, Germany, inaki.rano@gmail.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Inaki Rano Sebastian Noth Gregor Schöner Johann Edelbrunner Google Inaki Rano Sebastian Noth Gregor Schöner Johann Edelbrunner Google Scholar Inaki Rano Sebastian Noth Gregor Schöner Johann Edelbrunner PubMed Inaki Rano Sebastian Noth Gregor Schöner Johann Edelbrunner Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Analysis of Subjective Body Discomfort Ratings during Simulated Prolonged Driving Tasks: What Measures are most Effective?

Subjective discomfort ratings are a common assessment technique in human factors and ergonomics, and there exist a number of different methods for analyzing ratings (e.g., mean, median, maximum rating, etc.). The objective of this research was to evaluate multiple methods for analyzing body discomfort ratings. Perceived discomfort of eight participants was measured across ten body parts (buttock, left buttock, right buttock, lower back, upper back, neck, shoulder, eye, thigh and whole body) during 2-hour simulated driving tasks at 3 backrest angles (105°, 120°, 135°). Discomfort ratings were collected every 15 minutes using a modified Borg CR-scale. The time weighted discomfort (TWD) average of was found to be more sensitive to backrest angle changes than other measures considered. In addition, factor analysis revealed different methods provided different groupings of body parts, and the method selected for analyzing subjective discomfort ratings should be selected based on the objective of the study.

Analysis of Subjective Body Discomfort Ratings during Simulated Prolonged Driving Tasks: What Measures are most Effective?

Subjective discomfort ratings are a common assessment technique in human factors and ergonomics, and there exist a number of different methods for analyzing ratings (e.g., mean, median, maximum rating, etc.). The objective of this research was to evaluate multiple methods for analyzing body discomfort ratings. Perceived discomfort of eight participants was measured across ten body parts (buttock, left buttock, right buttock, lower back, upper back, neck, shoulder, eye, thigh and whole body) during 2-hour simulated driving tasks at 3 backrest angles (105°, 120°, 135°). Discomfort ratings were collected every 15 minutes using a modified Borg CR-scale. The time weighted discomfort (TWD) average of was found to be more sensitive to backrest angle changes than other measures considered. In addition, factor analysis revealed different methods provided different groupings of body parts, and the method selected for analyzing subjective discomfort ratings should be selected based on the objective of the study.

Effects of Age on Spinal Rotation during a Driving Task

Many older adults experience declines in their flexibility, which in turn can affect their safe operation of a vehicle and their driving performance. Previous research has shown that reduced trunk flexibility is associated with greater accident risks. To explore further questions about and measures of spinal flexibility, differences in spinal flexibility between younger and older drivers were explored in two contexts: a stretching exercise and a real driving maneuver. Results indicated that younger drivers had on average greater stretch spinal flexibility than older drivers, but that during the driving maneuver, study participants did whatever necessary, such as bracing themselves on the seatback or steering wheel, to overcome any flexibility limitations to complete the driving task. Using a multivariate regression mode, the degree of spinal rotation in the stretch and driving tasks were significantly affected by age and by the use of the vehicle to brace while rotating. In the stretch tasks, self-reported health and driving frequency were jointly statistically significant predictors of degree of rotation. In terms of driving, however, the use of bracing suggests that drivers may have evolved strategies to compensate for any physical limitations they may experience to continue driving.