The development of autonomous vehicles has become one of the greatest research endeavors in recent years. These vehicles rely on many complex systems working in tandem to make decisions. For practical use and safety r...The development of autonomous vehicles has become one of the greatest research endeavors in recent years. These vehicles rely on many complex systems working in tandem to make decisions. For practical use and safety reasons, these systems must not only be accurate, but also quickly detect changes in the surrounding environment. In autonomous vehicle research, the environment perception system is one of the key components of development. Environment perception systems allow the vehicle to understand its surroundings. This is done by using cameras, light detection and ranging (LiDAR), with other sensor systems and modalities. Deep learning computer vision algorithms have been shown to be the strongest tool for translating camera data into accurate and safe traversability decisions regarding the environment surrounding a vehicle. In order for a vehicle to safely traverse an area in real time, these computer vision algorithms must be accurate and have low latency. While much research has studied autonomous driving for traversing well-structured urban environments, limited research exists evaluating perception system improvements in off-road settings. This research aims to investigate the adaptability of several existing deep-learning architectures for semantic segmentation in off-road environments. Previous studies of two Convolutional Neural Network (CNN) architectures are included for comparison with new evaluation of Vision Transformer (ViT) architectures for semantic segmentation. Our results demonstrate viability of ViT architectures for off-road perception systems, having a strong segmentation accuracy, lower inference speed and memory footprint compared to previous results with CNN architectures.展开更多
Increasing frame torsional stiffness of off-road vehicle will lead to the decrease of body torsional deformation, but the increase of torsional loads of frame and suspension system and the decrease of wheel adhesive w...Increasing frame torsional stiffness of off-road vehicle will lead to the decrease of body torsional deformation, but the increase of torsional loads of frame and suspension system and the decrease of wheel adhesive weight. In severe case, a certain wheel will be out of contact with road surface. Appropriate matching of body, frame and suspension torsional stiffnesses is a difficult problem for off-road vehicle design. In this paper, these theoretically analytic models of the entire vehicle, body, frame and suspension torsional stiffness are constructed based on the geometry and mechanism of a light off-road vehicle＇s body, frame and suspension. The body and frame torsional stiffnesses can be calculated by applying body CAE method, meanwhile the suspension＇s rolling angle stiffness can be obtained by the bench test of the suspension＇s elastic elements. Through fixing the entire vehicle, using sole timber to raise wheels to simulate the road impact on a certain wheel, the entire vehicle torsional stiffness can be calculated on the geometric relation and loads of testing. Finally some appropriate matching principles of the body, frame and suspension torsional stiffness are summarized according to the test and analysis results. The conclusion can reveal the significance of the suspension torsional stiffness on off-road vehicle＇s torsion-absorbing capability. The results could serve as a reference for the design of other off-road vehicles.展开更多
This paper presents a software framework for off-road autonomous robot navigation system.With the requirements of accurate terrain perception and instantaneous obstacles detection,one navigation software framework was...This paper presents a software framework for off-road autonomous robot navigation system.With the requirements of accurate terrain perception and instantaneous obstacles detection,one navigation software framework was advanced based on the principles of "three layer architecture" of intelligence system.Utilized the technologies of distributed system,machine learning and multiple sensor fusion,individual functional module was discussed.This paper aims to provide a framework reference for autonomous robot navigation system design.展开更多
The controllable suspension system can improve the performances of off-road vehicles both on road and cross-country. So far, four controllable suspensions, that is, body height control, active, semi-active and slow-ac...The controllable suspension system can improve the performances of off-road vehicles both on road and cross-country. So far, four controllable suspensions, that is, body height control, active, semi-active and slow-active suspensions, have been developed. For off-road vehicles, the slow-active suspension and the semi-active suspension which have controllable stiffness, damping and body height are more appropriate to use. For many years, some control methodologies for controllable suspension systems have been developed along with the development of modern control theory, and two or more original control methods are integrated as a new control method. Today, for military or civilian off-road vehicles, the R&D of controllable suspension systems is ongoing.展开更多
Run-off-road crashes in the United States have become a major cause of serious injuries and fatalities. A significant portion of run-off-road crashes are single vehicle crashes that occur due to collisions with fixed ...Run-off-road crashes in the United States have become a major cause of serious injuries and fatalities. A significant portion of run-off-road crashes are single vehicle crashes that occur due to collisions with fixed objects and overturning. These crashes typically tend to be more severe than other types of crashes. Single vehicle run-off-road crashes that occurred between 2004 and 2008 were extracted from Kansas Accident Reporting System (KARS) database to identify the important factors that affected their severity. Different driver, vehicle, road, crash, and environment related factors that influence crash severity are identified by using binary logit models. Three models were developed to take different levels of crash severity as the response variables. The first model taking fatal or incapacitating crashes as the response variable seems to better fit the data than the other two developed models. The variables that were found to increase the probability of run-off-road crash severity are driver related factors such as driver ejection, being an older driver, alcohol involvement, license state, driver being at fault, medical condition of the driver;road related factors such as speed, asphalt road surface, dry road condition;time related factors such as crashes occurring between 6 pm and midnight;environment related factors such as daylight;vehicle related factors such as being an SUV, motorcycles, vehicle getting destroyed or disabled, vehicle maneuver being straight or passing;and fixed object types such as trees and ditches.展开更多
文摘The development of autonomous vehicles has become one of the greatest research endeavors in recent years. These vehicles rely on many complex systems working in tandem to make decisions. For practical use and safety reasons, these systems must not only be accurate, but also quickly detect changes in the surrounding environment. In autonomous vehicle research, the environment perception system is one of the key components of development. Environment perception systems allow the vehicle to understand its surroundings. This is done by using cameras, light detection and ranging (LiDAR), with other sensor systems and modalities. Deep learning computer vision algorithms have been shown to be the strongest tool for translating camera data into accurate and safe traversability decisions regarding the environment surrounding a vehicle. In order for a vehicle to safely traverse an area in real time, these computer vision algorithms must be accurate and have low latency. While much research has studied autonomous driving for traversing well-structured urban environments, limited research exists evaluating perception system improvements in off-road settings. This research aims to investigate the adaptability of several existing deep-learning architectures for semantic segmentation in off-road environments. Previous studies of two Convolutional Neural Network (CNN) architectures are included for comparison with new evaluation of Vision Transformer (ViT) architectures for semantic segmentation. Our results demonstrate viability of ViT architectures for off-road perception systems, having a strong segmentation accuracy, lower inference speed and memory footprint compared to previous results with CNN architectures.
文摘Increasing frame torsional stiffness of off-road vehicle will lead to the decrease of body torsional deformation, but the increase of torsional loads of frame and suspension system and the decrease of wheel adhesive weight. In severe case, a certain wheel will be out of contact with road surface. Appropriate matching of body, frame and suspension torsional stiffnesses is a difficult problem for off-road vehicle design. In this paper, these theoretically analytic models of the entire vehicle, body, frame and suspension torsional stiffness are constructed based on the geometry and mechanism of a light off-road vehicle＇s body, frame and suspension. The body and frame torsional stiffnesses can be calculated by applying body CAE method, meanwhile the suspension＇s rolling angle stiffness can be obtained by the bench test of the suspension＇s elastic elements. Through fixing the entire vehicle, using sole timber to raise wheels to simulate the road impact on a certain wheel, the entire vehicle torsional stiffness can be calculated on the geometric relation and loads of testing. Finally some appropriate matching principles of the body, frame and suspension torsional stiffness are summarized according to the test and analysis results. The conclusion can reveal the significance of the suspension torsional stiffness on off-road vehicle＇s torsion-absorbing capability. The results could serve as a reference for the design of other off-road vehicles.
基金supported by Nature Science Foundation of Zhejiang Province(No. Y10808 83 and No.Y1080967)Supported by Preferential Subject Key Project of Zhejiang Province(No.2008C13G2040006)
文摘This paper presents a software framework for off-road autonomous robot navigation system.With the requirements of accurate terrain perception and instantaneous obstacles detection,one navigation software framework was advanced based on the principles of "three layer architecture" of intelligence system.Utilized the technologies of distributed system,machine learning and multiple sensor fusion,individual functional module was discussed.This paper aims to provide a framework reference for autonomous robot navigation system design.
文摘The controllable suspension system can improve the performances of off-road vehicles both on road and cross-country. So far, four controllable suspensions, that is, body height control, active, semi-active and slow-active suspensions, have been developed. For off-road vehicles, the slow-active suspension and the semi-active suspension which have controllable stiffness, damping and body height are more appropriate to use. For many years, some control methodologies for controllable suspension systems have been developed along with the development of modern control theory, and two or more original control methods are integrated as a new control method. Today, for military or civilian off-road vehicles, the R&D of controllable suspension systems is ongoing.
文摘Run-off-road crashes in the United States have become a major cause of serious injuries and fatalities. A significant portion of run-off-road crashes are single vehicle crashes that occur due to collisions with fixed objects and overturning. These crashes typically tend to be more severe than other types of crashes. Single vehicle run-off-road crashes that occurred between 2004 and 2008 were extracted from Kansas Accident Reporting System (KARS) database to identify the important factors that affected their severity. Different driver, vehicle, road, crash, and environment related factors that influence crash severity are identified by using binary logit models. Three models were developed to take different levels of crash severity as the response variables. The first model taking fatal or incapacitating crashes as the response variable seems to better fit the data than the other two developed models. The variables that were found to increase the probability of run-off-road crash severity are driver related factors such as driver ejection, being an older driver, alcohol involvement, license state, driver being at fault, medical condition of the driver;road related factors such as speed, asphalt road surface, dry road condition;time related factors such as crashes occurring between 6 pm and midnight;environment related factors such as daylight;vehicle related factors such as being an SUV, motorcycles, vehicle getting destroyed or disabled, vehicle maneuver being straight or passing;and fixed object types such as trees and ditches.
