Autonomous Manoeuvring Systems for Collision Avoidance on Single Carriageway Roads

Jiménez, Felipe; Naranjo, José Eugenio; Gómez, Óscar

doi:10.3390/s121216498

Cited by 22 publications

(21 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AVs require a plethora of data from multiple sensor platforms to generate a collision-free trajectory (Huang et al, 2013;Polychronopoulos et al, 2007). Most of AVs utilize cameras (Bertozzi et al, 2000) and laser scanners (Jiménez et al, 2012;Mertz et al, 2013) to scan the surroundings and estimate a safe path for the vehicle. However, it is still unknown how AVs would identify the optimal course of action in the face of a system failure (Dixit et al, 2016;Koopman and Wagner, 2016).…”

Section: Implementation Challenges and Recommendationsmentioning

confidence: 99%

A new integrated collision risk assessment methodology for autonomous vehicles

Katrakazas

Quddus

Chen

2019

Accident Analysis & Prevention

102

View full text Add to dashboard Cite

Real-time risk assessment of autonomous driving at tactical and operational levels is extremely challenging since both contextual and circumferential factors should concurrently be considered. Recent methods have started to simultaneously treat the context of the traffic environment along with vehicle dynamics. In particular, interaction-aware motion models that take inter-vehicle dependencies into account by utilizing the Bayesian interference are employed to mutually control multiple factors. However, communications between vehicles are often assumed and the developed models are required many parameters to be tuned. Consequently, they are computationally very demanding. Even in the cases where these desiderata are fulfilled, current approaches cannot cope with a large volume of sequential data from organically changing traffic scenarios, especially in highly complex operational environments such as dense urban areas with heterogeneous road users. To overcome these limitations, this paper develops a new risk assessment methodology that integrates a network-level collision estimate with a vehicle-based risk estimate in real-time under the joint framework of interaction-aware motion models and Dynamic Bayesian Networks (DBN). Following the formulation and explanation of the required functions, machine learning classifiers were utilized for the real-time network-level collision prediction and the results were then incorporated into the integrated DBN model for predicting collision probabilities in real-time. Results indicated an enhancement of the interaction-aware model by up to 9%, when traffic conditions are deemed as collision-prone. Hence, it was concluded that a wellcalibrated collision prediction classifier provides a crucial hint for better risk perception by autonomous vehicles.

show abstract

Section: Implementation Challenges and Recommendationsmentioning

confidence: 99%

A new integrated collision risk assessment methodology for autonomous vehicles

Katrakazas

Quddus

Chen

2019

Accident Analysis & Prevention

102

View full text Add to dashboard Cite

show abstract

“…In [25] the authors present a forward collision warning system, based on a laser scanner, which is able to detect several potential danger situations. Decision algorithms determine the most convenient manoeuvre, act on the actuators of the ego-vehicle and transmit this information to other vehicles using V2V communications.…”

Section: Papers In the Special Issuementioning

confidence: 99%

Introduction to the Special Issue on “New Trends towards Automatic Vehicle Control and Perception Systems”

Milanés

Bergasa

2013

Sensors

View full text Add to dashboard Cite

Intelligent and automatic systems are making our daily life easier. They are able to automate tasks that, up to now, were performed by humans, freeing them from these tedious tasks. They are mainly based on the classical robotic architectures where the stages of perception-using different sensor sources or even a fusion of a set of them-and planning-where intelligent control systems are applied-play a key role. Among all of the fields in which intelligent systems can be applied, transport systems are considered one of the most promising ones since over one million fatalities-including drivers, pedestrians, cyclists and motorcyclists-are registered each year worldwide and they can definitively help to reduce these figures.The growth in the number of drivers in the last decades, and consequently in the number of vehicles, has made traffic accidents become a major concern in the road transportation sector. Solutions such as building new transport infrastructures-specifically in urban areas where space limitations make it almost impossible-or increasing fines for inappropriate driving have not achieved the goal of reducing the number of fatalities, either in urban environments or highways. New policies on the part of the Governments are focused on the development of a safer, more reliable and more efficient transportation supported by intelligent systems.The field of research in which all these topics fall into is well-known as intelligent transportation systems (ITS). ITS focuses on improving road safety by acting on two possible aspects: on the one hand, the infrastructure and the possibilities of optimizing traffic flow, and on the other hand, acting on the cars with the development of Advanced Driver Assistance Systems (ADAS) and the possibilities of optimizing traffic safety. The final goal is trying to reduce the number of collisions, or at least to mitigate their consequences. In this connection, one of the currently hot topics in the road OPEN ACCESS

show abstract

“…Each of them has advantages and disadvantages [16] and sensor fusion is commonly used to overcome the individual limitations [17][18][19][20][21]. Regarding the technologies for detecting vehicle surroundings, which can be also used for autonomous guidance, computer vision and laser scanner can be highlighted [22,23].…”

Section: Introductionmentioning

confidence: 99%

Improving the Lane Reference Detection for Autonomous Road Vehicle Control

et al. 2016

Self Cite

View full text Add to dashboard Cite

Autonomous road vehicles are increasingly becoming more important and there are several techniques and sensors that are being applied for vehicle control. This paper presents an alternative system for maintaining the position of autonomous vehicles without adding additional elements to the standard sensor architecture, by using a 3D laser scanner for continuously detecting a reference element in situations in which the GNSS receiver fails or provides accuracy below the required level. Considering that the guidance variables are more accurately estimated when dealing with reference points in front of and behind the vehicle, an algorithm based on vehicle dynamics mathematical model is proposed to extend the detected points in cases where the sensor is placed at the front of the vehicle. The algorithm has been tested when driving along a lane delimited by New Jersey barriers at both sides and the results show a correct behaviour. The system is capable of estimating the reference element behind the vehicle with sufficient accuracy when the laser scanner is placed at the front of it, so the robustness of the control input variables (lateral and angular errors) estimation is improved making it unnecessary to place the sensor on the vehicle roof or to introduce additional sensors.

show abstract

Autonomous Manoeuvring Systems for Collision Avoidance on Single Carriageway Roads

Cited by 22 publications

References 43 publications

A new integrated collision risk assessment methodology for autonomous vehicles

A new integrated collision risk assessment methodology for autonomous vehicles

Introduction to the Special Issue on “New Trends towards Automatic Vehicle Control and Perception Systems”

Improving the Lane Reference Detection for Autonomous Road Vehicle Control

Contact Info

Product

Resources

About