Vehicle dynamics and external disturbance estimation for vehicle path prediction

Lin, Chiu-Feng; Ulsoy, A. Galip; LeBlanc, David J.

doi:10.1109/87.845881

Cited by 96 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This choice seems to be a realistic solution in view of the possible trajectories on the crossroads and the dynamics of vehicles. In order to attenuate the effect of the positioning noise error we filtered the modeled trajectory in real time using a Kalman model [18]. In the filtering process the movement of the vehicle is taken as a first degree linear movement.…”

Section: B Prediction Systemmentioning

confidence: 99%

Real-time crash avoidance system on crossroads based on 802.11 devices and GPS receivers

Ammoun

Nashashibi²,

Laurgeau³

2006

2006 IEEE Intelligent Transportation Systems Conference

View full text Add to dashboard Cite

In this paper we study the contribution of intervehicule communication in ADAS applications. We thus propose a collaborative system on the crossroads using our 802.11g communications tools and a low cost GPS receiver. Once the vehicles positions exchanged, the crash avoidance is performed by predicting the future positions of both cars and calculating the time to impact and the region of high risk. The prediction is biased in time and space. The time error is due to the GPS and the communication latencies. We thus propose an estimation of both latencies and integrate them in the prediction loop. The Space error is caused by the uncertainty of the positions delivered by the GPS receivers. We compensate this error not by considering a deterministic position of the vehicle but by a probability of being in a region of space and by proposing a Kalman filter witch first reduces noise on the positioning and second estimates the variance of error on the measurement. This approach is validated through real scenarios of road crossing. We show thus the contribution of the cooperation via the communication devices in the reduction of accidents rate on the crossroads. I. INTRODUCTIONHE recent quick development of wireless communications systems make possible the concept of an advanced collaborative driving. Relatively to the perception sensors usually exploited in ADAS systems the V2V (vehicle to vehicle communications) have three contributions: 1)extending the sensing capability to the communication coverage area (which is more and more increased with recent technologies), 2)delivering a valid and exact information about neighbor vehicles (other perception tools can only "estimate" the features of the detected vehicles) and 3)making possible the exchange of none measurable data by an autonomous system (i.e. the driver intentions). Many research teams world-wide are involved in the definition of this new kind of network. The research can be done on many layers: i.e. the selection of the most reliable physical layer, the selection of the more adapted routing and access protocols [1,12] and the definition of HMI for new road safety applications. This complexity and diversity explains the numerous projects involved in the definition and design of the V2V communications systems. From early 1980s Japanese IVHS projects [2] to platooninglike systems developed within the European Chauffeur [3] and US PATH program [4], the inter-vehicle communications played an essential role on the conception

show abstract

Section: B Prediction Systemmentioning

confidence: 99%

Real-time crash avoidance system on crossroads based on 802.11 devices and GPS receivers

Ammoun

Nashashibi²,

Laurgeau³

2006

2006 IEEE Intelligent Transportation Systems Conference

View full text Add to dashboard Cite

show abstract

“…Kalman Filter [15], are often combined with the motion model to improve prediction accuracy and account for noise in measurements from sensors. Nevertheless, techniques such as the one presented in [20] are greatly restricted to simple environments and to very short prediction horizon (for instance 1 second into the future). Alternatively, models based on Bayesian Framework such as Bayesian Networks (BNs) [14] and Hidden Markov Models (HMMs) [23] are often employed to further account for the probabilistic nature of the problem and capture relationships between sets of random variables.…”

Section: Introductionmentioning

confidence: 99%

Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networks

Dulian

Murray

2021

2021 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

As urban environments manifest high levels of complexity it is of vital importance that safety systems embedded within autonomous vehicles (AVs) are able to accurately anticipate short-term future motion of nearby agents. This problem can be further understood as generating a sequence of coordinates describing the future motion of the tracked agent. Various proposed approaches demonstrate significant benefits of using a rasterised top-down image of the road, with a combination of Convolutional Neural Networks (CNNs), for extraction of relevant features that define the road structure (eg. driveable areas, lanes, walkways). In contrast, this paper explores use of Capsule Networks (CapsNets) in the context of learning a hierarchical representation of sparse semantic layers corresponding to small regions of the High-Definition (HD) map. Each region of the map is dismantled into separate geometrical layers that are extracted with respect to the agent's current position. By using an architecture based on CapsNets the model is able to retain hierarchical relationships between detected features within images whilst also preventing loss of spatial data often caused by the pooling operation. We train and evaluate our model on publicly available dataset nuTonomy scenes and compare it to recently published methods. We show that our model achieves significant improvement over recently published works on deterministic prediction, whilst drastically reducing the overall size of the network.

show abstract

“…The second is the Constant Turn Rate (CTR) model (Li, Jilkov 2003), which assumes that the yaw rate and speed of the vehicle remain constant over time. The third model is the CTR and Constant Tangential Acceleration (CTRA) model (Lin et al 2000), which can be considered as a generalization of the other two models. Although the CTRA model describes the true motion of vehicles in a more realistic manner, the amount of computation needed is larger than for the others.…”

Section: Vehicle Motion Predictionmentioning

confidence: 99%

“…Using this information, collision detection algorithms were designed based on a model of determining the minimum distance of vehicles' future trajectories. A previous study (Lin et al 2000) addressed the on-board prediction of a motor vehicle's path using the numerical integration of a linearized two-degree-of-freedom vehicle-handling model. Another important task of CCW is analysing the time to avoid collision.…”

Section: Introductionmentioning

confidence: 99%

Collision avoidance on winding roads using dedicated short-range communication

Yuan¹,

Jian

Xia

2017

Transport

View full text Add to dashboard Cite

Abstract. The emergence of wireless communication technologies such as Dedicated Short-Range Communication (DSRC) has promoted the evolution of collision warning from simple ranging-sensor-based systems to cooperative systems. In cooperative systems, path prediction is a promising method for reflecting a driver's intention and estimating the future position of vehicles. In this study, a short-term trajectory-modelling method is proposed to predict vehicle motion behaviour in the cooperative vehicular environment. In addition, a collision detection algorithm for winding roads is presented based on a model for determining the minimum distance of vehicles' future trajectories. The cooperative collision avoidance system's performance is analysed through simulation, providing useful theoretical insights into the effects of DSRC technology on vehicle collision avoidance in a curved road environment.

show abstract

Vehicle dynamics and external disturbance estimation for vehicle path prediction

Cited by 96 publications

References 10 publications

Real-time crash avoidance system on crossroads based on 802.11 devices and GPS receivers

Real-time crash avoidance system on crossroads based on 802.11 devices and GPS receivers

Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networks

Collision avoidance on winding roads using dedicated short-range communication

Contact Info

Product

Resources

About