Learning-based approach for online lane change intention prediction

Kumar, P. Mohan; Perrollaz, Mathias; Lefèvre, Stéphanie; Laugier, Christian

doi:10.1109/ivs.2013.6629564

Cited by 334 publications

(157 citation statements)

References 12 publications

Supporting

Mentioning

145

Contrasting

Order By: Relevance

“…Then, the rule-based reasoning module generated the candidate models and input features of the models according to the relationships between vehicle56 and the surrounding objects (for vehicle56, Rule #2 in Table 2 is activated). The a priori probabilities were combined with the a posteriori probabilities by Equation (20) and the behavior tag is defined by Equation (21). Figure 13b shows the results of Approaches A and B.…”

Section: Field Testmentioning

confidence: 99%

A Scenario-Adaptive Driving Behavior Prediction Approach to Urban Autonomous Driving

Geng

Liang

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

Driving through dynamically changing traffic scenarios is a highly challenging task for autonomous vehicles, especially on urban roadways. Prediction of surrounding vehicles' driving behaviors plays a crucial role in autonomous vehicles. Most traditional driving behavior prediction models work only for a specific traffic scenario and cannot be adapted to different scenarios. In addition, priori driving knowledge was never considered sufficiently. This study proposes a novel scenario-adaptive approach to solve these problems. A novel ontology model was developed to model traffic scenarios. Continuous features of driving behavior were learned by Hidden Markov Models (HMMs). Then, a knowledge base was constructed to specify the model adaptation strategies and store priori probabilities based on the scenario's characteristics. Finally, the target vehicle's future behavior was predicted considering both a posteriori probabilities and a priori probabilities. The proposed approach was sufficiently evaluated with a real autonomous vehicle. The application scope of traditional models can be extended to a variety of scenarios, while the prediction performance can be improved by the consideration of priori knowledge. For lane-changing behaviors, the prediction time horizon can be extended by up to 56% (0.76 s) on average. Meanwhile, long-term prediction precision can be enhanced by over 26%.

show abstract

Section: Field Testmentioning

confidence: 99%

A Scenario-Adaptive Driving Behavior Prediction Approach to Urban Autonomous Driving

Geng

Liang

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Examples in the literature include assessing the driver's level of distraction from their body pose with k-means clustering (Shia et al, 2014), predicting a driver's intention to change lanes from the vehicle motion and the driver's actions with Support Vector Machines (Kumar et al, 2013), Relevance Vector Machines (Morris et al, 2011), or Hidden Markov Models (Lefèvre et al, 2014a), classifying drivers as compliant or violating at traffic lights with a Support Vector Machine (Aoude et al, 2012). More examples can be found in a recent survey on motion prediction for intelligent vehicles .…”

Section: Approachesmentioning

confidence: 99%

Automated driving: The role of forecasts and uncertainty—A control perspective

Carvalho

Lefèvre

Schildbach

et al. 2015

European Journal of Control

145

View full text Add to dashboard Cite

Driving requires forecasts. Forecasted movements of objects in the driving scene are uncertain. Inevitably, decision and control algorithms for autonomous driving need to cope with such uncertain forecasts. In assisted driving, the uncertainty in the human/vehicle interaction further increases the complexity of the control design task.Our research over the past ten years has focused on control design methods which systematically handle uncertain forecasts for autonomous and semi-autonomous vehicles. This article presents an overview of our findings and discusses relevant aspects of our recent results.

show abstract

“…The driver state can be estimated using standard classification techniques. Examples in the literature include assessing the driver's level of distraction from their body pose with k-means clustering, [10] predicting a driver's intention to change lanes from the vehicle motion and the driver's actions with support vector machines, [11] relevance vector machines, [12] or hidden Markov models (HMMs), [8] classifying drivers as compliant or violating at traffic lights with a support vector machine. [13] More examples can be found in a recent survey on motion prediction for intelligent vehicles.…”

Section: Driver Modelsmentioning

confidence: 99%

Driver models for personalised driving assistance

Lefèvre

Carvalho

Gao

et al. 2015

Vehicle System Dynamics

101

View full text Add to dashboard Cite

We propose a learning-based driver modelling approach which can identify manoeuvres performed by drivers on the highway and predict the future driver inputs. We show how this approach can be applied to provide personalised driving assistance. In a first example, the driver model is used to predict unintentional lane departures and a model predictive controller is used to keep the car in the lane. In a second example, the driver model estimates the preferred acceleration of the driver during lane keeping, and a model predictive controller is implemented to provide a personalised adaptive cruise control. For both applications, we use a combination of real data and simulation to evaluate the proposed approaches.

show abstract

Learning-based approach for online lane change intention prediction

Cited by 334 publications

References 12 publications

A Scenario-Adaptive Driving Behavior Prediction Approach to Urban Autonomous Driving

A Scenario-Adaptive Driving Behavior Prediction Approach to Urban Autonomous Driving

Automated driving: The role of forecasts and uncertainty—A control perspective

Driver models for personalised driving assistance

Contact Info

Product

Resources

About