Lane-Change Detection Based on Vehicle-Trajectory Prediction

Woo, Hanwool; Ji, Yonghoon; Kono, Hitoshi; Tamura, Yusuke; Kuroda, Yasuhide; Sugano, Takashi; Yamamoto, Yasunori; Yamashita, Atsushi; Asama, Hajime

doi:10.1109/lra.2017.2660543

Cited by 117 publications

(75 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Woo et al [12] installed sensor system in the subject vehicle to predict the target vehicle trajectory and hence detect the lane change of the target vehicle; the system consisted of a position sensor (RT3003) and six laser scanners (Ibeo LUX). This system enabled the subject vehicle to acquire its position, the position of other vehicles, and their velocity.…”

Section: Introductionmentioning

confidence: 99%

A framework for testing independence between lane change and cooperative intelligent transportation system

Elhenawy¹,

Glaser²,

Bond³

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

Cooperative Intelligent Transportation Systems (C-ITS) are being deployed in several cities around the world. We are preparing for the largest Field Operational Test (FOT) in Australia to evaluate C-ITS safety benefits. Two of the safety benefit hypotheses we formulated assume a dependency between lane changes and C-ITS warnings displayed on the Human Machine Interface (HMI) during safety events. Lane change detection is done by processing many predictors from several sensors at the time of the safety event. However, in our planned FOT, the participating vehicles are only equipped with the vehicle C-ITS and the IMU. Therefore, in this paper, we propose a framework to test lane change and C-ITS dependency. In this framework, we train a random forest classifier using data collected from the IMU to detect lane changes. Consequently, the random forest output probabilities of the testing data in case of C-ITS and control are used to construct a 2x2 contingency table. Then we develop a permutation test to calculate the null hypothesis needed to test the independence of the lane change during safety events and the C-ITS.

show abstract

Section: Introductionmentioning

confidence: 99%

A framework for testing independence between lane change and cooperative intelligent transportation system

Elhenawy¹,

Glaser²,

Bond³

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Mandalia et al [6] classify the LC maneuver using support vector machine (SVM), while Schlechitriemen et al [7] use Gaussian mixture models to estimate driving intentions. Woo et al [8] also adopt an SVM, and suggest using trajectory prediction to reject false alarms from the intention estimations. These methods detect LCs based on the target's own maneuver pattern and only have a limited prediction horizon.…”

Section: Related Workmentioning

confidence: 99%

“…II, where we find that many proposed methods are detectionbased and only have a limited prediction horizon. For example, a lane change is detected only 1.0 s to 1.7 s before the prediction target crosses the dividing line [5]- [8]. To avoid generating false alarms in the face of noisy maneuvers such as zigzagging, these methods tend to detect the behavior only when it is clearly happening.…”

Section: Introductionmentioning

confidence: 99%

Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network

Ding

Chen

Shen

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Anticipating possible behaviors of traffic participants is an essential capability of autonomous vehicles. Many behavior detection and maneuver recognition methods only have a very limited prediction horizon that leaves inadequate time and space for planning. To avoid unsatisfactory reactive decisions, it is essential to count long-term future rewards in planning, which requires extending the prediction horizon. In this paper, we uncover that clues to vehicle behaviors over an extended horizon can be found in vehicle interaction, which makes it possible to anticipate the likelihood of a certain behavior, even in the absence of any clear maneuver pattern. We adopt a recurrent neural network (RNN) for observation encoding, and based on that, we propose a novel vehicle behavior interaction network (VBIN) to capture the vehicle interaction from the hidden states and connection feature of each interaction pair. The output of our method is a probabilistic likelihood of multiple behavior classes, which matches the multimodal and uncertain nature of the distant future. A systematic comparison of our method against two state-of-the-art methods and another two baseline methods on a publicly available real highway dataset is provided, showing that our method has superior accuracy and advanced capability for interaction modeling.

show abstract

“…Many existing trajectory prediction algorithms [1], [2] output deterministic results efficiently. However, these methods fail to capture the uncertain nature of human actions.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections

Huang¹,

McGill²,

Williams

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Predicting the motion of a driver's vehicle is crucial for advanced driving systems, enabling detection of potential risks towards shared control between the driver and automation systems. In this paper, we propose a variational neural network approach that predicts future driver trajectory distributions for the vehicle based on multiple sensors.Our predictor generates both a conditional variational distribution of future trajectories, as well as a confidence estimate for different time horizons. Our approach allows us to handle inherently uncertain situations, and reason about information gain from each input, as well as combine our model with additional predictors, creating a mixture of experts.We show how to augment the variational predictor with a physics-based predictor, and based on their confidence estimations, improve overall system performance. The resulting combined model is aware of the uncertainty associated with its predictions, which can help the vehicle autonomy to make decisions with more confidence. The model is validated on real-world urban driving data collected in multiple locations. This validation demonstrates that our approach improves the prediction error of a physics-based model by 25% while successfully identifying the uncertain cases with 82% accuracy.

show abstract

Lane-Change Detection Based on Vehicle-Trajectory Prediction

Cited by 117 publications

References 14 publications

A framework for testing independence between lane change and cooperative intelligent transportation system

A framework for testing independence between lane change and cooperative intelligent transportation system

Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network

Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections

Contact Info

Product

Resources

About