Investigation of different techniques for determining the road uphill gradient and the pitch angle of vehicles

Massel, T.; Ding, E.L.; Arndt, M.

doi:10.23919/acc.2004.1383884

Cited by 9 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of driverless and smart driving technologies, it is essential to optimize vehicle control techniques by efficiently forecasting future road slopes [7][8]. Numerous academics have studied the estimation of road slope, and the methods for road slope estimation are mainly divided into two major categories: One category of the estimation method is based on additional sensors to measure the road slope directly or indirectly by inclinometers [9], GIS [10] (Geographic Information System), GPS [11][12][13] (Global Positioning System), smart phone [14], accelerometers [15], etc. The other category is the method based on the dynamics model, in which the road slope is estimated by various algorithms based on dynamics model.…”

Section: Introductionmentioning

confidence: 99%

The Prediction Model for Road Slope of Electric Vehicles Based on Stacking Framework of Deep Learning

Zhu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Accurate real-time information on road slopes and the capacity to forecast future moment gradient values are critical for the vehicle control, stability, and driving comfort. Thus, this study proposes a stacking model method for road slope estimation of electric vehicles. Gated Circulation unit (GRU), Convolutional Neural Network (CNN), and CNN-GRU are used as the base classifiers, and Multilayer Perceptron (MLP) is used as a meta-classifier. The vehicle dynamics equations are examined to select the appropriate parameters to feed into the base classifier for training. The meta-classifier is trained using the estimated results from the basic classifier. The current slope values are estimated by slicing the training set by data sampling time and windowing the training data set to predict the future slope values in 2s, 3s, and 4s. Road experiments are conducted, and error indicators are selected for evaluation. The stacking model is compared with each base classifier, Adaptive Kalman filter, Recursive Least Squares with Forgetting Factor and Back Propagation Neural Network for estimating the current moment slope, and it is verified that the stacking model can better estimate the current slope value and outperform the conventional algorithm. Comparing the stacking model with the predicted results of each base classifier for future time slope prediction shows that the stacking model is more accurate at predicting the slope values in the short future time.

show abstract

Section: Introductionmentioning

confidence: 99%

The Prediction Model for Road Slope of Electric Vehicles Based on Stacking Framework of Deep Learning

Zhu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Since the longitudinal acceleration can be measured by the sensor, it is important to eliminate the noise caused by sampling. Massel et al 10 and Klomp et al 11 used the recursive least-squares (RLS) algorithm and the KF respectively to estimate the road grade. Cheng et al 12 constructed a three-dimensional state transition matrix, which contained the speed, the acceleration and the road grade.…”

Section: Introductionmentioning

confidence: 99%

Road grade estimation based on the curvature of the vertical profile of a road

Nie

Shi

2016

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

A road grade estimation model which uses the curvature to express the rate of change in the grade is proposed in this paper. The assumption that the rate of change in the road grade equals zero is widely accepted in the field of online road grade estimation. This assumption is reasonable to some extent, but it results in an inevitable time lag in the rolling-hills situation. This paper offers a road curvature estimation method which can be used to express the rate of change in the road grade. The recursive least-squares algorithm is used to the estimate the curvature, and then the Kalman filter is employed to estimate the road grade from the other vehicle states. Field tests are performed on a highway in a mountainous area. The offline road grade is used to analyse the instantaneous error and the time lag. The field test results show that the model performs well in reducing the time lag, especially in periods where the gradient changes rapidly.

show abstract