Tire-Road Peak Adhesion Coefficient Estimation Method Based on Fusion of Vehicle Dynamics and Machine Vision

Leng, Bo; Jin, Da; Hou, Xinchen; Liu, Xiong; Yu, Zhuoping

doi:10.1109/tits.2022.3183691

Cited by 13 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Safety control of vehicles often needs to adjust the force between road surfaces and tires, and the interaction force is also a key and vital factor that affects the stability of the vehicle chassis [ 4 , 5 ]. Therefore, the adhesion coefficient of road surfaces is a vital parameter to obtain accurate motion control of vehicles [ 6 , 7 ], and it also provides a significant input for the decision and planning of intelligent vehicles. It is vital and essential to precisely identify the adhesion coefficients of the unstructured pavements for the safe driving of vehicles.…”

Section: Introductionmentioning

confidence: 99%

Adhesion Coefficient Identification of Wheeled Mobile Robot under Unstructured Pavement

Zhang,

Song,

et al. 2024

Sensors

View full text Add to dashboard Cite

Because of its uneven and large slope, unstructured pavement presents a great challenge to obtaining the adhesion coefficient of pavement. An estimation method of the peak adhesion coefficient of unstructured pavement on the basis of the extended Kalman filter is proposed in this paper. The identification accuracy of road adhesion coefficients under unstructured pavement is improved by introducing the equivalent suspension model to optimize the calculation of vertical wheel load and modifying vehicle acceleration combined with vehicle posture data. Finally, the multi-condition simulation experiments with Carsim are conducted, the estimation accuracy of the adhesion coefficient is at least improved by 3.6%, and then the precision and effectiveness of the designed algorithm in the article are verified.

show abstract

Section: Introductionmentioning

confidence: 99%

Adhesion Coefficient Identification of Wheeled Mobile Robot under Unstructured Pavement

Zhang,

Song,

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Therefore, estimation of the peak value of TRFC is usually carried out by identifying the road surface characteristics (texture, water film, pavement type, etc.) or the tire force states or fusion of these two approaches ( 13 , 14 ).…”

Section: Introductionmentioning

confidence: 99%

“…The first and foremost thing is that the accuracy of these methods usually depends on the accuracy of the tire model utilized to fit the estimated tire forces, which should be carefully calibrated through a flat belt or road tire testing machine. In addition, the maximum TRFC values can only be accurately identified when the tire deformation is significant enough ( 13 , 23 ). Specifically, the vehicle should be maneuvered with high tire excitation (hard braking, steering, accelerating, etc), which rarely occurs during normal driving conditions and does pose certain security risks to the driver.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, data-driven approaches for estimation of maximum TRFC in the forms of learning tire friction curves or stochastic modeling of tire behavior, extracting deep features of vehicle dynamics or road surface properties, and fusion estimation based on multi-source information, such as vehicle dynamics and road surface condition, have advanced significantly to address limitations of the approaches mentioned above ( 13 , 14 , 25 ). Berntorp ( 26 ) proposed a Bayesian framework based on particle filtering and Markov chain Monte-Carlo methods to learn the nonlinear mapping between wheel slip to TRFC.…”

Section: Introductionmentioning

confidence: 99%

“…Another idea is to utilize machine learning with images from vehicle-mounted cameras for road condition analysis, for example, maximum TRFC level inference ( 5 , 33 ), pavement texture depth estimation ( 34 ), water film thickness estimation ( 15 ), and so forth. In addition to methods taking vehicle operation data or pavement surface properties as the primary input data, a hybrid identification, through both vision and vehicle state, has also proved promising for improving the estimation accuracy ( 13 ). Meanwhile, the combination of vehicle operation data and vision data can compensate for the deficiencies of each and applies to more driving scenarios, such as constant speed driving with low tire excitation or poorly illuminated sections.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pavement Friction Evaluation Based on Vehicle Dynamics and Vision Data Using a Multi-Feature Fusion Network

Skar

Pettinari³

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

The tire–road friction coefficient is a critical evaluation index of the service performance of roads: it governs the stopping distance, traction control, and stability of vehicles. Moreover, friction information is also needed in many function units of modern vehicles. This paper proposes a novel data-driven approach for inference of the maximum tire–road friction coefficient using a combination of vehicle dynamics signal and machine vision data. The approach is aimed at robust road condition perception that can provide frequent measurements over large areas across all weather conditions. Two different neural network architectures were adopted to extract in-depth features behind vehicle dynamics signals and road surface images. Features from these two types of data were then fused in two different levels, namely feature level and decision level, forming a multi-feature fusion neural network. The proposed network performs better than models based only on dynamic signals or vision data. The method proposed was applied to real data obtained from an electric car in a highway driving scenario. For classification of the maximum tire–road friction coefficient, the proposed network can yield F1-score increments of 0.09 and 0.18 from dynamics-based and vision-based sub-models, respectively. For the maximum tire–road friction coefficient value regression, the proposed model also achieves the highest R-square score of 0.71. Of these two types of data collected under highway driving scenarios, the vision data contribute more to the overall performance of the proposed model. Nevertheless, the dynamics data possess excellent potential in poor lighting conditions. With these fused features, the proposed multi-feature fusion network can not only improve the accuracy of maximum tire–road friction coefficient estimation but also is deemed workable for a broader range of scenarios.

show abstract

Combined longitudinal and lateral dynamics regulation of autonomous vehicles via induced ℒ2$$ {\mathcal{L}}_2 $$‐gain linear parameter varying control strategies based on parameter‐dependent Lyapunov functions

Gagliardi,

D'Angelo,

Casavola

2024

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article considers a path tracking control problem for autonomous vehicles constrained to maintain a safe distance from the next vehicle in the lane. The control design problem is solved by considering a mathematical model of the vehicle that jointly describes the lateral and longitudinal dynamics. Specifically, the optimal controller is designed aimed at minimizing the orientation and position tracking errors with respect to a given reference path. Moreover, the controller is able to ensure that the vehicle can both follow a speed profile and automatically adjusts the vehicle speed to maintain a proper distance from the next vehicle. The lateral dynamic is regulated by a 2‐DOF feedforward/feedback controller, where the feedforward law is implemented by exploiting an inverse kinematic model of the vehicle. On the other side, the feedback action, along with the action of the controller in charge to regulate the longitudinal dynamics, is the optimal gain‐scheduling state‐feedback controller. In particular, a parameter‐dependent quadratic Lyapunov function approach is used to reduce the conservativeness of the solution and a suitable convex LMI optimization problem is formulated for the synthesis. The vehicle is described by a seven‐degrees‐of‐freedom (7DOF) full‐car model, with the tire‐generated forces described by the classical Pacejka's Magic Formula. In order to assess the performance of the proposed control strategy, simulations have been undertaken in Matlab/Simulink by considering an autonomous vehicle driving into an urban scenario.

show abstract

Tire-Road Peak Adhesion Coefficient Estimation Method Based on Fusion of Vehicle Dynamics and Machine Vision

Cited by 13 publications

References 23 publications

Adhesion Coefficient Identification of Wheeled Mobile Robot under Unstructured Pavement

Adhesion Coefficient Identification of Wheeled Mobile Robot under Unstructured Pavement

Pavement Friction Evaluation Based on Vehicle Dynamics and Vision Data Using a Multi-Feature Fusion Network

Combined longitudinal and lateral dynamics regulation of autonomous vehicles via induced ℒ2$$ {\mathcal{L}}_2 $$‐gain linear parameter varying control strategies based on parameter‐dependent Lyapunov functions

Contact Info

Product

Resources

About