Tire Conditions Research Articles

Tire wear monitoring using feature fusion and CatBoost classifier

Addressing the critical issue of tire wear is essential for enhancing vehicle safety, performance, and maintenance. Worn-out tires often lead to accidents, underscoring the need for effective monitoring systems. This study is vital for several reasons: safety, as worn tires increase the risk of accidents due to reduced traction and longer braking distances; performance, as uneven tire wear affects vehicle handling and fuel efficiency; maintenance costs, as early detection can prevent more severe damage to suspension and alignment systems; and regulatory compliance, as ensuring tire integrity helps meet safety regulations imposed by transportation authorities. In response, this study systematically evaluates tire conditions at 25%, 50%, 75%, and 100% wear, with an intact tire as a reference, using vibration signals as the primary data source. The analysis employs statistical, histogram, and autoregressive–moving-average (ARMA) feature extraction techniques, followed by feature selection to identify key parameters influencing tire wear. CatBoost is used for feature classification, leveraging its adaptability and efficiency in distinguishing varying wear patterns. Additionally, the study incorporates feature fusion to combine different types of features for a more comprehensive analysis. The proposed methodology not only offers a robust framework for accurately classifying tire wear levels but also holds significant potential for real-time implementation, contributing to proactive maintenance practices, prolonged tire lifespan, and overall vehicular safety.

Tire Texture Monitoring (VGG 19 VS Efficient Net b7)

Tires are crucial components of vehicles, continuously in contact with the road. Monitoring tire conditions is vital for safety and performance, as degradation in tire treads and sidewalls can affect traction, fuel efficiency, longevity, and road noise. This research leverages both VGG19 and Efficient Net B7 algorithms to enhance tire image rendering, addressing limitations of traditional techniques. Using a binary classification algorithm, we classify tire images as healthy or cracked. By fine-tuning VGG19 and EfficientNet B7 on a specialized tire dataset, we achieve high-quality, photorealistic renderings. Our results demonstrate remarkable improvements in texture quality and visual realism compared to traditional methods. The rendered images exhibit finer details and more accurate representations of the tire’s tread patterns and material properties. This research contributes to the field of computer graphics by presenting a novel application of deep learning techniques to a specific industrial need, paving the way for future advancements in high-quality rendering of complex tire textures. Key Words: VGG19,Photorealistic rendering, deep learning.

Substitution of Conventional Vehicles in Municipal Mobility

Among the economic sectors, mobility is showing significant environmental impacts, especially in the use phase of vehicles. By substituting fossil-fuelled propelling systems, environmental impacts such as the Global Warming Potential (GWP) can be reduced. The use of properly designed light electric vehicles (LEVs) significantly reduces further environmental impacts, as well as maintenance costs, which are relevant for a circular economy. For example, the use of low-voltage (42 V) propelling systems enables the maintenance of LEVs in a broader range of existing bicycle workshops. Regarding the environmental impacts, the described LCA results indicate the advantage of LEVs compared with EVs and ICVs, e.g., vehicle weight is found to be a main factor related to environmental impact for each type of vehicle. This implies a reduced need for battery capacity and lower emissions of particulate matter from tire and break abrasion. This study aims to present the application potential of LEVs and the related reduction in environmental impacts. Anonymised inventory lists of municipal vehicle fleets are analysed for quantifying the substitution potential of LEVs in specific use cases. For this purpose, the use phase of vehicles is analysed with a focus on product design for repair and recycling and supplemented by the results of a comparative environmental impact assessment of internal combustion engine vehicles (ICEVs), electric vehicles (EVs), and LEVs. The comparison is made on the premise of similar application requirements. These specifications are the ability of each of the vehicles to transport a maximum of three persons (driver included) or one driver and 250 kg of cargo in 3 m3 over a daily distance of 100 km in urban areas. On this basis, the municipal environmental benefits derived from substituting small vehicles in the form of ICEVs and EVs with LEVs are assessed. The results show that in the field of municipal mobility, a relevant number of conventional small vehicles can be substituted with LEVs. The environmental impacts in categories of the highest robustness level, RL I, that is, Global Warming Potential, fine dust emissions, and Ozone Depletion Potential, can be reduced by LEVs by 50% compared with EVs and by over 50% compared with ICEVs. The strong influence of vehicle weight on the abrasive conditions of tires and brakes is considerable, as shown by reduced fine dust emissions.

Сервисное обслуживание пневматических шин на самоходные машины для подземных горных работ

The article presents the issue of short life of pneumatic tyres for mobile underground mining machines. It is noted that the correct choice of pneumatic tyres will increase the tyre life, but for a greater increase it is necessary to control the entire life cycle of the tyre, i.e. to carry out its service. The life cycle stages to be taken into account during tyre maintenance are presented. Control at each stage will minimise damage to the pneumatic tyres. The maintenance phase should include the records of tyre usage history and stock management. Analysis of the records will help to determine the reasons for tyre rejection and the wear conditions, the tyre condition before and after repair, and before and after retreading. Service maintenance of pneumatic tyres will allow planning the approximate level of stock, replacement periods and effective stock management. The article justifies the relevance of holding joint meetings of service specialists, tyre designers, and the company’s. In conclusion, it is noted that the issue of creating a national standard of service maintenance of pneumatic tyres for mobile underground mining machines is relevant.

Enhancing Tire Condition Monitoring through Weightless Neural Networks Using MEMS-Based Vibration Signals

Tire pressure monitoring system (TPMS) has a critical role in safeguarding vehicle safety by monitoring tire pressure levels. Keeping the accurate tire pressure is necessary for confirming comfortable driving and safety, and improving fuel consumption. Tire problems can result from various factors, such as road surface conditions, weather changes, and driving activities, emphasizing the importance of systematic tire checks. This study presents a novel method for tire condition monitoring using weightless neural networks (WNN), which mimic neural processes using random-access memory (RAM) components, supporting fast and precise training. Wilkes, Stonham, and Aleksander Recognition Device (WiSARD), a type of WNN, stands out for its capability in classification and pattern recognition, gaining from its ability to avoid repetitive training and residual formation. For vibration data acquisition from tires, cost-effective micro-electro-mechanical system (MEMS) sensors are employed, offering a more economical solution than piezoelectric sensors. This approach yields a variety of features, such as autoregressive moving average (ARMA), statistical and histogram features. The J48 decision tree algorithm plays a critical role in selecting essential features for classification, which are subsequently divided into training and testing sets, crucial for assessing the WiSARD classifier’s efficacy. Hyperparameter optimization of the WNN leads to improved classification accuracy and shorter computation times. In practical tests, the WiSARD classifier, when optimally configured, achieved an impressive 97.92% accuracy with histogram features in only 0.008 seconds, showcasing the capability of WNN to enhance tire technology and the accuracy and efficiency of tire monitoring and maintenance.

EDT-STACK: A stacking ensemble-based decision trees algorithm for tire tread depth condition classification

Tires serve as the critical interface between a vehicle and the road. Their condition significantly impacts road safety, vehicle performance, fuel efficiency, and operational costs. Developing a machine learning model for accurately and efficiently classifying tire conditions using tread depth measurements poses a critical challenge in enhancing automotive safety and maintenance. This research aims to address this challenge by leveraging machine learning techniques to categorize and assess tire conditions based on tread depth, thereby contributing to developing a robust and automated system for tire safety condition monitoring in diverse vehicle fleets. This article presents a novel ensemble method-based machine learning algorithm called EDT-STACK (Stacking Ensembles-Based Decision Tree) that combines several decision tree-based methods using a stacking ensemble technique. The model is trained and tested on a dataset of 500 tires (new and disposed) with different tread depths, The model achieves 99 % accuracy in all classes, demonstrating its efficacy in classifying tire conditions from tread depth data. The study also compares the performance of EDT-STACK with other algorithms. Its superior performance outshines other decision tree algorithms, such as XGBoost, AdaBoost, Random Forest, ID3, and Histogram-based Decision Tree, which achieve accuracies of 98 %, 78 %, 85 %, 98 %, and 98 %, respectively. This study concludes that EDT-STACK offers an innovative solution for tire condition assessment, which can enhance road safety, reduce environmental impacts, and optimize vehicle maintenance.

Analysis of Off-Road Tire Cornering Characteristics by Using Advanced Analytical Techniques

ABSTRACT This paper focuses on analysis of the cornering characteristics of an off-road truck tire running under several operating conditions over different soils. The finite element analysis (FEA) method is used to model the Goodyear RHD 315/80R22.5 truck tire, and the smoothed-particle hydrodynamics (SPH) method is used to model the soil. The goal of this research is to provide a virtual testing environment in Pam-Crash software as an alternative to actual tests for FEA and SPH analyses of rolling tire interactions on deformable terrains. The study on the effects of different operating parameters on the cornering performance combined with the sensitivity study can be of interest to tire engineers or vehicle engineers because they provide insight into the design and real-time behavior of a vehicle. Tire and soil models are validated using experimental data and published measurements, showing good agreement. The tire–soil interaction is investigated under different tire conditions, such as longitudinal speed, inflation pressure, vertical load, and slip angle, and under various soil characteristics, such as cohesion, internal friction angle, and rut depth. Cornering force, self-aligning moment, and overturning moment are studied as the fundamental cornering characteristics that affect truck lateral stability and control. Owing to the excessive computational demands posed by the FEA-SPH tire–soil models, we propose unique mathematical relationships for estimating the cornering characteristics of free-rolling as well as driven truck tires in an efficient manner. The genetic algorithm (GA) technique is used to develop relationships between the cornering parameters and operating conditions. We conclude that the identified mathematical relationships could provide very good estimations of the cornering characteristics under a broad range of operating conditions and soils. The GA equations will ultimately be implemented into a full vehicle model to evaluate the full vehicle performance.

The future of tire energy: a novel one-end cap structure for sustainable energy harvesting

Piezoelectric energy harvesting is gaining popularity as an eco-friendly solution to harvest energy from tire deformation for tire condition monitoring systems in vehicles. Traditional piezoelectric harvesters, such as cymbal and bridge structures, cannot be used inside tires due to their design limitations. The wider adoption of renewable energy sources into the energy system is increasing rapidly, reflecting a global attraction toward the utilization of sustainable power sources (Aljendy et al. in Int J Power Energy Convers 12(4): 314–337, 2021; Yesner et al. in Evaluation of a novel piezoelectric bridge transducer. In: 2017 Joint IEEE International Symposium on the Applications of Ferroelectric (ISAF)/International Workshop on Acoustic Transduction Materials and Devices (IWATMD)/Piezoresponse Force Microscopy (PFM). IEEE, 2017). The growing interest in capturing energy from tire deformation for Tire Pressure Monitoring Systems (TPMS) aligns with this trend, providing a promising and self-sustaining alternative to traditional battery-powered systems. This study presents a novel one-end cap tire strain piezoelectric energy harvester (TSPEH) that can be used efficiently and reliably inside a tire. The interaction between the tire and energy harvester was analyzed using a decoupled modeling approach, which showed that stress concentration occurred along the edge of the end cap. The TSPEH generated a maximum voltage of 768 V under 2 MPa of load, resulting in an energy output of 32.645 J/rev under 1 MPa. The computational findings of this study were consistent with previous experimental investigations, confirming the reliability of the numerical simulations. The results suggest that the one-end cap structure can be an effective energy harvester inside vehicle tires, providing a valuable solution for utilizing one-end cap structures in high-deformation environments such as vehicle tires.

Monitoring the condition of nitrogen-filled tires using weightless neural networks

The novelty of this paper revolves around monitoring the condition of nitrogen-filled tires through the fusion of features and utilization of weightless neural networks. A tire pressure monitoring system (TPMS) plays a crucial role in ensuring vehicle safety and comfort. Reckless driving, poor road conditions, continual operation, higher road friction and excessive load are certain factors that can degrade the longevity of tires. Such conditions can result in instantaneous fault attacks in tires raising a concern for safety and comfort. To apply instantaneous and accurate fault diagnosis, the present study leverages machine learning techniques through the integration of an adaptive and robust algorithm, namely, the Wilkes, Stonham and Aleksander Recognition Device (WiSARD) classifier. The experiment uses three types of features namely, statistical, histogram and autoregressive moving average (ARMA) features. The J48 decision tree algorithm was used to pinpoint the key attributes crucial for classification. Following this, the identified attributes were segregated into training and testing datasets, facilitating the evaluation of the WiSARD classifier. Hyperparameter tuning was carried out to achieve optimal value for maximizing classification accuracy and minimizing computational time. Among the features considered, ARMA features delivered the best test set accuracy of about 96.18%.

Application of feature fusion strategy for monitoring the condition of nitrogen filled tires using tree family of classifiers

The tire pressure monitoring systems (TPMS) are dedicated vehicle systems that calculate the tire pressure under various conditions. Proper maintenance of tire pressure can have a significant impact on enhancing vehicle handling, vehicle performance, occupant safety, comfort and fuel efficiency. Recent years have seen a shift in the preference for nitrogen-filled tires over air filled due to the superior thermal stability and uniform pressure management characteristics displayed by nitrogen-filled tires. The present article details the application of machine learning in TPMS to provide more insights into the tire behaviour for four different tire conditions (puncture, idle, high and normal). This paper specifically focuses on the collaborative approach that combines various features extracted with tree-based classifiers. Vertical wheel hub vibrations were captured using an accelerometer from which distinct features like autoregressive moving average (ARMA), statistical and histogram were extracted. With the application of J48, the most significant and contributing features were identified for every feature set extracted that was fed into tree-based classifiers. The best-performing classifier for every feature set was determined to be 95.83% (statistical–random forest), 93.75% (histogram-optimized forest) and 93.75% (ARMA–random forest). Furthermore, an extensive analysis was carried out to determine the impact of the feature fusion approach on feature combinations like statistical-histogram, histogram-ARMA, statistical-ARMA and statistical-histogram-ARMA. The experimental results indicate a commendable classification accuracy of 97.92% for a feature fusion of statistical-histogram-ARMA features with a forest penalizing attributes algorithm.

A spoke strain-based method to estimate tire condition parameters for intelligent tires

Previous research on intelligent tires has shown that strain gauges are suitable for measuring the dynamic characteristics of tires. However, the process of mounting these gauges onto the tire tread and connecting the necessary wiring is relatively challenging. Furthermore, the high-speed rotation of the tire can generate significant heat and noise, which can adversely affect signal acquisition. With the aim of developing an innovative intelligent tire system, we endeavored to install strain gauges onto the spokes. Through analyzing the spokes' deformation characteristics in various driving conditions and directions (radial, longitudinal, and lateral), we determined the strain-sensitive areas and characteristic points on the spokes. Estimation models for tire forces, slip ratio, and slip angle were constructed successfully by considering the relationship between radial force, longitudinal force, lateral force, and strain on the spokes. Our simulation experiments validated these models. Unlike previous models for intelligent tires, the proposed estimation model achieves high accuracy without requiring complex algorithms to estimate tire condition parameters. Furthermore, incorporating strain gauges onto the spokes removes numerous superfluous complexities. The addition of this feature broadens the study scope of intelligent tires and presents novel insights for potential future advancements.

Research on simplified tire finite element modeling and simulation method

A simplified tire finite element model modeling and simulation method with high efficiency and accuracy is proposed to address the issues of poor efficiency and low accuracy in tire finite element simulation. Firstly, the detailed finite element model of the tire is established, and the viscoelastic material parameters are determined through theoretical analysis and simulation verification. Then, the Hyperelastic material parameters are obtained through cyclic Tensile testing, and finally, the static tire condition test verification is completed. Based on the established detailed finite element model of the tire, the influence of different rubber materials on the dynamic characteristics of the tire is studied. On this basis, simplified friction and structure models are proposed to complete the establishment of a simplified tire finite element model. The simulation results of lateral and longitudinal slip conditions are compared with experimental data by implanting a finite element friction model that considers slip velocity and contact pressure. Through simulation analysis, it was found that the tread compound has a significant impact on the dynamic characteristics of the tire, while other compounds have a relatively small impact. Simplifying the tire finite element model can significantly improve the efficiency of finite element simulation and reduce convergence issues. The comparison accuracy between the finite element model simulation results and experimental data is relatively high, with the average accuracy of longitudinal force, lateral force, and correction moment reaching 89%, 95%, and 81%, respectively. This verifies the correctness and effectiveness of the simplified tire finite element model modeling and simulation method. This method provides certain reference significance for improving the efficiency of tire finite element simulation and providing virtual matching between tires and the entire vehicle.

A Study on Wheel Member Condition Recognition Using 1D–CNN

The condition of a railway vehicle’s wheels is an essential factor for safe operation. However, the current inspection of railway vehicle wheels is limited to periodic major and minor maintenance, where physical anomalies such as vibrations and noise are visually checked by maintenance personnel and addressed after detection. As a result, there is a need for predictive technology concerning wheel conditions to prevent railway vehicle damage and potential accidents due to wheel defects. Insufficient predictive technology for railway vehicle’s wheel conditions forms the background for this study. In this research, a real-time tire wear classification system for light-rail rubber tires was proposed to reduce operational costs, enhance safety, and prevent service delays. To perform real-time condition classification of rubber tires, operational data from railway vehicles, including temperature, pressure, and acceleration, were collected. These data were processed and analyzed to generate training data. A 1D–CNN model was employed to classify tire conditions, and it demonstrated exceptionally high performance with a 99.4% accuracy rate.

Super-tough, super-elastic, temperature-responsive, and tunable viscoelastic elastomer enabled by embedding nanosized liquid metal droplets

Liquid metal (LM) based composites are playing irreplaceable roles in many emerging fields such as stretchable and wearable electronics, soft robotics. However, it is still challenging to facilely fabricate the LM-based elastomers with nanosized and well-dispersed LM domains. Herein, the LM droplets filled elastomer nanocomposites (ENCs) with temperature-responsive, super-tough, super-elastic and tunable viscoelastic properties are introduced. By employing the conventional rubber processing method, LM is fragmented into nanoscale droplets and dispersed uniformly in cross-linked natural rubber (NR) without compromising the soft and highly stretchable properties of the matrix. In addition to the remarkable enhancement in tear resistance, the toughness of the resulting composites is strikingly improved as lowering the applied temperature, which is attributed to the phase transition and the simultaneous volume expansion of LM droplets. Surprisingly, for the viscoelasticity, this LM-based ENCs exhibit almost the same dynamic hysteresis with the pure NR system at the service condition of automobile tires, which is remarkably reduced compared to the traditional ENCs filled with rigid nanoparticles. Furthermore, this material also shows a good damping property for noise attenuation in the case of submarine covering. Collectively, this work opens a new avenue for the next generation of high-performance and multifunctional ENCs equipped in low-temperature working conditions.

A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine).

The wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the operation of railway vehicles. To address this issue, this paper proposes a method for predicting abnormalities in railway wheels in advance and enhancing the learning and prediction performance of machine learning algorithms. Data were collected during the operation of Line 4 of the Busan Metro in South Korea by directly attaching sensors to the railway vehicles. Through the analysis of key factors in the collected data, factors that can be used for tire condition classification were derived. Additionally, through data distribution analysis and correlation analysis, factors for classifying tire conditions were identified. As a result, it was determined that the z-axis of acceleration has a significant impact, and machine learning techniques such as SVM (Linear Kernel, RBF Kernel) and Random Forest were utilized based on acceleration data to classify tire conditions into in-service and defective states. The SVM (Linear Kernel) yielded the highest recognition rate at 98.70%.

Design and Implementation of Intelligent Tire Detection System Based on Esp8266 IoT Platform and Deep Learning Technology

<p>傳統上，市售的胎壓偵測系統(TPMS)僅能透過測量胎壓、胎溫來判斷輪胎狀態，無法即時檢測如：輪框變形、胎面異常剝離、輪胎附著異物、異常抖動及打滑等的輪胎異常狀況，若駕駛有所疏忽，將造成嚴重的危害。因此，我們研究設計一套智慧輪胎系統，透過量測輪胎運行間的慣性感測資訊，包含：三軸加速度、角速度、絕對方向，再結合 AI 演算法之辨識技術，動態檢測出輪胎異常狀況，並實作設計下述物聯網平台元件 : 1.安裝於輪框上之硬體裝置，可偵測輪胎行進間之異常數值，2.具即時監測與異常提醒、維修保養建議、車友討論平台等功能之手機應用程式，3.基於深度學習神經網路技術辨識各式輪胎異常狀況，4.建立跨平台智慧輪胎網頁介面供職業車隊管理停車場。經實驗測試結果，本系統的 AI 判讀準確率高達 99.17%。</p> <p> </p><p>The tire pressure monitoring system (TPMS) sold on the market can only judge the tire status by measuring the tire pressure and tire temperature, and cannot detect such things as: wheel frame deformation, abnormal tread peeling, foreign objects attached to the tire, abnormal vibration and skidding, etc. If the tire is abnormal, if the driver is negligent, it will cause serious harm. Therefore, we design a set of smart tire system, through the measurement of inertial sensing information during tire operation, including: three-axis acceleration, angular velocity, absolute direction, combined with the identification technology of AI algorithm, dynamically detect abnormal tire conditions, and Realize the design of the following IoT platform components: 1. The hardware device installed on the wheel frame can detect abnormal values during tire travel. 2. It has real-time monitoring and abnormal reminders, maintenance suggestions, and a discussion platform for riders, etc. Functional mobile phone application, 3. Based on deep learning neural network technology to identify various tire abnormalities, 4. Establish a cross-platform smart tire web interface for professional fleets to manage parking lots. According to the experimental test results, the AI interpretation accuracy rate of this system is as high as 99.17%.</p> <p> </p>

Real-Time Monitoring of Tire Condition with Fast Detection Passive and Wireless TPMS

<div class="section abstract"><div class="htmlview paragraph">Accurate tire pressure monitoring system (TPMS) is of great practical importance and the reliability and safety of its power supply module has great concern. The piezoelectric-based surface acoustic wave (SAW) sensor is considered to have great potential in this field because of its passive, wireless and small size advantages. This paper presents the application of passive and wireless SAW sensors for real-time tire condition monitoring. The pressure sensitive structure is optimized and a three-resonator structure is also designed sensing temperature and pressure. Furthermore, a fast detection system is developed to realize high-speed signal acquisition. At last, experiments are executed and the SAW temperature and pressure sensor property is measured. The results show that the designed SAW sensor can realize real-time monitoring of tire condition; the temperature measurement range can reach -40~120°C with an accuracy of ±1°C; the pressure measurement range can reach 0~2MPa with an accuracy of 0.2MPa. This paper indicates the wireless and passive SAW temperature and pressure sensor system has the potential for application in real-time monitoring of tire condition.</div></div>

센서 데이터 기반의 타이어 상태진단 알고리즘 개발

Purpose: Tire maintenance is essential for safety, as tire failure can cause significant damage to human health and infrastructure during light rail operations. Therefore, we developed a diagnostic algorithm for light rail rubber tires to prevent such catastrophic events.BRMethods: Vibration signals measured by tri-axis accelerometers were acquired during real-world light rail operation, and we compared vibrations among various tire states, established a health index, and developed a model for determining tire state.BRResults: The most important type of vibration in terms of tire state was x-axis vibration. Our model determined tire states by calculating x-axis vibration differences in various tire conditions. Furthermore, high model accuracy was confirmed by stratified k-fold cross-validation.BRConclusion: Our diagnostic algorithm for determining tire condition reduces operating and support costs and promotes reliability and safety by enabling timely and appropriate maintenance that considers the age of individual tires. Thus, it could replace existing time-based maintenance protocols.

Tire Condition Monitoring Using Transfer Learning-Based Deep Neural Network Approach.

Monitoring tire condition plays a deterministic role in the overall safety and economy of an automobile. The tire condition monitoring system (TCMS) alerts the driver of the vehicle if the inflation pressure of a particular tire decreases below a specific value. Owing to the high costs involved in realizing this system, most vehicles do not feature this technology as a standard. With highly robust and accurate sensors making their way into an increasing number of applications, obtaining signals of varied types (especially vibration signals) is becoming easier and more modularized. In addition, feature-based machine learning techniques that enable accurate responses to varied input conditions have sought greater scientific attention. However, deep learning is gradually finding greater applications pertaining to condition monitoring. One approach of deep learning is presented in this paper, which instantaneously monitors the vehicle tire condition. For this purpose, vibration signals were obtained through the rotation of the tire under different inflation pressure conditions using a low-cost microelectromechanical system (MEMS) accelerometer.

TC-Driver: A Trajectory Conditioned Reinforcement Learning Approach to Zero-Shot Autonomous Racing

Autonomous racing is becoming popular for academic and industry researchers as a test for general autonomous driving by pushing perception, planning, and control algorithms to their limits. While traditional control methods such as model predictive control are capable of generating an optimal control sequence at the edge of the vehicles’ physical controllability, these methods are sensitive to the accuracy of the modeling parameters, such as tire modeling coefficients. As model mismatch is inevitable in reality, the heuristic nature of Reinforcement Learning (RL) offers a viable approach to modeling robustness. This paper presents TC-Driver, an RL approach for robust control in autonomous racing. In particular, the TC-Driver agent is conditioned by a trajectory generated by any arbitrary traditional high-level trajectory planner. The proposed TC-Driver architecture addresses the tire parameter modeling inaccuracies by exploiting the learning capabilities of RL while utilizing the reliability of traditional planning methods in a hybrid fashion. We train the agent under varying tire conditions, allowing it to generalize to different model parameters, aiming to increase the racing capabilities of the system in practice. Experimental results demonstrate that the proposed hybrid RL architecture of the TC-Driver improves the generalization robustness of autonomous racing agents when compared to a previous state-of-the-art end-to-end-based architecture. Namely, the proposed controller yields a 29-fold improvement in crash ratio when facing model mismatch and can zero-shot transfer its behavior on unseen tracks which present completely new features, while the end-to-end baseline fails. When deployed on a physical system, the proposed architecture demonstrates zero-shot Sim2Real capabilities that outperform end-to-end agents 10-fold in terms of crash ratio while exhibiting similar driving characteristics in reality as in simulation.