10 May 2022 in IEEE Transactions on Intelligent Vehicles
Precise localization is essential but also challenging for autonomous vehicles. In this article, A novel visual localization method is proposed. Specifically, a semantic local map describing the local environment is built with images sequence and wheel-inertial ego-motion results. Then the local semantic map is matched with the online map database for camera position estimation. The key novelty of the method lies in using a supervised neural network to simplify the map-matching problem, which avoids the complex data association and optimization processes. The network encodes the maps, infers the feature similarity, and predicts the camera position. The visual localization results are then loosely integrated with other onboard sensors by an invariant Kalman filter. We evaluate the map-matching module and the overall fusion system on scenario tests. The experiment results validate the effectiveness of the learning-based map-matching method. And the accuracy of the overall system is satisfactory, with mean absolute errors of 0.039m and 0.167m in the lateral and longitudinal directions, respectively.
15 November 2023 in IEEE Transactions on Industrial Informatics
The steer-by-wire (SbW) system has gained recognition as the future of intelligent vehicles due to its attributes, such as safety, simplification, and flexibility. However, the elimination of mechanical linkage necessitates the provision of artificial steering feedback torque (SFT), which is crucial for the potential driver to manipulate the vehicle. To enhance the steering feel, this article extends the SFT design range and proposes an SFT prediction scheme based on the sequence-to-sequence (S2S) network with the switcher-assisted (SA) training algorithm. The models of the electric power steering (EPS) and SbW are first established to analyze the input features. The S2S network with gated recurrent units (GRU) is then presented, where the encoder scheme incorporates the squeeze-and-excitation (SE) operation to achieve adaptive feature recalibration. Subsequently, the SA algorithm is proposed to alleviate the exposure bias based on the principle of multitask learning (MTL), wherein online training is regarded as the main task and offline training is treated as the auxiliary task. The weighting coefficients between tasks are optimized using an assisted network named switcher, facilitating a gradual transition from MTL to the single main task, thereby avoiding complex tuning processes. The validation results indicate the proposed scheme outperforms existing methods regarding estimation and prediction. The ablation experiments are further conducted to illustrate the effectiveness of SE blocks and the SA algorithm. Finally, the SFT construction simulation, involving target prediction and torque tracking, is conducted, validating that variable-length prediction can adapt to various conditions and improve tracking performance.
7 June 2022 in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Sideslip angle estimation is vital to the safety and active control of autonomous vehicles. In this paper, an innovative vehicle kinematic-based sideslip angle estimation method is proposed. The method is built on multi-sensor fusion, which fuses the information of inertial measurement unit, global navigation satellite system (GNSS), and onboard sensors to continuously estimate the attitude and velocity of the vehicle and thus obtain the sideslip angle. The invariant extended Kalman filter framework is adopted and the left-invariant form is derived to implement the GNSS measurement update. In order to solve the unobservability problem when only a single GNSS receiver is equipped, the vehicle motion constraint is introduced into the filter to improve the accuracy of heading angle estimation. The method is validated by field test and the results show that the method is robust in terms of converge efficiency. Furthermore, the sideslip angle estimation accuracy is satisfactory with the average absolute error less than 0.25°, which meets the active safety control requirements for autonomous driving.
24 July 2023 in IEEE Transactions on Transportation Electrification
Integrated brake system (IBS) is gaining attention due to its superior performance and applicability in high-level autonomous vehicles. Despite its high potential, the strong coupling and nonlinearity of the IBS system present significant challenges to controller design. The precision and response speed of the controller are critical factors affecting the performance of the IBS system. This paper proposes a pressure controller based on offset-free explicit model predictive control (OFEMPC) architecture to enhance accuracy and robustness. First, the pressure-position relationship is modeled as a second-order polynomial based on experimental results. Second, the Karnopp friction model is adopted for feedforward compensation, and is optimized according to the system characteristics. Further, a disturbance observer is constructed to estimate the total disturbance, which is composed of model mismatch, time-varying parameters, and unexpected disturbances. Last but not least, an explicit model predictive controller (EMPC) is constructed. To validate the performance of the OFEMPC controller, a co-simulation platform and a bench test are conducted. The results of the simulations and experiments demonstrate that the OFEMPC improves tracking precision and disturbance suppression capability. Additionally, the real-time performance is validated on the microchip.
13 September 2022 in IEEE Transactions on Vehicular Technology
On-demand four-wheel-drive vehicles have apparent advantages in power performance, stability, and manufacturing costs. The transfer case clutch is the core component of on-demand four-wheel-drive vehicles. The torque of the transfer case clutch is significant for control while not easy to measure or calculate. Thus, this paper aims to estimate the transfer case clutch torque. First, this paper constructs a model of transfer case clutch and vehicle model for simulation. Second, the system longitudinal model is established and an extended Kalman filter based unknown input observer is designed. Third, the effectiveness is validated by the simulation and vehicle experiments. The results show that the method has good performance compared to the friction-based method, and the accumulated relative error is less than 10%.
20 March 2024 in IEEE Transactions on Vehicular Technology
Brake-by-wire system (BBW) is quite important for the development of high-level autonomous vehicle which requires fully decoupled structure and superior braking performance. Integrated braking system (IBS) is a state-of-the-art technology of hydraulic BBW, consisting of mechanical, electrical, and hydraulic subsystems. However, the inherent nonlinear characteristics of hydraulic transmission dynamics cause delays and fluctuations in wheel cylinder pressure (WCP), which significantly impact brake performance and passenger comfort. Furthermore, the coupling of the subsystems within the IBS system amplifies the intricacies and challenges associated with controller design. This paper proposes a WCP control architecture to shorten the response time of WCP, suppress pressure fluctuation, and ensure stability. Further, a combined extended state observer (CESO) is designed to estimate unmeasurable states and total disturbance which includes model mismatch, uncertainties, and friction. Additionally, a WCP nonlinear controller (WNC) based on the backstepping method is designed and proved stable theoretically. The response time has been shortened 30 $\mathbf{\%}$ approximately and the tracking precision has been improved 50 $\mathbf{\%}$ approximately. Simulation results demonstrate that the proposed control architecture accurately estimates states, suppresses disturbances, meanwhile improves braking performance. The effectiveness and practical application of this control architecture are further validated through experiments on a test bench.