Driving comfort is a crucial consideration in the automotive industry. In the realm of autonomous driving, comfort has always been a factor that requires continuous improvement. A common approach to improving driving comfort is through the optimization of local path planning. Nevertheless, it is imperative to recognize that macroscopic factors, including traffic flow and road conditions, wield a substantial influence on comfort. For instance, complex traffic scenarios increase the possibility of emergency braking, thereby affecting comfort. Consequently, investigating the intricate interplay between comfort and global path planning becomes essential. This paper introduces a methodology and framework for predicting driving comfort by leveraging road information. The study established a road information-driving comfort dataset and devised prediction models using multi-head attention mechanism. The ensuing discussion elucidates the practical application of the model in path planning through examples and tests. Following the path optimized by the model, the vehicles exhibited a reduction in jerk. This research predicted driving comfort based on road information and integrated it with global path planning, which holds significant implications for autonomous driving navigation systems and provides a valuable reference for related research.

Comfort is a pivotal consideration in the realm of autonomous driving, prompting researchers to address methods of enhancing driving comfort for autonomous driving vehicles. A central focus of current research revolves around the judicious planning of driving trajectories with a primary emphasis on comfort. Given the transient nature of comfort, prevailing path planning strategies predominantly center on local considerations. Nevertheless, it is imperative to recognize that macroscopic factors, including traffic flow and road conditions, wield a substantial influence on comfort. For instance, complex traffic scenarios elevate the likelihood of emergency braking, thereby affecting comfort. Consequently, investigating the intricate interplay between comfort and global path planning becomes essential. In the context of autonomous driving, this paper introduces a methodology and framework for predicting driving comfort by leveraging road information. The study establishes a comprehensive road information-comfort dataset and devises predictive models for driving comfort, employing a multi-head attention approach. The ensuing discussion elucidates the practical application of the model in path selection and planning through illustrative examples. Finally, real-road vehicle tests were conducted. Following the utilization of the path optimized by the model, the autonomous driving car exhibited an approximate 17.3% reduction in the mean longitudinal jerk and a 9.7% reduction in the mean lateral jerk. These results serve to validate the effectiveness and significance of the proposed model. Notably, this research marks the pioneering integration of driving comfort with global path planning, which is of immense importance for autonomous driving navigation systems, offering an insightful and valuable reference for related study.

The bird’s-eye view (BEV) method, which is a vision-centric representation-based perception task, is essential and promising for future Autonomous Vehicle perception. It has advantages of fusion-friendly, intuitive, end-to-end optimization and is cheaper than LiDAR. The performance of existing BEV methods, however, would be deteriorated under the situation of a tire blow-out. This is because they quite rely on accurate camera calibration which may be disabled by noisy camera parameters during blow-out. Therefore, it is extremely unsafe to use existing BEV methods in the tire blow-out situation. In this paper, we propose a geometry-guided auto-resizable kernel transformer (GARKT) method, which is designed especially for vehicles with tire blow-out. Specifically, we establish a camera deviation model for vehicles with tire blow-out. Then we use the geometric priors to attain the prior position in perspective view with auto-resizable kernels. The resizable perception areas are encoded and flattened to generate BEV representation. GARKT predicts the nuScenes detection score (NDS) with a value of 0.439 on a newly created blow-out dataset based on nuScenes. NDS can still obtain 0.431 when the tire is completely flat, which is much more robust compared to other transformer-based BEV methods. Moreover, the GARKT method has almost real-time computing speed, with about 20.5 fps on one GPU.

In this paper, a learning based Model Predictive Control (MPC) using a low dimensional residual model is proposed for autonomous driving. One of the critical challenge in autonomous driving is the complexity of vehicle dynamics, which impedes the formulation of accurate vehicle model. Inaccurate vehicle model can significantly impact the performance of MPC controller. To address this issue, this paper decomposes the nominal vehicle model into invariable and variable elements. The accuracy of invariable component is ensured by calibration, while the deviations in the variable elements are learned by a low-dimensional residual model. The features of residual model are selected as the physical variables most correlated with nominal model errors. Physical constraints among these features are formulated to explicitly define the valid region within the feature space. The formulated model and constraints are incorporated into the MPC framework and validated through both simulation and real vehicle experiments. The results indicate that the proposed method significantly enhances the model accuracy and controller performance.

Compactly supported orthogonal wavelet filters are extensively applied to the analysis and description of abrupt signals in fields such as multimedia. Based on the application of an elementary method for compactly supported orthogonal wavelet filters and the construction of a system of nonlinear equations for filter coefficients, we design compactly supported orthogonal wavelet filters, in which both the scaling and wavelet functions have many vanishing moments, by approximately solving the system of nonlinear equations. However, when solving such a system about filter coefficients of compactly supported wavelets, the most widely used method, the Newton Iteration method, cannot converge to the solution if the selected initial value is not near the exact solution. For such, we propose optimization algorithms for the Gauss-Newton type method that expand the selection range of initial values. The proposed method is optimal and promising when compared to other works, by analyzing the experimental results obtained in terms of accuracy, iteration times, solution speed, and complexity