Prospective Role of Foundation Models in Advancing Autonomous Vehicles.

With the development of artificial intelligence and breakthroughs in deep learning, large-scale foundation models (FMs), such as generative pre-trained transformer (GPT), Sora, etc., have achieved remarkable results in many fields including natural language processing and computer vision. The application of FMs in autonomous driving holds considerable promise. For example, they can contribute to enhancing scene understanding and reasoning. By pre-training on rich linguistic and visual data, FMs can understand and interpret various elements in a driving scene, and provide cognitive reasoning to give linguistic and action instructions for driving decisions and planning. Furthermore, FMs can augment data based on the understanding of driving scenarios to provide feasible scenes of those rare occurrences in the long tail distribution that are unlikely to be encountered during routine driving and data collection. The enhancement can subsequently lead to improvement in the accuracy and reliability of autonomous driving systems. Another testament to the potential of FMs' applications lies in world models, exemplified by the DREAMER series, which showcases the ability to comprehend physical laws and dynamics. Learning from massive data under the paradigm of self-supervised learning, world models can generate unseen yet plausible driving environments, facilitating the enhancement in the prediction of road users' behaviors and the off-line training of driving strategies. In this paper, we synthesize the applications and future trends of FMs in autonomous driving. By utilizing the powerful capabilities of FMs, we strive to tackle the potential issues stemming from the long-tail distribution in autonomous driving, consequently advancing overall safety in this domain.

A modeling method for two-dimensional two-wheeler driving behavior during severe conflict interaction at intersections.

The safety of two-wheelers is a serious public safety issue nowadays. Two-wheelers usually have severe conflict interaction with vehicles at intersections, such as running red lights, which is very likely to cause traffic accidents. Therefore, a model of two-wheeler driving behavior in conflicting interactions can provide guidance for traffic safety management on one hand, and can be used for the development and testing of autonomous vehicles on the other. However, the existing models perform poorly when interacting with vehicles. To address the problems, this paper proposes a modeling method (an improved social force model, ISFM) for two-dimensional two-wheeler driving simulation for conflict interaction at intersections. Based on analysis of naturalistic driving study data, when two-wheelers encounter with vehicles, their driving intentions and trajectories can be categorized into two groups, which are yielding and overtaking. Therefore, the vehicle-related social forces are designed to be a set of two forces rather than a repulsion force in original SFM, which is a yielding force based on the relative distance between the two-wheeler and the vehicle, and an overtaking force based on the velocity of the two-wheeler itself. This opens up the possibilities for modeling the multi-modal driving intention of two-wheelers encountering with cross traffic. Based on ISFM, a bicycle model, a powered two-wheeler (PTW) model and a model of a group of PTWs, are then constructed. Compared to the original SFM, ISFM increases the precision of driving intention prediction by 19.7 % (yielding situation) and 25.0 % (overtaking situation), and reduces the root mean square error between simulated and actual trajectories by 7.8 % and 14.8 % on the bicycle model and the PTW model, respectively. Meanwhile, the model of a group of PTWs also performs well. Finally, the results of ablation experiments also validate the effectiveness of the social force designed based on velocity.

A synthetic digital city dataset for robustness and generalisation of depth estimation models.

Existing monocular depth estimation driving datasets are limited in the number of images and the diversity of driving conditions. The images of datasets are commonly in a low resolution and the depth maps are sparse. To overcome these limitations, we produce a Synthetic Digital City Dataset (SDCD) which was collected under 6 different weather driving conditions, and 6 common adverse perturbations caused by the data transmission. SDCD provides a total of 930 K high-resolution RGB images and corresponding perfect observed depth maps. The evaluation shows that depth estimation models which are trained on SDCD provide a clearer, smoother, and more precise long-range depth estimation compared to those trained on one of the best-known driving datasets KITTI. Moreover, we provide a benchmark to investigate the performance of depth estimation models in different adverse driving conditions. Instead of collecting data from the real world, we generate the SDCD under severe driving conditions with perfect observed data in the digital world, enhancing depth estimation for autonomous driving.

Adaptive Safe Reinforcement Learning With Full-State Constraints and Constrained Adaptation for Autonomous Vehicles.

High-performance learning-based control for the typical safety-critical autonomous vehicles invariably requires that the full-state variables are constrained within the safety region even during the learning process. To solve this technically critical and challenging problem, this work proposes an adaptive safe reinforcement learning (RL) algorithm that invokes innovative safety-related RL methods with the consideration of constraining the full-state variables within the safety region with adaptation. These are developed toward assuring the attainment of the specified requirements on the full-state variables with two notable aspects. First, thus, an appropriately optimized backstepping technique and the asymmetric barrier Lyapunov function (BLF) methodology are used to establish the safe learning framework to ensure system full-state constraints requirements. More specifically, each subsystem's control and partial derivative of the value function are decomposed with asymmetric BLF-related items and an independent learning part. Then, the independent learning part is updated to solve the Hamilton-Jacobi-Bellman equation through an adaptive learning implementation to attain the desired performance in system control. Second, with further Lyapunov-based analysis, it is demonstrated that safety performance is effectively doubly assured via a methodology of a constrained adaptation algorithm during optimization (which incorporates the projection operator and can deal with the conflict between safety and optimization). Therefore, this algorithm optimizes system control and ensures that the full set of state variables involved is always constrained within the safety region during the whole learning process. Comparison simulations and ablation studies are carried out on motion control problems for autonomous vehicles, which have verified superior performance with smaller variance and better convergence performance under uncertain circumstances. The effectiveness of the safe performance of overall system control with the proposed method accordingly has been verified.

Computational Efficient Motion Planning Method for Automated Vehicles Considering Dynamic Obstacle Avoidance and Traffic Interaction.

In complex driving scenarios, automated vehicles should behave reasonably and respond adaptively with high computational efficiency. In this paper, a computational efficient motion planning method is proposed, which considers traffic interaction and accelerates calculation. Firstly, the behavior is decided by connecting the points on the unequally divided road segments and lane centerlines, which simplifies the decision-making process in both space and time span. Secondly, as the dynamic vehicle model with changeable longitudinal velocity is considered in the trajectory generation module, the C/GMRES algorithm is used to accelerate the calculation of trajectory generation and realize on-line solving in nonlinear model predictive control. Meanwhile, the motion of other traffic participants is more accurately predicted based on the driver's intention and kinematics vehicle model, which enables the host vehicle to obtain a more reasonable behavior and trajectory. The simulation results verify the effectiveness of the proposed method.

Barrier Lyapunov Function-Based Safe Reinforcement Learning for Autonomous Vehicles With Optimized Backstepping.

Guaranteed safety and performance under various circumstances remain technically critical and practically challenging for the wide deployment of autonomous vehicles. Safety-critical systems in general, require safe performance even during the reinforcement learning (RL) period. To address this issue, a Barrier Lyapunov Function-based safe RL (BLF-SRL) algorithm is proposed here for the formulated nonlinear system in strict-feedback form. This approach appropriately arranges and incorporates the BLF items into the optimized backstepping control method to constrain the state-variables in the designed safety region during learning. Wherein, thus, the optimal virtual/actual control in every backstepping subsystem is decomposed with BLF items and also with an adaptive uncertain item to be learned, which achieves safe exploration during the learning process. Then, the principle of Bellman optimality of continuous-time Hamilton-Jacobi-Bellman equation in every backstepping subsystem is satisfied with independently approximated actor and critic under the framework of actor-critic through the designed iterative updating. Eventually, the overall system control is optimized with the proposed BLF-SRL method. It is furthermore noteworthy that the variance of the attained control performance under uncertainty is also reduced with the proposed method. The effectiveness of the proposed method is verified with two motion control problems for autonomous vehicles through appropriate comparison simulations.

Adaptive Decision-Making for Automated Vehicles Under Roundabout Scenarios Using Optimization Embedded Reinforcement Learning.

The roundabout is a typical changeable, interactive scenario in which automated vehicles should make adaptive and safe decisions. In this article, an optimization embedded reinforcement learning (OERL) is proposed to achieve adaptive decision-making under the roundabout. The promotion is the modified actor of the Actor-Critic framework, which embeds the model-based optimization method in reinforcement learning to explore continuous behaviors in action space directly. Therefore, the proposed method can determine the macroscale behavior (change lane or not) and medium-scale behaviors of desired acceleration and action time simultaneously with high sample efficiency. When scenarios change, medium-scale behaviors can be adjusted timely by the embedded direct search method, promoting the adaptability of decision-making. More notably, the modified actor matches human drivers' behaviors, macroscale behavior captures the human mind's jump, and medium-scale behaviors are preferentially adjusted through driving skills. To enable the agent adapts to different types of the roundabout, task representation is designed to restructure the policy network. In experiments, the algorithm efficiency and the learned driving strategy are compared with decision-making containing macroscale behavior and constant medium-scale behaviors of the desired acceleration and action time. To investigate the adaptability, the performance under an untrained type of roundabout and two more dangerous situations are simulated to verify that the proposed method changes the decisions with changeable scenarios accordingly. The results show that the proposed method has high algorithm efficiency and better system performance.

Strain Distribution Evaluation of Rat Tibia under Axial Compressive Load by Combining Strain Gauge Measurement and Finite Element Analysis.

This study is aimed at providing an effective method for determining strain-load relationship and at quantifying the strain distribution within the whole tibia under axial compressive load on rats. Rat tibial models with axial compressive load were designed. Strains in three directions (0°, 45°, and 90°) at the proximal shaft of the tibia were measured by using a strain gauge rosette, which was used to calculate the maximum and minimum principal strains. Moreover, the strain at the midshaft of the tibia was measured by a single-element strain gauge. The slopes of the strain-load curves with different peak loads were calculated to assess the stability of the strain gauge measurement. Mechanical environment in the whole tibia by the axial compressive load was quantified using finite element analysis (FEA) based on microcomputed tomography images. The von Mises elastic strain distributions of the whole tibiae were evaluated. Slopes of the strain-load curves showed no significant differences among different peak loads (ANOVA; P > 0.05), indicating that the strain-load relationship obtained from the strain gauge measurement was reasonable and stable. The FEA results corresponded to the experimental results with an error smaller than 15% (paired Student's t-test, P > 0.05), signifying that the FEA can simulate the experiment reasonably. FEA results showed that the von Mises elastic strain was the lowest in the middle and gradually increased to both sides along the lateral direction, with the maximal von Mises elastic strain being observed on the posterior side under the distal tibiofibular synostosis. The method of strain gauge measurements and FEA used in this study can provide a feasible way to obtain the mechanical environment of the tibiae under axial compressive load on the rats and serve as a reference for further exploring the mechanical response of the bone by axial compressive load.

Morphological and Microstructural Alterations of the Articular Cartilage and Bones during Treadmill Exercises with Different Additional Weight-Bearing Levels.

The aim of this study was to investigate the morphological and microstructural alterations of the articular cartilage and bones during treadmill exercises with different exercise intensities. Sixty 5-week-old female rats were randomly divided into 10 groups: five additional weight-bearing groups (WBx) and five additional weight-bearing with treadmill exercise groups (EBx), which were subjected to additional weight bearing of x% (x = 0, 5, 12, 19, and 26) of the corresponding body weight of each rat for 15 min/day. After 8 weeks of experiment, the rats were humanely sacrificed and their bilateral intact knee joints were harvested. Morphological analysis of the cartilages and microcomputed tomography evaluation of bones were subsequently performed. Results showed that increased additional weight bearing may lead to cartilage damage. No significant difference was observed among the subchondral cortical thicknesses of the groups. The microstructure of subchondral trabecular bone of 12% and 19% additional weight-bearing groups was significantly improved; however, the WB26 and EB26 groups showed low bone mineral density and bone volume fraction as well as high structure model index. In conclusion, effects of treadmill exercise on joints may be associated with different additional weight-bearing levels, and exercise intensities during joint growth and maturation should be selected reasonably.

Nonlinear gearshifts control of dual-clutch transmissions during inertia phase.

In this paper, a model-based nonlinear gearshift controller is designed by the backstepping method to improve the shift quality of vehicles with a dual-clutch transmission (DCT). Considering easy-implementation, the controller is rearranged into a concise structure which contains a feedforward control and a feedback control. Then, robustness of the closed-loop error system is discussed in the framework of the input to state stability (ISS) theory, where model uncertainties are considered as the additive disturbance inputs. Furthermore, due to the application of the backstepping method, the closed-loop error system is ordered as a linear system. Using the linear system theory, a guideline for selecting the controller parameters is deduced which could reduce the workload of parameters tuning. Finally, simulation results and Hardware in the Loop (HiL) simulation are presented to validate the effectiveness of the designed controller.

Design of a data-driven predictive controller for start-up process of AMT vehicles.

In this paper, a data-driven predictive controller is designed for the start-up process of vehicles with automated manual transmissions (AMTs). It is obtained directly from the input-output data of a driveline simulation model constructed by the commercial software AMESim. In order to obtain offset-free control for the reference input, the predictor equation is gained with incremental inputs and outputs. Because of the physical characteristics, the input and output constraints are considered explicitly in the problem formulation. The contradictory requirements of less friction losses and less driveline shock are included in the objective function. The designed controller is tested under nominal conditions and changed conditions. The simulation results show that, during the start-up process, the AMT clutch with the proposed controller works very well, and the process meets the control objectives: fast clutch lockup time, small friction losses, and the preservation of driver comfort, i.e., smooth acceleration of the vehicle. At the same time, the closed-loop system has the ability to reject uncertainties, such as the vehicle mass and road grade.