Define an agent's current state information as s = (x,y,θ,vx,vy), which includes the x,y positions in the coordinate space, and the yaw angle θ, and the velocities in the X and Y directions. The inverse kinematics can be used to calculate the actions for behavior cloning purpose. With the Bicycle action space, we propose a model to approximate the vehicle dynamics with the goal of minimizing the discrepancy between the predicted vehicle states and the recorded vehicle states. More specifically, define the vehicle's coordinates as x,y in the global coordinate system, and the predicted coordinates as ˆx,ˆy, the goal is to minimize (x ˆx)2 + (y ˆy)2. Define the current vehicle's state information as s, which includes the coordinates of the vehicle in the global coordinate system (x,y), the vehicle's yaw angle θ, the vehicle's speed in the x and y direction vx,vy.

Abstract--Developing a dynamic model for a high-performance vehicle is a complex problem that requires extensive structural information about the system under analysis. This information is often unavailable to those who did not design the vehicle and represents a typical issue in autonomous driving applications, which are frequently developed on top of existing vehicles; therefore, vehicle models are developed under conditions of information scarcity. This paper proposes a lightweight encoder-decoder model based on Gate Recurrent Unit layers to correlate the vehicle's future state with its past states, measured onboard, and control actions the driver performs. The results demonstrate that the model achieves a maximum mean relative error below 2.6% in extreme dynamic conditions. It also shows good robustness when subject to noisy input data across the interested frequency components. Furthermore, being entirely data-driven and free from physical constraints, the model exhibits physical consistency in the output signals, such as longitudinal and lateral accelerations, yaw rate, and the vehicle's longitudinal velocity. N the automotive sector developing a representative vehicle dynamics model is a complex and multifaceted challenge [1]-[3]. Numerous nonlinear factors influence vehicle dynamics, including tire characteristics, suspension geometry, aerodynamics, drivetrain effects, and external environmental factors, such as road surface grip conditions and climatic effects (e.g., wind). Accurately capturing these effects in a computational model requires high-fidelity multibody simulation software and a profound understanding of the vehicle system.

The vehicle dynamics model serves as a vital component of autonomous driving systems, as it describes the temporal changes in vehicle state. In a long period, researchers have made significant endeavors to accurately model vehicle dynamics. Traditional physics-based methods employ mathematical formulae to model vehicle dynamics, but they are unable to adequately describe complex vehicle systems due to the simplifications they entail. Recent advancements in deep learning-based methods have addressed this limitation by directly regressing vehicle dynamics. However, the performance and generalization capabilities still require further enhancement. In this letter, we address these problems by proposing a vehicle dynamics correction system that leverages deep neural networks to correct the state residuals of a physical model instead of directly estimating the states. This system greatly reduces the difficulty of network learning and thus improves the estimation accuracy of vehicle dynamics. Furthermore, we have developed a novel Transformer-based dynamics residual correction network, DyTR. This network implicitly represents state residuals as high-dimensional queries, and iteratively updates the estimated residuals by interacting with dynamics state features. The experiments in simulations demonstrate the proposed system works much better than physics model, and our proposed DyTR model achieves the best performances on dynamics state residual correction task, reducing the state prediction errors of a simple 3 DoF vehicle model by an average of 92.3% and 59.9% in two dataset, respectively.

Drift vehicle control offers valuable insights to support safe autonomous driving in extreme conditions, which hinges on tracking a particular path while maintaining the vehicle states near the drift equilibrium points (DEP). However, conventional tracking methods are not adaptable for drift vehicles due to their opposite steering angle and yaw rate. In this paper, we propose an adaptive path tracking (APT) control method to dynamically adjust drift states to follow the reference path, improving the commonly utilized predictive path tracking methods with released computation burden. Furthermore, existing control strategies necessitate a precise system model to calculate the DEP, which can be more intractable due to the highly nonlinear drift dynamics and sensitive vehicle parameters. To tackle this problem, an adaptive learning-based model predictive control (ALMPC) strategy is proposed based on the APT method, where an upper-level Bayesian optimization is employed to learn the DEP and APT control law to instruct a lower-level MPC drift controller. This hierarchical system architecture can also resolve the inherent control conflict between path tracking and drifting by separating these objectives into different layers. The ALMPC strategy is verified on the Matlab-Carsim platform, and simulation results demonstrate its effectiveness in controlling the drift vehicle to follow a clothoid-based reference path even with the misidentified road friction parameter.

Vehicle API testing verifies whether the interactions between a vehicle's internal systems and external applications meet expectations, ensuring that users can access and control various vehicle functions and data. However, this task is inherently complex, requiring the alignment and coordination of API systems, communication protocols, and even vehicle simulation systems to develop valid test cases. In practical industrial scenarios, inconsistencies, ambiguities, and interdependencies across various documents and system specifications pose significant challenges. This paper presents a system designed for the automated testing of in-vehicle APIs. By clearly defining and segmenting the testing process, we enable Large Language Models (LLMs) to focus on specific tasks, ensuring a stable and controlled testing workflow. Experiments conducted on over 100 APIs demonstrate that our system effectively automates vehicle API testing. The results also confirm that LLMs can efficiently handle mundane tasks requiring human judgment, making them suitable for complete automation in similar industrial contexts.

This paper presents a novel approach to automated drifting with a standard passenger vehicle, which involves a Nonlinear Model Predictive Control to stabilise and maintain the vehicle at high sideslip angle conditions. The proposed controller architecture is split into three components. The first part consists of the offline computed equilibrium maps, which provide the equilibrium points for each vehicle state given the desired sideslip angle and radius of the path. The second is the predictive controller minimising the errors between the equilibrium and actual vehicle states. The third is a path-following controller, which reduces the path error, altering the equilibrium curvature path. In a high-fidelity simulation environment, we validate the controller architecture capacity to stabilise the vehicle in automated drifting along a desired path, with a maximal lateral path deviation of 1 m. In the experiments with a standard passenger vehicle, we demonstrate that the proposed approach is capable of bringing and maintaining the vehicle at the desired 30 deg sideslip angle in both high and low friction conditions.

Vehicle teleoperation has numerous potential applications, including serving as a backup solution for autonomous vehicles, facilitating remote delivery services, and enabling hazardous remote operations. However, complex urban scenarios, limited situational awareness, and network delay increase the cognitive workload of human operators and degrade teleoperation performance. To address this, the successive reference pose tracking (SRPT) approach was introduced in earlier work, which transmits successive reference poses to the remote vehicle instead of steering commands. The operator generates reference poses online with the help of a joystick steering and an augmented display, potentially mitigating the detrimental effects of delays. However, it is not clear which minimal set of sensors is essential for the SRPT vehicle teleoperation control loop. This paper tests the robustness of the SRPT approach in the presence of state estimation inaccuracies, environmental disturbances, and measurement noises. The simulation environment, implemented in Simulink, features a 14-dof vehicle model and incorporates difficult maneuvers such as tight corners, double-lane changes, and slalom. Environmental disturbances include low adhesion track regions and strong cross-wind gusts. The results demonstrate that the SRPT approach, using either estimated or actual states, performs similarly under various worst-case scenarios, even without a position sensor requirement. Additionally, the designed state estimator ensures sufficient performance with just an inertial measurement unit, wheel speed encoder, and steer encoder, constituting a minimal set of essential sensors for the SRPT vehicle teleoperation control loop.

We present a system for estimating the friction of the pavement surface at any curved road section, by arriving at a consensus estimate, based on data from vehicles that have recently passed through that section. This estimate can help following vehicles. To keep costs down, we depend only on standard automotive sensors, such as the IMU, and sensors for the steering angle and wheel speeds. Our system's workflow consists of: (i) processing of measurements from existing vehicular sensors, to implement a virtual sensor that captures the effect of low friction on the vehicle, (ii) transmitting short kinematic summaries from vehicles to a road side unit (RSU), using V2X communication, and (iii) estimating the friction coefficients, by running a machine learning regressor at the RSU, on summaries from individual vehicles, and then combining several such estimates. In designing and implementing our system over a road network, we face two key questions: (i) should each individual road section have a local friction coefficient regressor, or can we use a global regressor that covers all the possible road sections? and (ii) how accurate are the resulting regressor estimates? We test the performance of design variations of our solution, using simulations on the commercial package Dyna4. We consider a single vehicle type with varying levels of tyre wear, and a range of road friction coefficients. We find that: (a) only a marginal loss of accuracy is incurred in using a global regressor as compared to local regressors, (b) the consensus estimate at the RSU has a worst case error of about ten percent, if the combination is based on at least fifty recently passed vehicles, and (c) our regressors have root mean square (RMS) errors that are less than five percent. The RMS error rate of our system is half as that of a commercial friction estimation service.

Autonomous driving has become real; semi-autonomous driving vehicles in an affordable price range are already on the streets, and major automotive vendors are actively developing full self-driving systems to deploy them in this decade. Before rolling the products out to the end-users, it is critical to test and ensure the safety of the autonomous driving systems, consisting of multiple layers intertwined in a complicated way. However, while safety-critical bugs may exist in any layer and even across layers, relatively little attention has been given to testing the entire driving system across all the layers. Prior work mainly focuses on white-box testing of individual layers and preventing attacks on each layer. In this paper, we aim at holistic testing of autonomous driving systems that have a whole stack of layers integrated in their entirety. Instead of looking into the individual layers, we focus on the vehicle states that the system continuously changes in the driving environment. This allows us to design DriveFuzz, a new systematic fuzzing framework that can uncover potential vulnerabilities regardless of their locations. DriveFuzz automatically generates and mutates driving scenarios based on diverse factors leveraging a high-fidelity driving simulator. We build novel driving test oracles based on the real-world traffic rules to detect safety-critical misbehaviors, and guide the fuzzer towards such misbehaviors through driving quality metrics referring to the physical states of the vehicle. DriveFuzz has discovered 30 new bugs in various layers of two autonomous driving systems (Autoware and CARLA Behavior Agent) and three additional bugs in the CARLA simulator. We further analyze the impact of these bugs and how an adversary may exploit them as security vulnerabilities to cause critical accidents in the real world.