Motion prediction is the fundamental input for decision-making in autonomous vehicles. The current motion prediction solutions are designed with a strong reliance on black box predictions based on neural networks (NNs), which is unacceptable for safety-critical applications. Motion prediction with high uncertainty can cause conflicting decisions and even catastrophic results. To address this issue, an uncertainty estimation approach based on the deep ensemble technique is proposed for motion prediction in this paper. Subsequently, the estimated uncertainty is considered in the decision-making module to improve driving safety. Firstly, a motion prediction model based on long short-term memory (LSTM) is built and the deep ensemble technique is utilized to obtain both epistemic and aleatoric uncertainty of the prediction model. Besides, an uncertainty-aware potential field is developed to process the prediction uncertainty. Furthermore, a decision-making framework is proposed based on the model predictive control algorithm that considers the uncertainty-aware potential field, road boundaries, and multiple constraints of vehicle dynamics. Finally, the public available NGSIM, HighD and INTERACTION datasets are used to evaluate the proposed motion prediction model. More importantly, two traffic scenarios are also extracted from NGSIM and INTERACTION datasets to verify the effectiveness of the proposed decision-making method and in particular, its real-time performance is shown by employing a hardware-in-the-loop (HiL) experiment bench.

This paper investigates the path-tracking control issue for autonomous ground vehicles with the integral sliding mode control (ISMC) considering the transient performance improvement. The path-tracking control is converted into the yaw stabilization problem, where the sideslip-angle compensation is adopted to reduce the steady-state errors, and then the yaw-rate reference is generated for the path-tracking purpose. The lateral velocity and roll angle are estimated with the measurement of the yaw rate and roll rate. Three contributions have been made in this paper: 1) To enhance the estimation accuracy for the vehicle states in the presence of the parametric uncertainties caused by the lateral and roll dynamics, a robust extended Kalman filter is proposed based on the minimum model error algorithm; 2) An improved adaptive radial basis function neural network (RBFNN) considering the approximation error adaptation is developed to compensate for the uncertainties caused by the vertical motion; 3) The RBFNN and composite nonlinear feedback (CNF)-based ISMC is developed to achieve the yaw stabilization and enhance the transient tracking performance considering the input saturation of the front steering angle. The overall stability is proved with Lyapunov function. Finally, the superiority of the developed control strategy is verified by comparing with the traditional CNF with high-fidelity CarSim-Matlab simulations.

Advanced algorithms can promote the development of energy management strategies (EMSs) as a key technology in hybrid electric vehicles (HEVs). Reinforcement learning (RL) with distributed structure can significantly improve training efficiency in complex environments, and multi-threaded parallel computing provides a reliable algorithm basis for promoting adaptability. Dedicated to trying more efficient deep reinforcement learning (DRL) algorithms, this paper proposed a deep q-network (DQN)-based energy and emission management strategy (E&EMS) at first. Then, two distributed DRL algorithms, namely asynchronous advantage actor-critic (A3C) and distributed proximal policy optimization (DPPO), were adopted to propose EMSs, respectively. Finally, emission optimization was taken into account and then distributed DRL-based E&EMSs were proposed. Regarding dynamic programming (DP) as the optimal benchmark, simulation results show that three DRL-based control strategies can achieve near-optimal fuel economy and outstanding computational efficiency, and compared with DQN, two distributed DRL algorithms have improved the learning efficiency by four times.

This paper investigates the lane keeping control of autonomous ground vehicles (AGVs) considering the rollover prevention and input saturation. An enhanced state observer-based sliding mode control (SMC) strategy is proposed to achieve the control purpose and maintain the lane keeping errors as well as the roll angle within the prescribed performance boundaries. Three contributions are made in this paper. First, a prescribed performance function (PPF) is proposed in the controller design, aiming to implement the error transformation so as to constrain the controlled variables within the prescribed performance boundaries. Second, a modified sliding surface is developed incorporating two nonlinear functions, whose specialities and benefits are taken advantage of: one is a barrier function to restrict the load transfer ratio (LTR) in a safe boundary to guarantee the roll stability; another is a monotonely decreasing function to adaptively change the damping ratio of the closed-loop system to improve the transient performance, including reducing the transient overshoots and steady-state errors. Third, a modified multivariable adaptive SMC controller is proposed to achieve the integrated lane-keeping and roll control in the presence of the input saturation and bound-unknown disturbances. The stability of the closed-loop system is rigorously proved via the Lyapunov function. Finally, the effectiveness of the proposed control strategy is verified with a high-fidelity and full-car model via the CarSim platform.

This study investigates adaptive neural network (NN) state feedback control and robust observation for an active suspension system that considers parametric uncertainties, road disturbances and actuator saturation. An adaptive radial basis function neural network is adopted to approximate uncertain non‐linear functions in the dynamic system. An auxiliary system is designed and presented to deal with the effects of actuator saturation. In addition, since it is difficult to obtain accurate states in practice, an NN observer is developed to provide state estimation using the measured input and output data of the system. The state observer‐based feedback control parameters with saturated inputs are optimised by the particle swarm optimisation scheme. Furthermore, the uniformly ultimately boundedness of all the closed‐loop signals is guaranteed through rigorous Lyapunov analysis. The simulation results further demonstrate that the proposed controller can effectively suppress car body vibrations and offers superior control performance despite the existence of non‐linear dynamics and control input constraints.