An autonomous vehicle sideslip angle estimation algorithm is proposed based on consensus and vehicle kinematics/ dynamics synthesis. Based on the velocity error measurements between the reduced Inertial Navigation System (R-INS) and the global navigation satellite system (GNSS), a velocity-based Kalman filter is formalized to estimate the velocity errors, attitude errors, and gyro bias errors of the R-INS. The observability issue of the heading error, which affects sideslip estimation, is analyzed. Then, to enhance the observability and improve the estimation accuracy of the heading error under normal driving conditions, a consensus Kalman information filter is developed to synthesize the vehicle kinematics and dynamics and estimate the heading error. Within the developed consensus framework, one node augments a novel heading error measurement from a linear vehicle-dynamic-based sideslip estimator and another node adopts the heading error from the GNSS course. Next, based on the vehicle lateral excitation level, a weighting scheme is proposed to fuse the error state estimates from the velocity-based and consensus Kalman state observers. The stability of the proposed state observers is also investigated. Comprehensive experimental studies, including critical slalom, slight/normal double lane change, and normal driving maneuvers, were conducted to verify the proposed estimation framework; they confirm the reliability and accuracy of the estimator in various automated driving conditions even in comparison with state-of-the-art methods that utilize more measurements (dual-antenna GNSS). Also, this novel multisensor framework is extendable to leverage speed information from other sensors such as cameras and light detection and ranging (LiDAR) to increase reliability and accuracy.

Accurate trajectory prediction of surrounding vehicles enables lower risk path planning in advance for autonomous vehicles, thus promising the safety of automated driving. A low-risk and high-efficiency path planning approach is proposed for autonomous driving based on the high-performance and practical trajectory prediction method. A long short-term memory (LSTM) network is trained and tested using the highD dataset, and the validated LSTM is used to predict the trajectories of surrounding vehicles combining the information extracted from vehicle-to-vehicle (V2V) technology. A risk assessment and mitigation-based local path planning algorithm is proposed according to the information of predicted trajectories of surrounding vehicles. Two driving scenarios are extracted and reconstructed from the highD dataset for validation and evaluation, i.e., an active lane-change scenario and a longitudinal collision-avoidance scenario. The results illustrate that the risk is mitigated and the driving efficiency is improved with the proposed path planning algorithm comparing to the constant-velocity prediction and the prediction method of the nonlinear input–output (NIO) network, especially when the velocity and trajectory with sudden changes. Note to Practitioners—This article was motivated by the problem of promising the safety decision-making and path planning through accurate environment prediction. There are two main parts included in this article. First, this article proposed one pragmatic approach to predict the environment movement correctly based on the long short-term memory (LSTM) approach. The prediction performance of LSTM was compared with nonlinear input–output (NIO). The results showed that the LSTM approach has a significant advantage in motivation prediction of the surrounded vehicles during path planning. The second part of this article is to make the decision and realize local path planning based on the risk assessment. The potential field-based approach is implemented on the risk assessment based on these accurate predictions. Some primary results demonstrate that the decision-making algorithm performs better under the accurate prediction model. The results also show that the safety and driving efficiency of the ego vehicle were improved by tracking the trajectory, which was planned based on the risk assessment. The only concern for the real-time application is the computation time; in future, we will figure it out how to further reduce the computation time.

The increasing requirements for vehicle driving safety improvement have led to numerous and in-depth studies on vehicle stability, especially for autonomous vehicles. The main concerns of vehicle stability research in autonomous vehicles include the vehicle stability analyzing, criterion constructing and controller designing. Therefore, this paper provides a comprehensive review of state-of-the-art vehicle stability criterion and control application for autonomous vehicles. First, the lateral vehicle linear stability criterion and widely-used active stability control applications are introduced. Next, the nonlinear vehicle stability analysis algorithm and criterion, based on the well-known phase plane method, are discussed in detail. The stability controller design, including the activation strategy and tracking objectives, is reviewed. In addition, emerging research challenges and trends for future improvement in lateral stabilization of autonomous vehicles are finally summarized.

Localization is critical for automated vehicles as it provides essential position, velocity, and heading angle information to perform object tracking, trajectory prediction, motion planning, and control. However, model/environmental uncertainties (including road friction) and noises in sensor measurements have a significant effect on the accuracy of the localization and vehicle state estimation, specially for perceptually degraded conditions. In this paper, an integrated localization method based on the fusion of an inertial dead reckoning model and 3D LiDAR-based map matching is proposed and experimentally verified in an urban environment with varying environmental conditions. Leveraging a global navigation satellite system (GNSS), inertial navigation system (INS), and 3D LiDAR point clouds, a novel light point cloud map generation method, which only keeps the necessary point clouds (i.e., buildings and roads regardless of vegetation varying with seasonal change), is proposed. Subsequently, based on the onboard sensors and the pre-built light point cloud map, a dead reckoning model is derived and integrated with the normal distribution transformation (NDT) based map matching algorithm by an error-state-constrained Kalman filter to limit the localization error. On top of the Kalman filter, the stability analysis of the estimator is presented. Finally, the performance of the algorithm is validated in real road experiments under various environmental conditions. Thorough experiments in winter and summer and associated results confirm the advantages of integrating the proposed light point cloud map generation with the dead reckoning model in terms of accuracy and reduced computational complexity.

This paper presents a model predictive vehicle stability controller that considers tire force nonlinearities and the combined-slip effect. Loss of cornering forces caused by increased longitudinal slip and changes in the slip angle due to the vehicle lateral response are considered in the prediction model of the controller. The developed controller adjusts tire slip ratios based on forces of the front and rear axles, monitors tire capacities and normal forces, and exhibits excellent performance in maintaining lateral responses within a stable region. The performance of the proposed predictive controller is assessed in software simulations as well as road experiments in various pure-slip and combined-slip driving scenarios and under different road friction conditions.