This paper presents a shared control driver assistance system based on the driving intention identification and situation assessment to avoid obstacles. A constrained linear-time-varying model predictive controller (LTV-MPC) is designed to follow the obstacle-avoidance path which is obtained by artificial potential method in real time. A human driver's driving intention and the desired maneuver are recognized by the inductive multi-label classification with unlabeled data (iMLCU) approach that is trained based on the lateral offset and lateral velocity to the road center line. In addition, the situation assessment of collision risk is represented by the time to collision (TTC) and the performance evaluation is designed according to lateral deviation. All of them are employed for the design of the shared control fuzzy controller. The cooperative coefficient, denoting the control authority between the controller and a human driver, is determined by three fuzzy controllers in different conditions, which are the consistent, the advanced inconsistent, and the lagged inconsistent fuzzy controller, respectively. More importantly, there are two scenarios studies are provided to verify the proposed system. The results prove that the shared control driver assistance system can successfully help drivers to avoid obstacles and obtains great vehicle stability performance in different scenarios.

This paper presents a hierarchical trajectory following framework for SAE-level 2/3 automatic driving by convex optimisation, which aims for daily common driving manoeuvres with low traffics on the highway, such as free driving, adaptively following and overtaking. More specifically, it includes several combined functionalities of lane keeping, adaptive following, active obstacle avoidance and speed adaptation. The trajectory-planning module would generate the optimal path and speed profiles for the structure road (e.g. highway) with different geometric shapes, by using the natural cubic spline and convex optimisation approach. While modules of trajectory following or adaptive following are realised by a linearised time-varying model predictive control method. It is expected that the proposed framework could improve the driving safety, as well as the driving efficiency and driving comforts simultaneously. Thus, typical scenarios are designed to verify the effectiveness of the proposed trajectory following framework. Simulation results demonstrate that it could successfully deal with daily manoeuvres on a straight or curved highway without human driver's interventions.

As driver-automation cooperative driving systems become increasingly integrated into modern vehicles as consumer technologies and electronics, how to ensure consumer acceptance of these systems is a noteworthy consideration. This paper proposes a human-centered shared steering control method for cooperative driving systems, aimed at reducing driver-automation steering conflicts and enhancing driver acceptance by integrating human factors into each module of a hierarchical shared steering control framework. Specifically, the target path of the automated system is generated by a novel cooperative path planning algorithm based on driver intention recognition, artificial potential fields, and polynomial curve. Then, the path-following controller is developed based on model predictive control and an integrated driver-vehicle dynamic model. Next, a numerical function model is established to determine the driver’s control authority in real time with consideration of driving risk and intervention degree. Finally, several driver-in-the-loop experiments are conducted to verify the effectiveness and superiority of proposed shared steering control approach. The subjective and objective evaluation results demonstrate that the proposed approach can minimize the degree of intervention in driver behavior while ensuring driving safety, thereby enhancing driver acceptance.

Due to the large variations of environment with ever-changing background and vehicles with different shapes, colors and appearances, to implement a real-time on-board vehicle recognition system with high adaptability, efficiency and robustness in complicated environments, remains challenging. This paper introduces a simultaneous detection and tracking framework for robust on-board vehicle recognition based on monocular vision technology. The framework utilizes a novel layered machine learning and particle filter to build a multi-vehicle detection and tracking system. In the vehicle detection stage, a layered machine learning method is presented, which combines coarse-search and fine-search to obtain the target using the AdaBoost-based training algorithm. The pavement segmentation method based on characteristic similarity is proposed to estimate the most likely pavement area. Efficiency and accuracy are enhanced by restricting vehicle detection within the downsized area of pavement. In vehicle tracking stage, a multi-objective tracking algorithm based on target state management and particle filter is proposed. The proposed system is evaluated by roadway video captured in a variety of traffics, illumination, and weather conditions. The evaluating results show that, under conditions of proper illumination and clear vehicle appearance, the proposed system achieves 91.2% detection rate and 2.6% false detection rate. Experiments compared to typical algorithms show that, the presented algorithm reduces the false detection rate nearly by half at the cost of decreasing 2.7%–8.6% detection rate. This paper proposes a multi-vehicle detection and tracking system, which is promising for implementation in an on-board vehicle recognition system with high precision, strong robustness and low computational cost.

A predicted trajectory guidance control (PTGC) framework is proposed to deal with the degradation of maneuverability and drivability of a teleoperated ground vehicle caused by large communication delays. Humans dominate the control of the teleoperated ground vehicle, and human sensitivity to delays is the main reason for control performance degradation. To address this problem, the proposed framework predicts the teleoperator's intended trajectory using the control commands and the 3D point cloud of the environment at the vehicle side, which is then used to guide the vehicle directly. The novelty of the approach is to attenuate the sensitivity of the human-in-loop system to delays by removing the teleoperator from the direct control loop. Delays can be compensated as long as the predicted horizon exceeds the delays. Human-in-loop simulation experiments are designed to evaluate the teleoperation performance of the proposed method at various delay levels. By means of repeated measurement analysis of variance, it is concluded that the proposed method can significantly improve maneuverability and drivability metrics at large delays (>200ms), such as the task completion time, deviation to centerline and steering efforts. In addition, the results also show that since teleoperators can adapt well to small delays (≤ 200 ms), the presented method is ineffective in this case.

Objectives: The uncertainties of pedestrian mobility are important factors affecting the accuracy and robustness of an active pedestrian protection system. This study is to provide the means for probabilistic risk evaluation of pedestrian–vehicle collision by counting the uncertainties in pedestrian motion. Method: The pedestrian is modeled by a first-order Markov model to characterize the stochastic properties in mobility according to field experiments of pedestrians crossing an uncontrolled road. Based on the assumption of Gaussian distribution, unscented transformation (UT) is employed to predict the collision risk probability with the symmetric σ-set constructed on the basis of discrete trajectory simulation. Simulation experiments were carried out with 10,000 Monte Carlo (MC) simulations as the reference. Results: The probability density distributions of time-to-collision, minimal distance, and collision probability estimated by UT coincide with the reference ones under various vehicle–pedestrian conflict scenarios, and the maximal deviation of collision probability from the reference is 5.33%. The UT method is about 600 times faster than the MC method (10,000 runs), which means that the proposed method has the potential for online application. Conclusions: This article presents an effective and efficient algorithm to estimate the collision probability by using a UT method to solve the nonlinear transformation of uncertainties in pedestrian motion. Simulation results show that the UT-based method achieves accurate collision probability estimation and higher computation efficiency than MC and provides more valuable information concerning collision avoidance than the deterministic methods in the design of a pedestrian collision avoidance system.