Search Results

To address the current situation of the limited driver-vehicle cooperative steering actuation structure, this paper proposes a feasible driver-vehicle shared steering control actuation architecture based on the differential steering. Firstly, a shared steering execution architecture is established, which contains traditional steering system controlled by human driver and differential steering system acting as the automatic execution system. In this paper, a specific driver-vehicle shared control architecture is established with the front-wheel hub motor-based differential steering system and a single-view angle based human driver model. Then, an upper-level sliding mode controller for path tracking is developed and implemented as the automatic steering system, and the driver-vehicle shared control is achieved by the proposed non-cooperative game model.

It’s hard to achieve complete self-driving using hand-crafting generalized decision-making rules, while the end-to-end self-driving system is low in complexity, does not require hand-crafting rules, and can deal with complex situations. Modular-based self-driving systems require multi-task fusion and high-precision maps, resulting in high system complexity and increased costs. In end-to-end self-driving, we usually only use camera to obtain scene status information, so image processing is very important. Numerous deep learning applications benefit from multi-task learning, as the multi-task learning can accelerate model training and improve accuracy with combine all tasks into one model, which reduces the amount of calculation and allows these systems to run in real-time. Therefore, the approach of obtaining rich scene state information based on multi-task learning is very attractive. In this paper, we propose an approach to multi-task learning for semantics, geometry and motion.

With the rise of intelligent transportation systems around the world, research on automobile active safety technology has gained widespread attention. Autonomous Emergency Braking (AEB) which can avoid or mitigate collision by active braking has become a hot research topic in the field of automobile. However, there are some limitations in the present AEB collision avoidance strategy, including lack of effective identification of road adhesion conditions, mismatch of active braking system parameters and imperfection of target vehicle motion information, which leads to poor collision avoidance performance on low adhesion coefficient road surface and intervention with the normal driving operation of the driver. A new collision avoidance strategy for AEB is proposed in this paper.

This paper presents a HiL test bench specifically designed for closed-loop testing of the monocular-vision based ADAS sensors, whereby the animated pictures of the virtual scene is calibrated and projected onto a 120-degree circular screen, such that the camera sensor installed has the same vision as the observation of the real-world scene. A high-fidelity AEBs model is established and deployed in the real-time target of the HiL system, making intervention decisions based on the instance-level detection information transmitted from the physical sensor. By referring to the 2018 edition of the C-NCAP testing protocol, the HiL tests of the rear-end collision scenarios is performed to investigate the performance and characteristics of the longitudinal-motion sensing of the sensor sample under test.

This paper presents an integrated chassis controller with multiple hierarchical layers for 4WID/4WIS electric vehicle. The proposed systematic design consists of the following four parts: 1) a reference model is in the driver control layer, which maps the relationship between the driver's inputs and the desired vehicle motion. 2) a sliding mode controller is in the vehicle motion control layer, whose objective is to keep the vehicle following the desired motion commands generated in the driver control layer. 3) By considering the tire adhesive limits, a tire force allocator is in the control allocation layer, which optimally distributes the generalized forces/moments to the four wheels so as to minimize the tire workloads during normal driving. 4) an actuator controller is in the executive layer, which calculates the driving torques of the in-wheel motors and steering angles of the four wheels in order to finally achieve the distributed tire forces.

This paper presents a simultaneous longitudinal and lateral motion control strategy for a full drive-by-wire autonomous vehicle. A nonlinear model predictive control (NMPC) problem is formulated in which the nonlinear prediction model utilizes a spatial transformation to derive the dynamics of the vehicle about the reference trajectory, which facilitates the acquisition of the tracking errors at varying speeds. A reference speed profile generator is adopted by taking account of the road geometry information, such that the lateral stability is guaranteed and the lane guidance performance is improved. Finally, the nonlinear multi-variable optimization problem is simplified by considering only three motion control efforts, which are strictly confined within a convex set and are readily distributed to the four tires of a full drive-by-wire vehicle.

A full drive-by-wire electric vehicle, named Urban Future Electric Vehicle (UFEV) is developed, where the four wheels' traction and braking torques, four wheels' steering angles, and four active suspensions (in the future) are controlled independently. It is an ideal platform to realize the optimal vehicle dynamics, the marginal-stability and the energy-efficient control, it is also a platform for studying the advanced chassis control methods and their applications. A centralized control system of hierarchical structure for UFEV is proposed, which consist of Sensor Layer, Identification and Estimation Layer, Objective Control Layer, Forces and Motion Distribution Layer, Executive Layer. In the Identification and Estimation Layer, identification model is established by utilizing neural network algorithms to identify the driver characteristics. Vehicle state estimation and road identification of UFEV based on EKF and Fuzzy Logic Control methods is also conducted in this layer.

Electronic braking system (EBS) of commercial vehicle is developed based on Anti-lock Braking System (ABS), for the purpose of enhancing the braking performance. Based on the previous study, this paper aims at the development and research on the control strategy of advanced electronic braking system for commercial vehicle, which mainly includes braking force distribution and multiple targets control strategy. In the study of braking force distribution control strategy, the mass of vehicle and the axle loads will be calculated dynamically and the braking force of each wheel will be distributed regarding to the axle loads. The braking intention recognition takes the brake pad wear into account when braking uncritically, so it can detect a difference in the pads between the front and the rear axles. The brake assist strategy supports the driver during emergency braking and the braking distance is shortened by the reduction of the braking system response time.

Pneumatic Electric Braking System (EBS) is getting widely spread for commercial vehicles. Pneumatic EBS improves the problem of slow response of traditional pneumatic braking system by implementing brake-by-wire. However, the time-delay response and hysteresis of some electro-pneumatic components and some other issues decrease the response and control accuracy of the pneumatic EBS.

Four-wheel independent control electric vehicle is a new type of x-by-wire EV with four wheels independent steering and four wheels independent drive/brake systems. In order to take full advantage of the vehicle's performance potential, this paper presents a novel integrated chassis control strategy. In the paper, the strategy is designed by the hierarchical control structure and divided into integrated control layer and allocation layer. By this method, the control logical can be modularized and simplified. In the integrated control layer, Model Prediction Control (MPC) is adopted to design the integrated control unit, which belongs to be a kind of local optimization algorithm with feedback correction features. Using this method could avoid the system performance degradation caused by the control model mismatch. The control allocation layer is to optimally distribute the vehicle control forces to the steering/driving/brake actuators on each wheel.

Electronic braking system (EBS) of commercial vehicle is developed from ABS to enhance the brake performance. Based on the early development of controller hardware, this paper starts with an analysis of the definition of EBS. It aims at the software design of electronic control unit, and makes it compiled into the controller in the form of C language by the in-depth study about control strategy of EBS in different braking conditions. Designed controller software is divided into two layers. The upper control strategy includes the recognition algorithm of driver's braking intention, estimation algorithm of the vehicle state, conventional braking strategy which consists of the algorithm of deceleration control and braking force distribution, and emergency braking strategy which consists of the algorithm of brake assist control and ABS control.