Search Results

The fusion of multi-modal perception in autonomous driving plays a pivotal role in vehicle behavior decision-making. However, much of the previous research has predominantly focused on the fusion of Lidar and cameras. Although Lidar offers an ample supply of point cloud data, its high cost and the substantial volume of point cloud data can lead to computational delays. Consequently, investigating perception fusion under the context of 4D millimeter-wave radar is of paramount importance for cost reduction and enhanced safety. Nevertheless, 4D millimeter-wave radar faces challenges including sparse point clouds, limited information content, and a lack of fusion strategies. In this paper, we introduce, for the first time, an approach that leverages Graph Neural Networks to assist in expressing features from 4D millimeter-wave radar point clouds. This approach effectively extracts unstructured point cloud features, addressing the loss of object detection due to sparsity.

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

This paper presents an optimal cooperative path planning method considering driver’s driving intention for shared control to address target path conflicts during the driver-automation interaction by using the convex optimization technique based on the natural cubic spline. The optimal path criteria (e.g. the optimal curvature, the optimal heading angle) are formulated as quadratic forms using the natural cubic spline, and the initial cooperative path profiles of the cooperative path in the Frenet-based coordinate system are induced by considering the driver’s lane-changing intention recognized by the Support Vector Machine (SVM) method. Then, the optimal cooperative path could be obtained by the convex optimization techniques. The noncooperative game theory is adopted to model the driver-automation interaction in this shared control framework, where the Nash equilibrium solution is derived by the model predictive control (MPC) approach.

In this paper, gear ratios of a two-speed transmission system are optimized for an electric passenger car. Quasi static system models, including the vehicle model, the motor, the battery, the transmission system, and drive cycles are established in MATLAB/Simulink at first. Specifically, since the regenerative braking capability of the motor is affected by the SoC of battery and motors torque limitation in real time, the dynamical variation of the regenerative brake efficiency is considered in this study. To obtain the optimal gear ratios, iterations are carried out through Nelder-Mead algorithm under constraints in MATLAB/Simulink. During the optimization process, the motor efficiency is observed along with the drive cycle, and the gear shift strategy is determined based on the vehicle velocity and acceleration demand. Simulation results show that the electric motor works in a relative high efficiency range during the whole drive cycle.

The interactions between automatic controls, physics, and driver is an important step towards highly automated driving. This study investigates the dynamical interactions between human-selected driving modes, vehicle controller and physical plant parameters, to determine how to optimally adapt powertrain control to different human-like driving requirements. A cyber-physical system (CPS) based framework is proposed for co-design optimization of the physical plant parameters and controller variables for an electric powertrain, in view of vehicle’s dynamic performance, ride comfort, and energy efficiency under different driving modes. System structure, performance requirements and constraints, optimization goals and methodology are investigated. Intelligent powertrain control algorithms are synthesized for three driving modes, namely sport, eco, and normal modes, with appropriate protocol selections. The performance exploration methodology is presented.

This paper outlines the procedure used to assess the performance of a Lane Keeping Assistance System (LKAS) in a virtual test environment using the newly developed Euro NCAP Lane Support Systems (LSS) Test Protocol, version 1.0, November 2015 [1]. A tool has also been developed to automate the testing and analysis of this test. The Euro NCAP LSS Test defines ten test paths for left lane departures and ten for right lane departures that must be followed by the vehicle before the LKAS activates. Each path must be followed to within a specific tolerance. The vehicle control inputs required to follow the test path are calculated. These tests are then run concurrently in the virtual environment by combining two different software packages. Important vehicle variables are recorded and processed, and a pass/fail status is assigned to each test based on these values automatically.

Recently, the development of braking assistance system has largely benefit the safety of both driver and pedestrians. A robust prediction and detection of driver braking intention will enable driving assistance system response to traffic situation correctly and improve the driving experience of intelligent vehicles. In this paper, two types unsupervised clustering methods are used to build a driver braking intention predictor. Unsupervised machine learning algorithms has been widely used in clustering and pattern mining in previous researches. The proposed unsupervised learning algorithms can accurately recognize the braking maneuver based on vehicle data captured with CAN bus. The braking maneuver along with other driving maneuvers such as normal driving will be clustered and the results from different algorithms which are K-means and Gaussian mixture model (GMM) will be compared.

One main objective is to find out how these parameters interact and optimal driver control gain and driver preview time are obtained. Some steps further, neuromuscular dynamics is considered and the system becomes different from the simplified driver-vehicle system studied before. New optimal driver control gain and driver preview time could be obtained for both tensed and relaxed muscle state. Final step aims at analysing the full system considering driver, neuromuscular, steer-by-wire and vehicle models. The steer-by-wire system could potentially have a significant influence on the vehicle when the driver is at impaired state, which could be represented by setting higher response delay time or smaller preview time. Vehicle's stability and active safety could also be improved by introducing the steer-by-wire system.

Compared to the vehicles with conventional steering, the articulated frame steer vehicles (ASV) are known to exhibit lower directional and roll stability limits. Furthermore, the tire interactions with relatively rough terrains could adversely affect the directional and roll stability limits of an ASV due to terrain-induced variations in the vertical and lateral tire forces. It may thus be desirable to assess the dynamic safety of ASVs in terms of their directional control and stability limits while operating on different terrains. The effects of terrain roughness on the directional stability limits of an ASV are investigated through simulations of a comprehensive three-dimensional model of the vehicle with and without a rear axle suspension. The model incorporates a torsio-elastic rear axle suspension, a kineto-dynamic model of the frame steering struts and equivalent random profiles of different undeformable terrains together with coherence between the two tracks profiles.

This study analyzes the effect of soil deformation on ride dynamics of off-road vehicles using a quarter-vehicle model integrating different equivalent soil stiffness models. Soil deformation has an effect on the tire sinkage, wheels contact area and the wheels dynamic interaction with the terrain, which affects the overall ride dynamics of the vehicle. Apart from the very simplified equivalent soil stiffness model documented in the literature, a new equivalent soil stiffness model is developed in this study, which encompasses the effect of soil deformability on tire-soil contact area. Two measured ground roughness profiles are then used for vehicle ride dynamics simulation.

This study analyzes the power consumption of a specific Planetary Exploration Vehicle (PEV) subsystem known as Flexible-Wheel (FW) suspension, more specifically the interaction between a FW and the deformable terrain upon which it traverses. To achieve this a systematic and analytical calculation procedure has been developed, which culminates in the definition of three dimensionless properties to capture the FW-soil interaction. Aimed towards the design engineer participating in concept evaluation, and the control engineer conducting initial analyses, this study has found that the resistance coefficient for the interaction between a FW and the deformable terrain can, in general, be several orders of magnitude higher than the rolling resistance of a pneumatic tire operating upon rigid terrain.

This study proposes a novel semi-active hydro-pneumatic suspension design and investigates its performance potentials. The proposed new semi-active suspension design involves pneumatic interconnection between the front and rear suspension struts of the vehicle. The analytical formulations of suspension forces due to two suspension configurations, a passive unconnected and the proposed semi-active interconnected, are derived to analyze suspension properties. Based on a validated pitch-plane vehicle braking model, vehicle dynamic responses are conducted under a range of measured road roughness excitations and driving speeds, as well as braking inputs.

This study investigates influence of compressible hydraulic fluid and suspension floating piston dynamics of fluidic suspensions on heavy vehicle roll stability and ride dynamics. Two fluidic suspension designs, including a single-gas-chamber strut and a novel twin-gas-chamber strut, are analyzed to develop the mathematical formulations of dynamic forces, upon considerations of hydraulic fluid compressibility and floating piston dynamics. Dynamic responses of the heavy vehicle with the different suspension configurations are then performed using a nonlinear roll plane vehicle model. The excitations arise from vehicle-road interactions as well as a steady steering maneuver. The results demonstrate that the compressibility characteristic of hydraulic fluid within a hydro-pneumatic suspension could affect the vehicle roll stability and ride dynamics, while the influence of suspension floating piston dynamics on vehicle dynamic responses is negligible.

This study investigates the fundamental stiffness and damping properties of a self-damped pneumatic suspension system, based on both the experimental and analytical analyses. The pneumatic suspension system consists of a pneumatic cylinder and an accumulator that are connected by an orifice, where damping is realized by the gas flow resistance through the orifice. The nonlinear suspension system model is derived and also linearized for facilitating the properties characterization. An experimental setup is also developed for validating both the formulated nonlinear and linearized models. The comparisons between the measured data and simulation results demonstrate the validity of the models under the operating conditions considered. Two suspension property measures, namely equivalent stiffness coefficient and loss factor, are further formulated.

The ride performance potentials of a prototype torsio-elastic axle suspension for an off-road vehicle were investigated analytically and experimentally. A forestry vehicle was fitted with the prototype suspension at its rear axle to assess its ride performance benefits. Field measurements of ride vibration along the vertical, lateral, fore-aft, roll and pitch axes were performed for the suspended and an unsuspended vehicle, while traversing a forestry terrain. The measured vibration responses of both vehicles were evaluated in terms of unweighted and frequency-weighted rms accelerations and the acceleration spectra, and compared to assess the potential performance benefits of the proposed suspension. The results revealed that the proposed suspension could yield significant reductions in the vibration magnitudes transmitted to the operator's station.

Ride performance characteristics of a road vehicle involving different suspension system layouts are investigated. The suspension layouts consist of conventional rectangular 4-wheel, novel diamond-shaped 4-wheel, triangular 3-wheel and inverse-triangular 3-wheel. A generalized full-vehicle model integrating different suspension system layouts is formulated. The fundamental suspension properties are compared in terms of bounce-, roll- and pitch-mode. The ride dynamic responses and power consumption characteristics are explored under two measured road roughness excitations and a range of vehicle speeds. The results demonstrate that the novel diamond-shaped suspension system layout could yield significantly enhanced vehicle ride performance in an energy-saving manner.

The handling and braking responses of a heavy vehicle equipped with a cross-axle fluidically-coupled hydro-pneumatic suspension concept are investigated. The proposed fluidically-coupled suspension is conceived by diagonally interconnecting different hydraulic fluid chambers of the four suspension struts of the vehicle. The analytical formulations of suspension forces are derived based on fluid flows through the couplings and damping valves. A generalized full-vehicle model is developed and validated to evaluate the handling and braking responses to two critical vehicle maneuvers: (i) braking-in-a-turn; and (ii) split-μ straight-line braking. The responses of the vehicle model with the coupled suspension are compared with those of the uncoupled suspension under various inputs to demonstrate the potential benefits of the proposed cross-axle fluidic coupling of the suspension struts.

The influences of fluidic X-coupling of hydro-pneumatic suspension struts on the various suspension properties are investigated for a sport utility vehicle (SUV). The stiffness and damping properties in the bounce, pitch, roll and warp modes are particularly addressed together with the couplings between the roll, pitch, bounce and warp modes of the vehicle. The proposed X-coupled suspension configuration involves diagonal hydraulic couplings among the different chambers of the four hydro-pneumatic struts. The static and dynamic forces developed by the struts of the unconnected and X-coupled suspensions are formulated using a simple generalized model, which are subsequently used to derive the stiffness and damping properties. The properties of the X-coupled suspension are compared with those of the unconnected suspension configuration, in terms of four fundamental vibration modes, namely bounce, roll, pitch and warp, to illustrate the significant effects of fluidic couplings.

The optimal damping design of roll plane interconnected hydro-pneumatic suspension is investigated, in order to improve vertical ride and road-friendliness of heavy vehicles, while maintaining enhanced roll stability. A nonlinear roll plane vehicle model is developed to study vertical as well as roll dynamics of heavy vehicles. The damping valves and gas chamber are integrated within the same suspension strut unit to realize compact design. The influence of variations in damping valve threshold velocity on relative roll stability is explored, under centrifugal acceleration excitations arising from steady turning and lane change maneuvers, as well as crosswind. The effects of damping valve design parameters on the vertical ride vibration and vehicle-road interaction characteristics are also investigated under a medium rough road input and two different vehicle speeds.

This study investigates the performance potentials of hydro-pneumatic suspensions interconnected in the pitch plane of a heavy vehicle. Different configurations of interconnected suspensions comprising pneumatic, hydraulic or hybrid fluidic couplings between the front-and rear-suspension struts are proposed and analyzed. A 7-DOF pitch plane vehicle model is formulated to explore the relative vertical and pitch properties of different suspension configurations, as well as the dynamic responses of the vehicle under braking and road inputs. The mathematical formulations of strut forces due to both the unconnected and pitch-connected suspensions are derived. Relative performance potentials of different configurations are evaluated in terms of sprung mass pitch angle, suspension travel and stopping distance characteristics under different braking inputs and road conditions. The vertical ride quality is further assessed under a range of road roughness excitations and vehicle speeds.