This paper presents an object classification method for vision and light detection ranging (LIDAR) fusion of autonomous vehicles in the environment. is based on convolutional neural network (CNN) image upsampling theory. By creating a point cloud LIDAR data converting into pixel-level depth information, information connected with Red Green Blue fed deep CNN. The proposed can obtain informative feature representation vehicle environment using integrated data. also adopted to guarantee both...

Decision making for self‐driving cars is usually tackled by manually encoding rules from drivers’ behaviours or imitating manipulation using supervised learning techniques. Both of them rely on mass driving data to cover all possible scenarios. This study presents a hierarchical reinforcement method decision cars, which does not depend large amount labelled data. comprehensively considers both high‐level manoeuvre selection and low‐level motion control in lateral longitudinal directions. The...

In reinforcement learning (RL), function approximation errors are known to easily lead the Q -value overestimations, thus greatly reducing policy performance. This article presents a distributional soft actor-critic (DSAC) algorithm, which is an off-policy RL method for continuous control setting, improve performance by mitigating overestimations. We first discover in theory that distribution of state-action returns can effectively mitigate overestimations because it capable adaptively...

This paper presents a drowsiness on-line detection system for monitoring driver fatigue level under real driving conditions, based on the data of steering wheel angles (SWA) collected from sensors mounted lever. The proposed firstly extracts approximate entropy (ApEn)featuresfromfixedslidingwindowsonreal-timesteeringwheelanglestimeseries. Afterthat, this linearizes ApEn features series through an adaptive piecewise linear fitting using given deviation. Then, calculates warping distance between...

Eco-driving at signalized intersections has significant potential for energy saving. In this paper, we focus on eco-departure operations of connected vehicles equipped with an internal combustion engine and a step-gear automatic transmission. A Bolza-type optimal control problem (OCP) is formulated to minimize fuel consumption. Due the discrete gear ratio, OCP nonlinear mixed-integer problem, which challenging handle by most existing optimization methods. The Legendre pseudospectral method...

The recent progress of advanced vehicle control systems presents a great opportunity for the application model predictive (MPC) in automotive industry. However, high computational complexity inherently associated with receding horizon optimization must be addressed to achieve real-time implementation. This paper generic scale reduction framework reduce online burden MPC controllers. A lower dimensional algorithm is formulated by combining an existing "move blocking " strategy "constraint-set...

Accurate trajectory prediction of surrounding road users is critical to autonomous driving systems. In mixed traffic flows, with different kinds behaviors and styles bring complexity the environment, which requires considering interactions among when anticipating their future trajectories. This paper presents a long-term interactive method for vehicles using hierarchical multi-sequence learning network. contrast non-interactive assumes that are independent each other, this can automatically...

Driver distraction has been identified as one major cause of unsafe driving. The existing studies on cognitive detection mainly focused high-speed driving situations, but less low-speed traffic in urban This paper presents a method for the driver at stop-controlled intersections and compares its feature subsets classification accuracy with that speed-limited highway. In simulator study, 27 subjects were recruited to participate. is induced by clock task taxes visuospatial working memory....

Decision and control are core functionalities of high-level automated vehicles. Current mainstream methods, such as functional decomposition end-to-end reinforcement learning (RL), suffer high time complexity or poor interpretability adaptability on real-world autonomous driving tasks. In this article, we present an interpretable computationally efficient framework called integrated decision (IDC) for vehicles, which decomposes the task into static path planning dynamic optimal tracking that...

This paper studies the principles and mechanism of a fuel-optimal strategy in cruising scenarios, i.e., pulse glide (PnG) operation, for road vehicles equipped with step-gear transmission. In PnG strategy, control engine transmission determines fuel-saving performance, it is obtained by solving an optimal problem (OCP). Due to discrete gear ratio, strong nonlinear fuel characteristics, different dynamics pulse/glide mode, OCP switching mixed-integer problem. challenging converted knotting...

The platooning of automated vehicles has the potential significantly enhancing fuel efficiency road transportation. This paper presents a periodic switching control method for an vehicle platoon to minimize overall consumption. Considering nonlinearity operation, concept bounded stability is defined replace conventional internal and string stability. distributed servo loop controller based on dual-pulse-and-glide operation designed each vehicle, wherein sectionalized map adopted proper mode...

It is widely acknowledged that drivers should remain in the control loop before automated vehicles completely meet real-world operational conditions. This paper presents an "indirect shared control" framework for steer-by-wire vehicles, which allows authority to be continuously between driver and automation through weighted-input-summation method. A "best-response" steering model based on predictive (MPC) indirect proposed. Unlike any conventional manual driving, this assumes can learn...

Fuel consumption of fossil-based road vehicles is significantly affected by the way are driven. The same true for automated with longitudinal control. This paper presents a periodic servo-loop control algorithm an adaptive cruise (ACC) system to minimize fuel in car-following scenarios. fuel-saving mechanism pulse-and-glide (PnG) operation first discussed powertrain internal combustion engine and step-gear transmission. controller then designed based on switching map real-time implementation...

This paper studies the fuel-optimal cruising strategies of parallel hybrid electric vehicles (HEVs) and their underlying mechanisms. To achieve operations, a discontinuous nonlinear optimal control problem is formulated solved using Legendre pseudospectral method knotting technique. Three in free/fixed-speed scenarios are proposed: vehicle speed pulse-and-glide strategy, state-of-charge (SoC) (PnG) constant-speed strategy. The performance behavior engine motor presented, fuel-saving...

There are still some problems need to be solved though there a lot of achievements in the fields automatic driving. One those is difficulty designing car-following decision-making system for complex traffic conditions. In recent years, reinforcement learning shows potential solving sequential decision optimization problems. this article, we establish reward function R each driver data based on inverse algorithm, and r visualization carried out, then driving characteristics following...

This paper presents two fuel-prioritized feedback controllers, which are called the estimated minimum principle (EMP) and kinetic energy conversion (KEC), to realize eco-cruising on varying slopes for vehicles with conventional powertrains. The former is derived from an Hamiltonian, latter designed based equivalent between kinetic-energy change of vehicle body fuel consumption engine. They implemented analytical control laws rely current road slope information only without look-ahead...