Adaptive cruise control and autonomous lane-change systems represent pivotal advancements in intelligent vehicle technology. To enhance the operational efficiency of vehicles combined car-following scenarios, we propose a coordinated decision model based on hierarchical time series prediction deep reinforcement learning under influence multiple surrounding vehicles. Firstly, analyze behavior establish boundary conditions for safe lane-change, divide trajectory planning problem into...

Path planning for intelligent semi-trailers encounters numerous challenges in complex traffic conditions. Serious consequences, such as vehicle rollover, may occur when the conditions change. Therefore, it is vital to consider both surrounding dynamic and vehicle’s roll stability during lane-changing process of semi-trailers. We propose an innovative path-planning method tailored This designed on straight-road alignments. Firstly, we employ a fuzzy inference system information about traffic,...

Articulated heavy vehicles is the mainstay of inter-city freight transportation, and one most likely fields for earliest practical applications intelligent driving. Trajectory planning tracking lane change are critical technologies Autonomous Heavy Vehicles (AAHVs). Characteristics AAHVs susceptible to stability problems resulting from high height, long lengths, load, mutual coupling tractor trailer, combined complex environments with dynamic changes in states adjacent road adhesion...

The decision-making system of intelligent vehicles is the core component an advanced driving for both passenger and commercial vehicles. Finding ways to improve strategies suit complex unfamiliar environments a standing problem traditional rule-based methods. This paper proposes semi-rule-based strategy heavy based on Deep Deterministic Policy Gradient algorithm. Firstly, according car-following characteristics, problems high dimensions large amount data in vehicle action space state are...

This paper proposes a fractional order optimization method of multi-variable Grey model (GM( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$r$</tex-math> </inline-formula> ,2)) based on full transfer learning LSTM network. Firstly, GM( ,2) was built with adhesion coefficient as input variable, namely, correlation factor sequence, and driving intention output system behaviour characteristic sequence....

Trajectory planning and tracking of lane change are critical technologies for autonomous buses. Characteristics the buses susceptible to stability problems resulting from high height, large passenger capacity long lengths, coupling dynamic traffic with changes in states adjacent vehicles road adhesion coefficient, put forward great challenges (ABs). To cope foregoing challenges, a framework is proposed achieve trajectory ABs. For approach, replanning optimized safe range longitudinal length...

A normalization method of road adhesion coefficient and tire cornering stiffness is proposed to provide the significant information for vehicle direct yaw-moment control (DYC) system design. This carried out based on a fractional-order multi-variable gray model (FOMVGM) long short-term memory (LSTM) network. FOMVGM used generate training data testing LSTM network, network employed predict with coefficient. In addition that, represented by can be built lateral dynamic participate in DYC...

Traditional adaptive cruise control (ACC) would choose to follow when encountering low-speed cars in front, but this may lead low driving efficiency. This paper proposes a controller of enhanced with lane-change assistance (LCACC) for an articulated vehicle. A two-layer hierarchical structure is adopted study. The upper determines high-level commands, while the bottom consisting two modified deep deterministic policy gradient (DDPG) networks, controls steering wheel and throttle/brake,...

Dynamic lateral lane change (DLLC) control of automated and connected vehicles (ACVs) is challenging because the time‐varying complex properties traffic environment. This study proposes a DLLC strategy combining dynamic trajectory planning tracking. According to real‐time longitudinal accelerations velocities multiple surrounding vehicles, as well states ACVs, safe reference obtained by solving case‐dependent constrained optimisation problem. The changing efficiency, vehicle stability...

In the paper, a novel framework for control system of lateral obstacle avoidance (LOA), which is based on dynamic early warning intelligent vehicles shared-driven by people and (IVSDPVs), presented to perform LOA in conditions (e.g. speed changes). Firstly, achieve accurate IVSDPVs adjust that with intervention driver conditions, multi-level algorithm fusion complementarity critical safe distance reciprocal collision time proposed. Moreover, obtained using combination longitudinal...

Driving intention, which can assist drivers to avoid dangerous emergence for the advanced driver assistant systems (ADAS), be hardly described accurately complex traffic environments. At present, driving intention mainly obtained by deep neural networks with neuromuscular dynamics and electromyography (EMG) signals of drivers. This method needs numerous drivers’ a structure. paper proposes direct inference method, namely from road surface condition. A safety distance model based on network...

A control strategy for lateral performance improvement of articulated heavy vehicles (AHVs) by integrating active trailer steering and differential braking is presented. linear model with real-time parameters adopted in the to achieve precise AHVs under vehicle states conditions. The divided into a path following mode rollover mode. switching method employed good yaw stability normal working conditions avoid limit Moreover, order obtain optimal effects different objectives fusion...