Complex Road Conditions Research Articles

Fuzzy-Torque Approximation-Enhanced Sliding Mode Control for Lateral Stability of Mobile Robot

Accurate path tracking and stability are the main challenges of lateral motion control in mobile robots, especially under the situation with complex road conditions. The interaction force between robots and the external environment may cause interference, which should be considered to guarantee its path tracking performance in dynamic and uncertain environments. In this article, a flexible lateral control scheme is considered for the developed wheel-legged robot, which consists of a cubature Kalman algorithm to evaluate the centroid slip angle and the yaw rate. Furthermore, a fuzzy compensation and preview angle-enhanced sliding model controller to improve the tracking accuracy and robustness. Finally, some simulations and experimental demonstrations using the four-wheel-legged robot (BIT-NAZA) are carried out to illustrate the effectiveness and robustness, and the proposed method has achieved satisfactory results in high-precision trajectory tracking and stability control of the mobile robot.

Applicability analysis of waste heat recovery technology and strategy exploration for hybrid electric vehicles under diverse road conditions

The challenges of energy conservation and environmental protection are becoming severe. Therefore, hybrid electric vehicles (HEVs), owing to their low fuel consumption and low emissions, are being considered as the ideal transition models between conventional fuel vehicles and pure electric vehicles. The growing demand for increasing vehicle efficiency has motivated the introduction of waste heat recovery (WHR) technology in the automotive industry. The organic Rankine cycle (ORC), with its advantages of great flexibility, high safety, low cost, and low maintenance requirements, is considered to be a potential WHR method. Currently, only a few studies have been conducted on coupling the HEV with ORC-WHR systems, which focus on the exploration of hybrid powertrain strategies under a certain type of road condition, but lack the applicability analysis of WHR technology and strategy exploration for HEVs operating under diverse road conditions. To analyze whether the WHR system has considerable and valuable energy savings potential under various road conditions, an applicability analysis is conducted under nine types of standard driving cycles. Based on these, for better adaptability to the complex and changing road conditions, an optimization strategy for the HEV-WHR integrated system is proposed based on road condition recognition technology. The results reveal that the WHR system is not suitable for urban road conditions, but is well adapted to suburban and highway conditions. For example, under the NYCC (New York City Cycle) and the Artemis Urban Driving Cycle, the WHR system even increases energy consumption by 0.18% and 0.12%, respectively, while under suburban and highway road conditions, the overall impact of coupling the WHR system reduces energy consumption by 3.36%–10.60%. Meanwhile, in HEV-WHR system coupling with the above proposed optimization strategy, the state of charge (SOC) of the battery is more stable, the start and stop times of the WHR system decrease, the engine thermal efficiency and average motor efficiency are much higher than the efficiencies obtained without the optimization strategy, and the ultimate energy savings potentials are calculated as 3.19%, 3.59%, and 4.16% under the CLTC (China Light Vehicle Test Cycle), NEDC (New European Driving Cycle), and WLTC (Worldwide Light Vehicle Test Cycle) driving cycles.

Optimization of VRR for Cold Chain with Minimum Loss Based on Actual Traffic Conditions

Recently, fresh agricultural cold‐chain logistics have been greatly developed with the increasing needs of people’s life. Reducing costs of cold‐chain distribution has become the main object of loss control in logistics enterprises. The objective of this research is to find a set of optimal routes that minimize the total loss, including fuel cost, refrigeration cost, soft time window penalty cost, and cargo damage cost over transit time. In this paper, the definition and model construction of vehicle routing problem (VRP) with multiobjective minimum lost are introduced first. Then, an ant colony optimization (ACO) algorithm combined with Pareto local search (PLS) is put forward to solve the minimum loss model. In order to avoid the influence of complex road conditions during distribution, the distance matrix and the transit time matrix are both derived from the recommended navigation road based on E‐map API. At last, a compare experiment between the traditional method and our proposed method is performed. The results indicate that our method has strong applicability and potential advantages in cold‐chain logistic and has important practical significance and application value.

Four-Wheel Anti-Lock Braking System With Robust Adaptation Under Complex Road Conditions

Because of the nonlinear feature of tire force, the anti-lock braking system (ABS) research based on wheel slip control (WSC) is widely used even without the measured wheel slip and road friction. Combined with the WSC technology, the four-wheel ABS with the fuzzy sliding mode (FSM) control method is introduced in this paper. Unlike most single-wheel independent ABS, this design has more advantages when braking under the unusual road conditions, such as the transition of road conditions, the split-road conditions between the left-side wheels and the right-side wheels, even the extreme situation in which road conditions of each wheel are different, as it has the smooth-braking judgment module that is designed for wheel-to-wheel control. Besides, based on the nonlinear function of the tire-road interaction (TRI) model, the designed road condition detection module provides characteristics of the braking road that are required in the ABS operation. The model of vehicle and tire is established in Simulink by using parameters of a vehicle: BYD F0. The effectiveness of the proposed four-wheel ABS is validated through the combined use of MATLAB and RT-lab and via substantial simulations and RT-LAB co-simulations.

Determination of Curve Speed Zones for Mountainous Freeways

Different vehicular speed limits may have an impact on the balance between safety and efficiency of travel on mountainous road corners associated with complex road conditions. Placing suitable speed limit warning signs does not merely effectively improve traffic safety but can also improve traffic efficiency. In this study, a global positioning system (GPS) terminal and Metrocount were used to collect vehicle speed data from more than 40 provincial-level curves in 8 provinces over the course of 1 year. Each road data collection time-period lasted approximately 8 hours. A descriptive statistics method was adopted by means of data screening and pretreatment. Additionally, both a velocity difference estimation model was established and a linear model of velocity differential estimation was constructed. Quantitative analysis was carried out on the safe speed, the driver’s expected speed, and the location of the speed limit warning signs. This demonstrated a positive correlation with the initial speed. When the difference in speed was greater than 15 km/h, a safety warning sign was required to limit the design speed to 80 km/h. A safety warning sign was also required when the corner radius was less than 300 m. The location of safety warning signs could be calculated based on the operating speed and taking driving safety and the visual range of drivers into consideration. The results can provide a theoretical reference for setting up appropriate safe speed limiting signs on road corners in mountainous areas.

Real-Time Evacuation Strategy Based on Cell-Inspired Simulation Model.

During the evacuation process in an emergency, the route conditions usually change instantaneously, which makes routing selection a challenging work. To describe dynamic changes in the evacuation environment, this work proposes a real-time evacuation strategy based on a comprehensive route constraint in the framework of a cell-inspired simulation model, intelligence decision P system (IDPS). In our model, the comprehensive route constraint is formed to describe more complex road condition information including the total distance, congestion state, and unreliability of the route. Meanwhile, the IDPS model has been further improved in both the knowledge base description and the decision-making ability. Experiments are conducted to simulate five different scenarios in a fire evacuation. The results show that the evacuation strategy with a comprehensive route constraint has a significant improvement in the evacuation efficiency and has higher robustness. Which kind of route condition should be emphasized more in different evacuation scenarios is also analyzed.

Body attitude control strategy based on road level for heavy rescue vehicles

This paper proposes an attitude control strategy based on road level for heavy rescue vehicles. The strategy aims to address the problem of poor ride comfort and stability of heavy rescue vehicles in complex road conditions. Firstly, with the pressure of the suspension hydraulic cylinder chamber without a piston rod as the parameter, Takagi–Sugeno fuzzy controller classification and adaptive network-based fuzzy inference system controller classification are used to recognise the road level. Secondly, particle swarm optimisation is adopted to obtain the optimal parameters of the active suspension system of vehicle body attitude control under different road levels. Lastly, the parameters of the active suspension system are selected in accordance with the road level recognised in the driving process to improve the adaptive adjustment capability of the active suspension system at different road levels. Test results show that the root mean square values of vertical acceleration, pitch angle and roll angle of the vehicle body are reduced by 59.9%, 76.2% and 68.4%, respectively. This reduction improves the ride comfort and stability of heavy rescue vehicles in complex road conditions.

Optimal design of urban cloud transportation planning based on information retrieval and social IoT

Optimal design of urban cloud transportation planning based on information retrieval and social IoT is proposed in this manuscript. Transportation is a necessary part of the human society's production, life and economic development. With the development of the times and advancement of science and technology, people are strongly dependent on transportation and at the same time, they have put forward more demands on transportation. In this paper, based on the omnidirectional and complex road conditions of vehicle nodes in the urban road network environment, and the road environment has blocking and superimposed interference effects on wireless signals, combined with the intelligent driving model, this paper analyzes and studies the propagation of network worms and builds a stable and reliable system. The experimental results have proven the performance, and the future research directions have been pointed out.

Analysis of Force Transmission Characteristics of Modular Deformable Tire

In order to improve the explosion-proof, puncture-proof and safety performance of tires, a new type of modular deformable tires which can be used in complex road conditions has been put forward. The main innovation is the absence of so-called inner tubes and the modular design of the tire — which mainly consist of six petal-shaped connecting blocks and wheel frames. Firstly, this paper analyzes the structure and working principle of the tire. On this basis, the mechanical modeling of the tire under driving and braking conditions has been established. At last, through ADAMS software, the dynamic simulation of this tire under four circumstances of driving, accelerating, decelerating and braking has been carried out, and the response characteristic curves have been obtained The simulation results show that the force transmission performance of the modular deformable tire is rather good under the above four conditions. The simulation results provide a theoretical foundation and guidance for the structural design of new modular deformable tires.

A Connectivity-Prediction-Based Dynamic Clustering Model for VANET in an Urban Scene

Maintaining network connectivity is an important challenge for vehicular ad hoc network (VANET) in an urban scene, which has more complex road conditions than highways and suburban areas. Most existing studies analyze end-to-end connectivity probability under a certain node distribution model, and reveal the relationship among network connectivity, node density, and a communication range. Because of various influencing factors and changing communication states, most of their results are not applicable to VANET in an urban scene. In this article, we propose a connectivity prediction-based dynamic clustering (DC) model for VANET in an urban scene. First, we introduce a connectivity prediction method (CP) according to the features of a vehicle node and relative features among vehicle nodes. Then, we formulate a DC model based on connectivity among vehicle nodes and vehicle node density. Finally, we present a DC model-based routing method to realize stable communications among vehicle nodes. The experimental results show that the proposed CP can achieve a lower error rate than the geographic routing based on predictive locations and multilayer perceptron. The proposed routing method can achieve lower end-to-end latency and higher delivery rate than the greedy perimeter stateless routing and modified distributed and mobility-adaptive clustering-based methods.

Parallel structure of six wheel-legged robot trajectory tracking control with heavy payload under uncertain physical interaction

PurposeThis paper aims on the trajectory tracking of the developed six wheel-legged robot with heavy load conditions under uncertain physical interaction. The accuracy of trajectory tracking and stable operation with heavy load are the main challenges of parallel mechanism for wheel-legged robots, especially in complex road conditions. To guarantee the tracking performance in an uncertain environment, the disturbances, including the internal friction, external environment interaction, should be considered in the practical robot system.Design/methodology/approachIn this paper, a fuzzy approximation-based model predictive tracking scheme (FMPC) for reliable tracking control is developed to the six wheel-legged robot, in which the fuzzy logic approximation is applied to estimate the uncertain physical interaction and external dynamics of the robot system. Meanwhile, the advanced parallel mechanism of the electric six wheel-legged robot (BIT-NAZA) is presented.FindingsCo-simulation and comparative experimental results using the BIT-NAZA robot derived from the developed hybrid control scheme indicate that the methodology can achieve satisfactory tracking performance in terms of accuracy and stability.Originality/valueThis research can provide theoretical and engineering guidance for lateral stability of intelligent robots under unknown disturbances and uncertain nonlinearities and facilitate the control performance of the mobile robots in a practical system.

Intelligent design of street lamp based on Arduino

In order to promote the process of social modernization, the traditional street lamps are also moving towards intelligent development. However, the existing street lamps mostly use a single LED lamp or high-pressure sodium lamp, which can’t cope with the complex road conditions in China. The designer proposes to install the monitoring system on the street lamp, design the fine artificial intelligence light distribution and color temperature regulation scheme, add the functions of positioning, alarm, repair, pollutant and rain and snow monitoring, and realize the data interaction between the street lamp and the user and the manual intervention of the user when necessary through the infrared Bluetooth Internet of things and other technologies. The design is developed, simulated, debugged and tested on Arduino hardware and software platform. The results show that the design is reasonable and feasible.

Neural fuzzy approximation enhanced autonomous tracking control of the wheel-legged robot under uncertain physical interaction

The accuracy of trajectory tracking and stable operation with heavy load are the main challenges of parallel mechanism for wheel-legged robots, especially in complex road conditions. To guarantee the tracking performance in an uncertain environment, the disturbances, including the internal-robot friction and external-robot and environment interaction forces, should be considered in the robot’s dynamical system. In this article, a neural fuzzy-based model predictive tracking scheme (NFMPC) for reliable tracking control is proposed to the developed four wheel-legged robot, and the fuzzy neural network approximation is applied to estimate the unknown physical interaction and external dynamics of the robot system. Meanwhile, the advanced parallel mechanism of the four wheel-legged robot (BIT-NAZA) is introduced. Finally, co-simulation and experiment results using the BIT-NAZA robot derived from the proposed hybrid control strategy indicate that the methodology can achieve satisfactory tracking performance in terms of accuracy and stability. This research can provide theoretical and engineering guidance for lateral stability of intelligent robots under unknown disturbances and uncertain nonlinearities, and facilitate the control performance of the wheel-legged robot in a practical system.

Multi-mode energy management strategy for hydraulic hub-motor auxiliary system based on improved global optimization algorithm

Heavy commercial vehicles equipped with a hydraulic hub-motor auxiliary system (HHMAS) often operate under complex road conditions. Selecting appropriate operating mode and realizing reasonable energy management to match unpredictable road conditions are the keys to the driving performance and fuel economy of HHMAS. Therefore, a multi-mode energy management strategy (MM-EMS) based on improved global optimization algorithm is proposed in this study for HHMAS. First, an improved dynamic programming (DP) algorithm for HHMAS is developed. This improved DP algorithm considers the effect of SOC and vehicle speed, thereby preventing the calculation results from falling into local optimization. This algorithm also reduces the dimension of the control variable data grid, and the calculation time is reduced by 35% without affecting the accuracy. Second, a MM-EMS with hierarchical control is proposed. This strategy extracts the optimal control rules from the results of the improved DP algorithm. Then it divides the system’s operating region into two types, namely, single-mode working region and mixedmode working region. In the single-mode working region, mode switching is realized through fixed thresholds. In the mixedmode working region, a linear quadratic regulator (LQR) is adopted to determine a target mode and realize SOC tracking control. Finally, the designed MM-EMS is verified separately in offline simulation and hardware-in-the-loop (HIL) under actual vehicle test cycles. Simulation results show that the results between HIL and offline simulation are largely coincidence. Besides, in comparison with the engine optimal control strategy, the designed MM-EMS can achieve an approximate optimal control, with oil savings of 3.96%.

Ripple-GAN: Lane Line Detection With Ripple Lane Line Detection Network and Wasserstein GAN

With artificial intelligence technology being advanced by leaps and bounds, intelligent driving has attracted a huge amount of attention recently in research and development. In intelligent driving, lane line detection is a fundamental but challenging task particularly under complex road conditions. In this paper, we propose a simple yet appealing network called Ripple Lane Line Detection Network (RiLLD-Net), to exploit quick connections and gradient maps for effective learning of lane line features. RiLLD-Net can handle most common scenes of lane line detection. Then, in order to address challenging scenarios such as occluded or complex lane lines, we propose a more powerful network called Ripple-GAN, by integrating RiLLD-Net, confrontation training of Wasserstein generative adversarial networks, and multi-target semantic segmentation. Experiments show that, especially for complex or obscured lane lines, Ripple-GAN can produce a superior detection performance to other state-of-the-art methods.

Lane Detection: A Survey with New Results

Lane detection is essential for many aspects of autonomous driving, such as lane-based navigation and high-definition (HD) map modeling. Although lane detection is challenging especially with complex road conditions, considerable progress has been witnessed in this area in the past several years. In this survey, we review recent visual-based lane detection datasets and methods. For datasets, we categorize them by annotations, provide detailed descriptions for each category, and show comparisons among them. For methods, we focus on methods based on deep learning and organize them in terms of their detection targets. Moreover, we introduce a new dataset with more detailed annotations for HD map modeling, a new direction for lane detection that is applicable to autonomous driving in complex road conditions, a deep neural network LineNet for lane detection, and show its application to HD map modeling.

Accessibility Analysis and Modeling for IoV in an Urban Scene

Compared with traditional Internet of Vehicles (IoV) in highways or suburban areas, maintaining network connectivity and stability is an important challenge for IoV in an urban scene, which has complex road conditions. Most existing studies focus on connectivity probability and whole network connectivity analysis. They analyze end-to-end connectivity probability under a certain node distribution model, and reveal the relationship between whole network connectivity and node density. Most of their results are not applicable to IoV in an urban scene. This work presents a concept of an IoV backbone net for IoV in an urban scene, called IoVB-net for short, to realize interconnections among nodes, and formulates an accessibility model based on IoVB-net, and proposes a routing method. The experimental results demonstrate that the trend of the accessibility's theoretical value is in accordance with that of data packet delivery rate, and the proposed routing method based on accessibility can also realize higher delivery rate and lower end-to-end latency than the improved greedy traffic aware routing and greedy perimeter stateless routing.

Road identification system based on CNN

In recent years, convolutional neural network (CNN) has been widely used in image recognition, but there is still a big gap in automatic driving and road recognition. Here we have designed a system that maps raw pixels directly from a single front-facing camera to a steering command. The system mainly uses the camera to recognize the auxiliary lines on the road to realize automatic driving, and the accuracy rate has reached 98%. Unfortunately, such data can only be used in the laboratory, and the recognition of complex road conditions needs further development of machine learning.

Speed Prediction Based on a Traffic Factor State Network Model

The rapid development of traffic theory and information technology has provided diversified and large-scale traffic data resources for traffic research and urban traffic management. At the same time, these data also present many challenges, such as missing data and deviations in data collection. Many researchers have reported that inaccurate or incomplete measurements of traffic variables can be corrected based on either traditional traffic flow theory, which ignores the randomness of traffic, or are performed using machine learning methods, which emphasize data quantity, but do not make effective use of domain knowledge. This paper proposes a Traffic Factor State Network framework defined by traffic factors and their links to represent the relationships between traffic factors; this framework includes not only obvious traffic factors like volume and speed, but also hidden traffic factors such as the environmental impact factor, which is a variable used to represent complex road conditions. This variable is used to describe the influence of non-traffic flow parameters such as road condition and environmental factors, and is estimated by the EM (Expectation Maximization) algorithm based on historical data. This study used a high-order multivariate Markov model to implement the TFSN, which was then used to establish a stochastic model of speed and related factors. A large amount of historical data was used to calculate and calibrate the strength of the links between the model factors. Finally, a stochastic model of speed prediction was established. The verification results compared with actual cases demonstrate the validity and applicability of the proposed model.

A Study of Unmanned Path Planning Based on a Double-Twin RBM-BP Deep Neural Network

Addressing the shortcomings of unmanned path planning, such as significant error and low precision, a path-planning algorithm based on the whale optimization algorithm (WOA)-optimized double-blinking restricted Boltzmann machine-back propagation (RBM-BP) deep neural network model is proposed. The model consists mainly of two twin RBMs and one BP neural network. One twin RBM is used for feature extraction of the unmanned path location, and the other RBM is used for the path similarity calculation. The model uses the WOA algorithm to optimize parameters, which reduces the number of training sessions, shortens the training time, and reduces the training errors of the neural network. In the MATLAB simulation experiment, the proposed algorithm is superior to several other neural network algorithms in terms of training errors. The comparison of the optimal path under the simulation of complex road conditions shows the superior performance of this algorithm. To further test the performance algorithm introduced in this paper, a flower bed, computer room and other actual scenarios were chosen to conduct path-planning experiments for unmanned paths. The results show that the proposed algorithm has obvious advantages in path selection, reducing the running time and improving the running efficiency. Therefore, it has definitive practical value in unmanned driving.