Vehicles In Complex Environment Research Articles

An improved ant colony algorithm based on Q-Learning for route planning of autonomous vehicle

In view of the problems existing in the path planning algorithms of unmanned vehicles, such as low search efficiency, slow convergence speed and easy to fall into the local optimal. Based on the characteristics of route planning for unmanned vehicles, this paper introduces Q-Learning into the traditional ant colony algorithm to enhance the learning ability of the algorithm in dynamic environment, so as to improve the overall efficiency of route search. By mapping pheromones into Q values in Q-learning, rapid search in complex environments is realized, and a collection-free path satisfying constraints is quickly found. The results of case analysis show that compared with the traditional ant colony algorithm and the improved ant colony algorithm considering reward and punishment factors, the improved ant colony algorithm based on Q-Learning can effectively reduce the number of iterations, shorten the path optimization time and path length and other performance indicators, and has many advantages in jumping out of the local optimal, improving the global search ability and improving the convergence speed, and has good adaptability and robustness in complex environments. It ensures the safety and stability of unmanned vehicles in complex environments.

Self-Evaluation of Trajectory Predictors for Autonomous Driving

Driving experience and anticipatory driving are essential skills for humans to operate vehicles in complex environments. In the context of autonomous vehicles, the software must offer the related features of scenario understanding and motion prediction. The latter feature of motion prediction is extensively researched with several competing large datasets, and established methods provide promising results. However, the incorporation of scenario understanding has been sparsely investigated. It comprises two aspects. First, by means of scenario understanding, individual assumptions of an object’s behavior can be derived to adaptively predict its future motion. Second, scenario understanding enables the detection of challenging scenarios for autonomous vehicle software to prevent safety-critical situations. Therefore, we propose a method incorporating scenario understanding into the motion prediction task to improve adaptivity and avoid prediction failures. This is realized by an a priori evaluation of the scenario based on semantic information. The evaluation adaptively selects the most accurate prediction model but also recognizes if no model is capable of accurately predicting this scenario and high prediction errors are expected. The results on the comprehensive scenario library CommonRoad reveal a decrease in the Euclidean prediction error by 81.0% and a 90.8% reduction in mispredictions of our method compared to the benchmark model.

A Dynamic Path-Planning Method for Obstacle Avoidance Based on the Driving Safety Field.

Establishing an accurate and computationally efficient model for driving risk assessment, considering the influence of vehicle motion state and kinematic characteristics on path planning, is crucial for generating safe, comfortable, and easily trackable obstacle avoidance paths. To address this topic, this paper proposes a novel dual-layered dynamic path-planning method for obstacle avoidance based on the driving safety field (DSF). The contributions of the proposed approach lie in its ability to address the challenges of accurately modeling driving risk, efficient path smoothing and adaptability to vehicle kinematic characteristics, and providing collision-free, curvature-continuous, and adaptable obstacle avoidance paths. In the upper layer, a comprehensive driving safety field is constructed, composed of a potential field generated by static obstacles, a kinetic field generated by dynamic obstacles, a potential field generated by lane boundaries, and a driving field generated by the target position. By analyzing the virtual field forces exerted on the ego vehicle within the comprehensive driving safety field, the resultant force direction is utilized as guidance for the vehicle's forward motion. This generates an initial obstacle avoidance path that satisfies the vehicle's kinematic and dynamic constraints. In the lower layer, the problem of path smoothing is transformed into a standard quadratic programming (QP) form. By optimizing discrete waypoints and fitting polynomial curves, a curvature-continuous and smooth path is obtained. Simulation results demonstrate that our proposed path-planning algorithm outperforms the method based on the improved artificial potential field (APF). It not only generates collision-free and curvature-continuous paths but also significantly reduces parameters such as path curvature (reduced by 62.29% to 87.32%), curvature variation rate, and heading angle (reduced by 34.11% to 72.06%). Furthermore, our algorithm dynamically adjusts the starting position of the obstacle avoidance maneuver based on the vehicle's motion state. As the relative velocity between the ego vehicle and the obstacle vehicle increases, the starting position of the obstacle avoidance path is adjusted accordingly, enabling the proactive avoidance of stationary or moving single and multiple obstacles. The proposed method satisfies the requirements of obstacle avoidance safety, comfort, and stability for intelligent vehicles in complex environments.

Smart Navigation and Energy Management Framework for Autonomous Electric Vehicles in Complex Environments

Autonomous Electric Vehicles (AEVs) are revolutionizing the world of smart city transportation due to their low resource consumption, improved traffic efficiency, zero carbon emissions, and improved road safety. To ensure the safe passage of vehicles through a complex environment, it is essential to plan for safe and smart navigation and energy management for AEVs. This demands an effective model for locating the optimal Electric Charging Stations (ECS) for scheduling and recharging the AEVs when they run on low battery. Many research works, however, do not focus on navigation and scheduling policies for AEV charging that would occur in extreme events in complex environments. This paper puts forth a Collaborative Optimal Navigation and Charge Planning (CONCP) framework based on Multi-Agent Deep Reinforcement Learning (MADRL). To ensure the safe passage of vehicles through the complex environment, it is essential to plan for safe and smart navigation and energy management for AEVs. The CONCP framework aims to achieve the best route from the origin to the final destination for each AEV, scheduling the optimal ECS while avoiding obstacles, reducing traffic congestion, and maximizing energy efficiency, accordingly. The experimental results indicate that CONCP achieves 27% higher success rates, 31% fewer collision rates, and 37% higher reward per episode than the other state-of-the-art algorithms.

Research on a Horizon Line Detection Method for Unmanned Surface Vehicles in Complex Environments

A critical step in the visual navigation of unmanned surface vehicles (USVs) is horizon line detection, which can be used to adjust the altitude as well as for obstacle avoidance in complex environments. In this paper, a real-time and accurate detection method for the horizon line is proposed. Our approach first differentiates the complexity of navigational scenes using the angular second moment (ASM) parameters in the grey level co-occurrence matrix (GLCM). Then, the region of interest (ROI) is initially extracted using minimal human interaction for the complex navigation scenes, while subsequent frames are dynamically acquired using automatic feature point matching. The matched ROI can be maximally removed from the complex background, and the Zernike-moment-based edges are extracted from the obtained ROI. Finally, complete sea horizon information is obtained through a linear fitting of the lower edge points to the edge information. Through various experiments carried out on a classical dataset, our own datasets, and that of another previously published paper, we illustrate the significance and accuracy of this technique for various complex environments. The results show that the performance has potential applications for the autonomous navigation and control of USVs.

Toward distributed control of networked omnidirectional automated ground vehicles in complex environment with delay communication

The utilization of multiple small-sized automated ground vehicles (AGVs) with omnidirectional movement for cooperative transportation of large objects in manufacturing and logistics is a growing area of research. Utilizing multiple AGVs can improve system flexibility and efficiency compared to using a single large AGV, particularly in clustered and narrow spaces. This study presents a control framework for multiple AGVs to cooperatively transport an object in a cluster environment. The framework utilizes the rapidly-exploring random tree (RRT∗) algorithm to plan a feasible path through the environment, and a new distributed synchronization control algorithm for each AGV to track its desired trajectory and synchronize with its neighbors. The proposed control framework can be applied in cases with time-varying communication delays and networks with directed spanning tree connections, making it more versatile than existing synchronization control methods. Simulation and experimental results are provided to validate the proposed framework.

MPC-based Motion Planning for Autonomous Truck-Trailer Maneuvering

Time-optimal motion planning of autonomous vehicles in complex environments is a highly researched topic. This paper describes a novel approach to optimize and execute locally feasible trajectories for the maneuvering of a truck-trailer Autonomous Mobile Robot (AMR), by dividing the environment in a sequence or route of freely accessible overlapping corridors. Multi-stage optimal control generates local trajectories through advancing subsets of this route. To cope with the advancing subsets and changing environments, the optimal control problem is solved online with a receding horizon in a Model Predictive Control (MPC) fashion with an improved update strategy. This strategy seamlessly integrates the computationally expensive MPC updates with a low-cost feedback controller for trajectory tracking, for disturbance rejection, and for stabilization of the unstable kinematics of the reversing truck-trailer AMR. This methodology is implemented in a flexible software framework for an effortless transition from offline simulations to deployment of experiments. An experimental setup showcasing the truck-trailer AMR performing two reverse parking maneuvers validates the presented method.

Smart Vehicle Path Planning Based on Modified PRM Algorithm.

Path planning is a very important step for mobile smart vehicles in complex environments. Sampling based planners such as the Probabilistic Roadmap Method (PRM) have been widely used for smart vehicle applications. However, there exist some shortcomings, such as low efficiency, low reuse rate of the roadmap, and a lack of guidance in the selection of sampling points. To solve the above problems, we designed a pseudo-random sampling strategy with the main spatial axis as the reference axis. We optimized the generation of sampling points, removed redundant sampling points, set the distance threshold between road points, adopted a two-way incremental method for collision detections, and optimized the number of collision detection calls to improve the construction efficiency of the roadmap. The key road points of the planned path were extracted as discrete control points of the Bessel curve, and the paths were smoothed to make the generated paths more consistent with the driving conditions of vehicles. The correctness of the modified PRM was verified and analyzed using MATLAB and ROS to build a test platform. Compared with the basic PRM algorithm, the modified PRM algorithm has advantages related to speed in constructing the roadmap, path planning, and path length.

Multi-antenna GNSS tight combination attitude determination in the urban environment

It is a challenging task to determine dynamic vehicle attitude using a single-frequency single-epoch multi-antenna global navigation satellite system (GNSS). In the urban environment, the number of visible satellites drops sharply due to the occlusion of trees and tall buildings, hence it is difficult to obtain the high-precision attitude of vehicles using only a multi-antenna GNSS. The GNSS tight combination algorithm selects the same reference satellite between different systems, and can effectively increase the number of observation equations after eliminating the inter-system bias, to improve the attitude accuracy of vehicles in complex environments. Compared with the loose combination algorithm, which selects reference satellites separately between different systems, the tight combination algorithm can further improve the locatable performance when there are fewer satellites. Dynamic vehicle experiments were carried out in an open environment and a complex environment, respectively, using the GPS/BDS/GALILEO three-system single-frequency and single-epoch positioning mode. The results show that the tight combination algorithm and the loose combination algorithm have the same accuracy when there are enough visible satellites in the open environment. In a complex environment, with a cut-off elevation angle of 40°, the percentage of pitch angle error, yaw angle error and roll angle error within 2° increased by 6.1%, 8.07% and 13.43%, respectively, and the ambiguity fixed rate was increased by 14.78%.

An optimal control-based path planning method for unmanned surface vehicles in complex environments

This paper proposes an optimal control-based method named the rapid-Gauss pseudospectral method (RGPM) to obtain a smooth time-optimal path for unmanned surface vehicles (USVs). It is a general global path planning method, improving the Gauss pseudospectral method (GPM) which cannot be applied to complex ocean scenarios. In addition, we optimize the representation of obstacles and add a Maklink algorithm to reduce the computaitonal cost. More specifically, a unified obstacle modeling approach is first introduced, then a continuous-time-optimal-control path planning problem considering USV kinematics is formulated. The orthogonal collocation method is used to discretize the continuous-time-optimal control problem into a nonlinear programming (NLP) problem. Furthermore, we introduce a mesh refinement technique to achieve collision avoidance between adjacent discrete points. To enhance computational efficiency, an initialization and iteration approach is further proposed. Herein, a MAKLINK graph is established to obtain a suboptimal path as the initial guess for the NLP problem. Obstacle-avoidance constraints are iteratively updated according to whether or not there are collisions in the current path. The proposed method was compared with the traditional GPM under two different scenarios. The simulation results show that the proposed method is superior to the traditional GPM in terms of path quality and convergence speed and can obtain quasi-time-optimal paths under complex conditions simultaneously.

Path Planning Method Based on D* lite Algorithm for Unmanned Surface Vehicles in Complex Environments

Path Planning Method Based on D* lite Algorithm for Unmanned Surface Vehicles in Complex Environments

Research on 2D Laser Automatic Navigation Control for Standardized Orchard

With the increase of labor cost and the development of agricultural mechanization, standardized orchards suitable for autonomous operations of agricultural machinery will be a future development trend of the fruit-planting industry. For field-planting processes of standardized orchards, autonomous navigation of orchard vehicles in complex environments is the foundation of mechanized and intelligent field operations. In order to realize autonomous driving and path-tracking of vehicles in complex standardized orchards that involve much noise and interference between rows of fruit trees, an automatic navigation system was designed for orchard vehicles, based on 2D lasers. First, considering the agronomic requirements for orchard planting such as plant spacing, row spacing and trunk diameter, different filtering thresholds were established to eliminate discrete points of 2D laser point cloud data effectively. Euclidean clustering algorithm and the important geometric theorems of three points collinearity was used to extract the central feature points of the trunk, as the same time, navigation path was fitted based on the least square method. Secondly, an automatic navigation control algorithm was designed, and the fuzzy control was used to realize the dynamic adjustment of the apparent distance of the pure pursuit model. Finally, the reliability of the proposed approach was verified by simulation using MATLAB/Simulink, and field tests were carried out based on electric agricultural vehicle. Experimental results show that the method proposed in this study can effectively improve the precision of automatic navigation in complex orchard environment and realize the autonomous operation of orchard vehicles.

Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning

Sampling-based motion planning is an effective tool to compute safe trajectories for automated vehicles in complex environments. However, a fast convergence to the optimal solution can only be ensured with the use of problem-specific sampling distributions. Due to the large variety of driving situations within the context of automated driving, it is very challenging to manually design such distributions. This letter introduces, therefore, a data-driven approach utilizing a deep convolutional neural network (CNN): Given the current driving situation, future ego-vehicle poses can be directly generated from the output of the CNN allowing to guide the motion planner efficiently toward the optimal solution. A benchmark highlights that the CNN predicts future vehicle poses with a higher accuracy compared to uniform sampling and a state-of-the-art A*-based approach. Combining this CNN-guided sampling with the motion planner bidirectional RRT* reduces the computation time by up to an order of magnitude and yields a faster convergence to a lower cost as well as a success rate of 100% in the tested scenarios.

A Hybrid Path Planning Algorithm for Unmanned Surface Vehicles in Complex Environment With Dynamic Obstacles

Unmanned surface vesssel (USV) has been widely applied due to its advantages in the military reconnaissance and resources exploration. Path planning is one of the critical issues for USV applications, which usually includes global and local path planning methods. However, individual global path planning algorithms may not be easy to detect the dynamic obstacles in the environment, and individual local path planning algorithms may not always guarantee the existence of the feasible solution for the complex environment. Therefore, a hybrid algorithm which effectively combines global and local path planning is proposed in this paper to overcome these drawbacks. The A* algorithm is used in the global path planning to generate a global path for USV to reach the target point. The dynamic window algorithm (DWA) is used in the local path planning to avoid the dynamic obstacles and track the global path by following the local target point which is the intersection of the global and local path planning. The weight coefficient considering sea state is added in the objective function of DWA, where the security of USV can be guaranteed by reducing the weight of velocity and increasing the weight of distance when the sea state level becomes high. Thus, USV can get a global optimal path and reach the target point in complex environment with dynamic obstacles and ocean currents via the proposed hybrid algorithm, and the comparative simulation is carried out to verify the effectiveness and advantage of the proposed method.

Optimal Motion Planning for Differentially Flat Systems Using Bernstein Approximation

This letter presents a computational framework to efficiently generate feasible and optimal trajectories for differentially flat autonomous vehicle systems. We formulate the optimal motion planning problem as a continuous-time optimal control problem, and approximate it by a discrete-time formulation using Bernstein polynomials. These polynomials allow for efficient computation of various constraints along the entire trajectory, and are particularly convenient for generating trajectories for safe operation of multiple vehicles in complex environments. The advantages of the proposed method are investigated through theoretical analysis and numerical examples.

Recursive Path Planning Using Reduced States for Car-Like Vehicles on Grid Maps

We present a recursive path-planning method that efficiently generates a path by using reduced states of the search space and taking into account the kinematics, shape, and turning space of a car-like vehicle. Our method is based on a kinematics-aware node expansion method that checks for collisions based on the shape and turning space of a vehicle. We present two heuristics that simultaneously consider the kinematics of a vehicle with and without obstacles. In particular, for challenging environments containing complex obstacles and even narrow passages, we recursively identify intermediate goals and nodes that allow the vehicle to compute a path to its destination. We show the benefits of our method through simulations and experimental results by using an autonomous ground vehicle. Furthermore, we show that our method can efficiently generate a collision-free path for vehicles in complex environments with passageways.

Video-Based Vehicle Detection Approach with Data-Driven Adaptive Neuro-Fuzzy Networks

This paper proposes a novel video-based vehicle detection approach with data-driven adaptive neuro-fuzzy networks. The key ideas include configuring several virtual loops as vehicle detection zones in the image, assuming moving vehicles will cause pixel intensities and local textures to change, and then identifying such changes to detect vehicles. In this work, vehicle detection is treated as a pattern classification problem. First, 14 image features (regarding foreground area, texture change, and environmental condition) are extracted to represent the distinction between vehicle and nonvehicle patterns. Then, three neuro-fuzzy networks are trained via incremental semi-supervised learning to build a data-driven adaptive classifier, which judges whether a vehicle is located in the virtual loop. The semi-supervised learning procedure is performed based on a modified tri-training approach, to automatically optimize the structures and parameters of the component neuro-fuzzy networks. Experimental results illustrate that the proposed approach is accurate and robust to detect vehicles in complex environments (e.g. adverse illumination and weather conditions), and thus can improve the performance of video-based vehicle detection.

Development of Fast Error Compensation Algorithm for Integrated Inertial-Satellite Navigation System of Small-size Unmanned Aerial Vehicles in Complex Environment

Development of Fast Error Compensation Algorithm for Integrated Inertial-Satellite Navigation System of Small-size Unmanned Aerial Vehicles in Complex Environment

A Continuous Local Motion Planning Framework for Unmanned Vehicles in Complex Environments

As the complexity of an unmanned vehicle's operational environment increases so does the need to consider the obstacle space continually, and this is aided by splitting the motion planning functionality into distinct global and local layers. This paper presents a new continuous local motion planning framework, where the output and control space elements of the traditional receding horizon control problem are separated into distinct layers. This separation reduces the complexity of the local motion trajectory optimisation, enabling faster design and increased horizon length. The focus of this paper is on the output space component of this framework. Bezier polynomial functions are used to describe local motion trajectories which are constrained to vehicle performance limits and optimised to track a global trajectory. Development and testing is in simulation, targeted at a nonlinear model of a quadrotor unmanned air vehicle. The defined framework is used to provide situation-aware tracking of a global trajectory in the presence of static and dynamic obstacles, as well as realistic turbulence and gusts. Also demonstrated is the immediate-term decentralised deconfliction of multiple unmanned vehicles, and multiple formations of unmanned vehicles.

A Probabilistic Algorithm for Mode Based Motion Planning of Agile Unmanned Air Vehicles in Complex Environments

In this work, we consider the design of a probabilistic trajectory planner for a highly maneuverable unmanned air vehicle flying in a dense and complex city-like environment. Our design hinges on the decomposition of the problem into a) flight controls of fundamental agile-maneuvering flight modes and b) trajectory planning using these controlled flight modes from which almost any aggressive maneuver (or a combination of) can be created. This allows significant decreases in control input space and thus search dimensions, resulting in a natural way to design controllers and implement trajectory planning using the closed-form flight modes. Focusing on the trajectory planning part, we provide a three-step probabilistic trajectory planner. In the first step, the algorithm rapidly explores the environment through a randomized reachability tree search using an approximate line segment models. The resulting connecting path is converted into flight milestones through a line-of-sight segmentation. This path and the corresponding milestones are refined with a single-query Probabilistic Road Map (PRM) implementation that creates dynamically feasible flight paths with distinct flight mode selections. We address the problematic issue of narrow passages through non-uniform distributed capture regions, which prefer state solutions that align the vehicle to enter the milestone region in line with the next milestone to come. Numerical simulations in 3D and 2D demonstrate the ability of the method to provide real-time solutions in dense and complex environments.