In this paper, we introduce the Aapf* algorithm, an innovative approach that synergistically integrates the A-star search algorithm (A*) with the artificial potential field (apf) method. This algorithm is designed to ...
详细信息
In this paper, we introduce the Aapf* algorithm, an innovative approach that synergistically integrates the A-star search algorithm (A*) with the artificial potential field (apf) method. This algorithm is designed to enhance safety and ensure smoother global path planning for autonomous vehicles, particularly addressing vehicle cornering constraints. Initially, for augmenting the safety of autonomous vehicle, we implement an obstacle expansion strategy with a factor of 2 units, enhancing environmental adaptability. The study then delves into the classical A* algorithm, examining its core principles and characteristics, leading to the development of novel heuristic functions and search strategies that address the limitations inherent in the classic A* algorithm. Subsequently, we explore the apf algorithm, recognized for its excellence in obstacle avoidance in path planning. The paper culminates in the amalgamation of the apf's repulsive field concept with the improved A* algorithm, crafting a comprehensive global planning algorithm tailored for autonomous vehicle path planning schemes. Experiments conducted in a simulated environment model validate the Aapf* algorithm's efficacy in improving both the safety and smoothness, demonstrating its potential for real-world applications.
In the current research field, aiming at the problem of robot path planning, this study proposes an optimization strategy combining RRT algorithm and apf method. This strategy aims to achieve more efficient and reliab...
详细信息
ISBN:
(纸本)9798350352511;9798350352504
In the current research field, aiming at the problem of robot path planning, this study proposes an optimization strategy combining RRT algorithm and apf method. This strategy aims to achieve more efficient and reliable robot path planning by improving the path search efficiency of RRT algorithm and combining the goal-oriented and obstacle-avoiding capability of apf. Specifically, we optimize the RRT algorithm as follows: First, we introduce an apf-based heuristic strategy, which helps guide the path search process closer to the target point faster;Secondly, in the process of path generation, the apf method is used to smooth the path in real time to reduce the complexity of the path and the energy consumption during execution. After extensive testing in simulation environments, the optimization strategy shows significant improvements in path length, planning time, and obstacle avoidance. Compared with the traditional RRT algorithm, the new strategy not only reduces the path length, but also shows stronger adaptive ability and robustness in the face of complex environment and sudden obstacles. In addition, through the path smoothing process guided by apf, the dynamic response and stability of the robot when executing the path are also improved.
This paper focuses on the path planning improvement for mobile robots in cluttered environments. Due to the uncertainty of searching direction in traditional path planning algorithms, each node often searches for its ...
详细信息
This paper focuses on the path planning improvement for mobile robots in cluttered environments. Due to the uncertainty of searching direction in traditional path planning algorithms, each node often searches for its following path node in irrelevant directions, which increases the time cost and the number of invalid nodes. In this study, an artificial potential field guided jump point search algorithm is proposed to solve this low-efficiency problem. This method builds an apf and a direction map, which represent resultant force distribution and node directionality to the target node, respectively. Then, with consideration of apf influence and direction map guidance, an expansion direction priority for path planning is calculated, which guides and improves the search for subsequent jump points. To evaluate its performance and efficiency, the apf-JPS algorithm is compared with the conventional JPS, RRT, apf and 8-domains A* algorithms in simulation and mobile robot experiments. The experimental results indicate that the apf-JPS algorithm not only plans the shortest available path with the least time cost, but also reaches the highest node utilization rate. Comparing with the conventional JPS algorithm, which ranks second in overall performance, both the number of key nodes and the path planning time decrease by 45.0% and 53.8%, respectively, while the node utilization rate increases by 23.4%. Therefore, the apf-JPS algorithm shows its advantages in path planning, mainly by reducing the system computational load, improving the real-time performance, and increasing the mobile robot endurance time.
The rapid development of shipping trade pushes automated container terminals toward the direction of intelligence, safety and efficiency. In particular, the formulation of AGV scheduling tasks and the safety and stabi...
详细信息
The rapid development of shipping trade pushes automated container terminals toward the direction of intelligence, safety and efficiency. In particular, the formulation of AGV scheduling tasks and the safety and stability of transportation path is an important part of port operation and management, and it is one of the basic tasks to build an intelligent port. Existing research mainly focuses on collaborative operation between port equipment and path optimization under environmental perception, while there is relatively little research on optimization of path smoothness and safety. Therefore, we propose a path optimization model based on the artificial potential field and twin delayed deep deterministic policy gradient (apf-TD3) framework for the port environment. Firstly, we obtain the scheduling task plan of a single AGV by enumeration. Secondly, according to the artificial potential field (apf) algorithm to generate repulsion for obstacles in the harbor and attraction for container storage at the target point with the position information of the AGV as the input data of the reinforcement learning algorithm is inputted into the twin delayed deep deterministic policy gradient algorithm (TD3). Then TD3 selects the optimal action strategy for the AGV according to the input AGV state information and the designed reward mechanism as well as executes the action. Through repeated execution, the optimal action for the next step is selected at each point to generate a path with start and end points. We validate the model by simulating the scale of containerized cargo in the port i.e. small scale, medium scale and large scale scenes. The experimental results show that the method has the shortest path length of 27.519 m, 270.847 m, and 496.389 m compared to artificial potential field and deep deterministic policy gradient (apf-DDPG), apf, and rapidlyexploring random tree (RRT) algorithms, which also have significant advantages in terms of path security and path smoothness. T
Aiming at the problem of automated guided vehicle path planning in storage system, this paper provided a new method which combines global path planning algorithm and local path planning algorithm to achieve the goal o...
详细信息
ISBN:
(纸本)9781510845541
Aiming at the problem of automated guided vehicle path planning in storage system, this paper provided a new method which combines global path planning algorithm and local path planning algorithm to achieve the goal of finding the optimal path. In this paper, the improved A* algorithm is used as the global path planning algorithm, and the improved apf algorithm is used as the local path planning algorithm. The hybrid algorithm not only makes full use of the known information to generate the global optimal path, but also can effectively avoid obstacles on the path. The advantages and effectiveness of the hybrid algorithm are proved by the results of simulations and applications.
暂无评论