Generating Autonomous Driving Hazard Test Scenarios Using Multi-Agent Proximal Policy Optimization and Enhanced Artificial Potential Field Method

It is a hot topic in the field of road landscape planning technology that a mobile robot can quickly and safely find an optimal path in a multi-obstacle environment. In path planning, in light of the problems of poor cooperation and slow convergence of ant colony algorithm in a known environment, the existing potential field method in the local path environment focuses on avoiding dynamic obstacles but cannot guarantee an optimal path. This study provides a new fusion algorithm for path planning optimization in both static and dynamic environments. Firstly, to prevent slipping into a local optimum, create a pheromone diffusion model and adaptively tweak the population information entropy factor to speed up the convergence speed of the Adaptive Ant Colony Optimization (AACO) algorithm. Secondly, on the basis of the globally planned path, by designing the local stability detection and escape functions, the Improved Artificial Potential Field (IAPF) method is utilized to solve the problem of unreachable destination. Finally, we conduct simulation experiments through MATLAB to compare the indicators for evaluating paths, it verifies that the fusion algorithm proposed in this research has obvious advantages in path planning in both static and dynamic environments.KeywordsPath planningAdaptive ant colony optimizationPopulation information entropyImproved artificial potential field

Forest fire is a natural disaster that causes huge damage to human life and property. Emergency rescue and evacuation actions are crucial in such situations, and path planning is an important part of such actions. Artificial Potential Field (APF) method is a popular path planning method, but it has limitations in complex dynamic environments such as forest fires. In this paper, we propose an improved APF method for forest fire emergency rescue and evacuation path planning. This method uses a dynamic repulsive field to avoid obstacles in the fire scene and an improved attractive field to guide people towards the target. We also combine the classic Rothermel model in forest fire spread to further improve the realism of dynamic spread path planning in forest fires. Computational simulation results show that compared with the original APF method, this method still maintains an acceptable level of computational efficiency as the number of fire scene obstacles increases and is superior to traditional APF method in terms of path planning safety.

Wireless ultraviolet light MIMO assisted UAV direction perception and collision avoidance method

In order to ensure the safety and efficiency of the section tracking operation of a guided transport system, a safety headway control method of section tracking based on intersection conditions is proposed in this paper. Considering the difference of signal phase, the evaluation model of road conditions was established based on a fuzzy comprehensive evaluation method, FAGT. Based on the artificial potential field method, the time-varying hybrid artificial potential field (TH-APF) method was proposed, and the tracking headway control algorithm was designed to realize the dynamic control of the tracking headway of the guide transport vehicle. The simulation results verified the effectiveness and applicability of the evaluation model of intersection road conditions; the tracking headway can be maintained at about 120 s. The tracking headway control algorithm of guided transport vehicles can respond to the road conditions and avoid the local optimum of the artificial potential field method, thus improving the operating efficiency.

For the time sensitive multi-target attack missions, a large amount of information in battlefield is miscellaneous and rapidly changing, so it is essential to study a more efficient and accurate decision-making method. The chief aim of this paper is to build real-time battlefield model and plan flight path with Artificial Potential Field (APF) method, meanwhile, a multi-attribute decision-making method based on information entropy-AHP is proposed to make dynamic decision of attack mission under sudden threats. In order to demonstrate the effectiveness of this method, a combat scenario model is employed. Simulation results show that the proposed decision-making method can quickly update the battlefield information and give decision results, which can meet the attack requirements of aircraft against multiple targets in time-sensitive missions.KeywordsMulti-target attackDecision-makingArtificial Potential Field (APF)Entropy-AHP

Mobile robots require the ability to plan collision-free paths. This paper introduces a wheel-foot hybrid parallel-leg walking robot based on the 6-Universal-Prismatic-Universal-Revolute and 3-Prismatic (6UPUR + 3P) parallel mechanism model. To enhance path planning efficiency and obstacle avoidance capabilities, an improved artificial potential field (IAPF) method is proposed. The IAPF functions are designed to address the collision problems and issues with goals being unreachable due to a nearby problem, local minima, and dynamic obstacle avoidance in path planning. Using this IAPF method, we conduct path planning and simulation analysis for the wheel-foot hybrid parallel-legged walking robot described in this paper, and compare it with the classic artificial potential field (APF) method. The results demonstrate that the IAPF method outperforms the classic APF method in handling obstacle-rich environments, effectively addresses collision problems, and the IAPF method helps to obtain goals previously unreachable due to nearby obstacles, local minima, and dynamic planning issues.

This paper addresses the issues of target unreachability and local optima in traditional artificial potential field (APF) methods for UAV swarm path planning by proposing an improved collaborative obstacle avoidance algorithm. By introducing a virtual target position function to reconstruct the repulsive field model, the repulsive force exponentially decays as the UAV approaches the target, effectively resolving the problem where excessive obstacle repulsion prevents UAVs from reaching the goal. Additionally, we design a dynamic virtual target point generation mechanism based on mechanical state detection to automatically create temporary target points when UAVs are trapped in local optima, thereby breaking force equilibrium. For multi-UAV collaboration, intra-formation UAVs are treated as dynamic obstacles, and a 3D repulsive field model is established to avoid local optima in planar scenarios. Combined with a leader–follower control strategy, a hybrid potential field position controller is designed to enable rapid formation reconfiguration post-obstacle avoidance. Simulation results demonstrate that the proposed improved APF method ensures safe obstacle avoidance and formation maintenance for UAV swarms in complex environments, significantly enhancing path planning reliability and effectiveness.

In order to make the trajectories of robot more close to the actual situation, and make the robot avoid obstacles which are very close to the target point to arrive at the target, in this paper the robot's path optimization in the 3-D space force field have been studied. By using the method of artificial potential field, the traditional artificial potential field theory will be improved. By adding an adjustment factor, a new repulsive force field function has been constructed, and the robot's motion trajectories will be extended to three-dimensional space. Simulating the trajectory planning through the platform of Matlab software, the simulation results show that robots can avoid obstacles effectively and arrive at the target quickly under the method of the improved artificial potential field, even if the obstacle and target is very close.

The objective of this study is to apply differential global positioning system (DGPS) and an improved artificial potential field (APF) method to a wheeled mobile robot (WMR) for path planning under unknown environment. A laser sensor is utilized to detect obstacles and surroundings. With the distance information given by the laser sensor, the repulsive force is used for collision-free of the WMR. By the iterative closest point (ICP) algorithm, the rotation and translation information can be calculated and utilized to aid the position and attitude determination. Fuzzy theory is applied to change the attractive factor to improve the zigzag trajectory. To deal with the local minimum problem, we add the path finding method A* algorithm to find the shortest unblocked path to destination. With the integration of fuzzy rule, positioning and path finding algorithms, the APF can be created. The experiments confirm that the proposed control scheme works properly.

In this paper, a novel obstacle avoidance algorithm for the multi-UAV flocking was proposed by combining artificial potential field and Dubins path planning method. For the multi-UAV flocking, a virtual-leader was considered, and its flight path was designed by Dubins path planning method, which can take into account the overload constraint of the UAV. In this way, the flight path of the whole multi-UAV flocking was roughly planned, so as to save obstacle avoidance time, and the flight path of the follower-UAVs was designed according to the artificial potential field method, which has a better performance in real-time obstacle avoidance, and the algorithm is relatively simple. The simulation results show that the obstacle avoidance algorithm designed by combining the two methods has a better obstacle avoidance ability.

Motion planning for multi-HUG formation in an environment with obstacles

Path planning is a fundamental task in autonomous mobile robot navigation and one of the most computationally intensive tasks. In this work, a parallel version of the bacterial potential field (BPF) method for path planning in mobile robots is presented. The BPF is a hybrid algorithm, which makes use of a bacterial evolutionary algorithm (BEA) with the artificial potential field (APF) method, to take advantage of intelligent and classical methods. The parallel bacterial potential field (parallel-BPF) algorithm is implemented on a graphics processing unit (GPU) to speed up the path planning computation in mobile robot navigation. Simulation results to validate the analysis and implementation are provided; the experiments were specially designed to show the effectiveness and the efficiency of the parallel-BPF algorithm.

Unmanned Aerial Vehicles (UAVs), particularly quadrotor UAVs, are widely recognized for their cost-effectiveness, operational flexibility, and vertical takeoff and landing capabilities, making them ideal for specific airspace operations and emergency response scenarios. Efficient path planning is critical for UAV mission execution, requiring optimal flight paths that ensure safe obstacle avoidance while addressing challenges such as dynamic environments, energy optimization, and multi-parameter management. Despite advancements in path planning techniques, including the artificial potential field (APF) method and reinforcement learning (RL), issues like local optima and parameter tuning complexity persist, limiting adaptability in dynamic environments. This study proposes a hybrid approach integrating Markov Decision Process (MDP) theory with an improved artificial potential field (IAPF) method to enhance quadrotor UAV path planning in three-dimensional environments. By generating global waypoints based on known obstacle, the method minimizes flight path deviations and improves navigation performance. The results demonstrate significant advancements in trajectory accuracy and adaptability, offering a robust solution for UAV path optimization in complex scenarios.

This paper presents a collision-free trajectory planning algorithm for cable-driven robots (CDPRs) in dynamic environment. As the basis, the wrench feasible workspaces (WFW) of CDPRs are obtained. The tradition artificial potential field (APF) method can quickly plan a trajectory. However, APF is not time-efficient with dynamic obstacles. In order to solve this problem, a new scope of APF based on kinematic model is used to generate a trajectory in dynamic environment. Then, Bezier curve is employed to optimize the initial trajectory making motors run smoothly. To validate the proposed improved APF method, kinematic simulations are carried out. The results demonstrate the trajectory generated by improved APF can avoid obstacles in different motion states smoothly.

A novel model predictive artificial potential field based ship motion planning method considering COLREGs for complex encounter scenarios