Cooperative Search of UAV Swarm Based on Ant Colony Optimization with Artificial Potential Field

An ant colony optimization with artificial potential field(ACOAPF)algorithm is proposed to solve the cooperative search mission planning problem of unmanned aerial vehicle(UAV)swarm.This algorithm adopts a distributed architecture where each UAV is considered as an ant and makes decision autonomously.At each decision step,the ants choose the next gird according to the state transition rule and update its own artificial potential field and pheromone map based on the current search results.Through iterations of this process,the cooperative search of UAV swarm for mission area is realized.The state transition rule is divided into two types.If the artificial potential force is larger than a threshold,the deterministic transition rule is adopted,otherwise a heuristic transition rule is used.The deterministic transition rule can ensure UAVs to avoid the threat or approach the target quickly.And the heuristics transition rule considering the pheromone and heuristic information ensures the continuous search of area with the goal of covering more unknown area and finding more targets.Finally,simulations are carried out to verify the effectiveness of the proposed ACOAPF algorithm for cooperative search mission of UAV swarm.

Dynamic collision avoidance for cooperative fixed-wing UAV swarm based on normalized artificial potential field optimization

Cooperative path planning is an important area in fixed-wing UAV swarm.However,avoiding multiple timevarying obstacles and avoiding local optimum are two challenges for existing approaches in a dynamic environment.Firstly,a normalized artificial potential field optimization is proposed by reconstructing a novel function with anisotropy in each dimension,which can make the flight speed of a fixed UAV swarm independent of the repulsive/attractive gain coefficient and avoid trapping into local optimization and local oscillation.Then,taking into account minimum velocity and turning angular velocity of fixed-wing UAV swarm,a strategy of decomposing target vector to avoid moving obstacles and pop-up threats is proposed.Finally,several simulations are carried out to illustrate superiority and effectiveness.

Collision avoidance planning in multi-robot system based on improved artificial potential field and rules

For real-time and distributed features of multi-robot system,the strategy of combining the improved artificial potential field method and the rules based on priority is proposed to study the collision avoidance planning in multi-robot systems. The improved artificial potential field based on simulated annealing algorithm satisfactorily overcomes the drawbacks of traditional artificial potential field method,so that robots can find a local collision-free path in the complex environment. According to the movement vector trail of robots,collisions between robots can be detected,thereby the collision avoidance rules can be obtained. Coordination between robots by the priority based rules improves the real-time property of multi-robot system. The combination of these two methods can help a robot to find a collision-free path from a starting point to the goal quickly in an environment with many obstacles. The feasibility of the proposed method is validated in the VC-based simulated environment.

Solution to reinforcement learning problems with artificial potential field

A novel method was designed to solve reinforcement learning problems with artificial potential field.Firstly a reinforcement learning problem was transferred to a path planning problem by using artificial potential field(APF),which was a very appropriate method to model a reinforcement learning problem.Secondly,a new APF algorithm was proposed to overcome the local minimum problem in the potential field methods with a virtual water-flow concept.The performance of this new method was tested by a gridworld problem named as key and door maze.The experimental results show that within 45 trials,good and deterministic policies are found in almost all simulations.In comparison with WIERING's HQ-learning system which needs 20 000 trials for stable solution,the proposed new method can obtain optimal and stable policy far more quickly than HQ-learning.Therefore,the new method is simple and effective to give an optimal solution to the reinforcement learning problem.

NOVEL APPROACH FOR ROBOT PATH PLANNING BASED ON NUMERICAL ARTIFICIAL POTENTIAL FIELD AND GENETIC ALGORITHM

A novel approach for collision-free path planning of a multiple degree-of-freedom （DOF） articulated robot in a complex environment is proposed. Firstly, based on visual neighbor point （VNP）, a numerical artificial potential field is constructed in Cartesian space, which provides the heuristic information, effective distance to the goal and the motion direction for the motion of the robot joints. Secondly, a genetic algorithm, combined with the heuristic rules, is used in joint space to determine a series of contiguous configurations piecewise from initial configuration until the goal configuration is attained. A simulation shows that the method can not only handle issues on path planning of the articulated robots in environment with complex obstacles, but also improve the efficiency and quality of path planning.

Mobile robot path planning method combined improved artificial potential field with optimization algorithm

To overcome the shortcomings of the traditional artificial potential field method in mobile robot path planning, an improved artificial potential field model （IAPFM） was established, then a new path planning method combining the IAPFM with optimization algorithm （trust region algorithm） is proposed. Attractive force between the robot and the target location, and repulsive force between the robot and the obstacles are both converted to the potential field intensity; and filled potential field is used to guide the robot to go out of the local minimum points ; on this basis, the effect of dynamic obstacles velocity and the robot＇s velocity is consid thers and the IAPFM is established, then both the expressions of the attractive potential field and the repulsive potential field are obtained. The trust region algorithm is used to search the minimum value of the sum of all the potential field inten- sities within the movement scope which the robot can arrive in a sampling period. Connecting of all the points which hare the minimum intensity in every sampling period constitutes the global optimization path. Experiment result shows that the method can meet the real-time requirement, and is able to execute the mobile robot path planning task effectively in the dynamic environment.

Intelligent decision-making method for vehicles in emergency conditions based on artificial potential fields and finite state machines

This study aims to propose a decision-making method based on artificial potential fields(APFs)and finite state machines(FSMs)in emergency conditions.This study presents a decision-making method based on APFs and FSMs for emergency conditions.By modeling the longitudinal and lateral potential energy fields of the vehicle,the driving state is identified,and the trigger conditions are provided for path planning during lane changing.In addition,this study also designed the state transition rules based on the longitudinal and lateral virtual forces.It established the vehicle decision-making model based on the finite state machine to ensure driving safety in emergency situations.To illustrate the performance of the decision-making model by considering APFs and finite state machines.The version of the model in the co-simulation platform of MATLAB and CarSim shows that the developed decision model in this study accurately generates driving behaviors of the vehicle at different time intervals.The contributions of this study are two-fold.A hierarchical vehicle state machine decision model is proposed to enhance driving safety in emergency scenarios.Mathematical models for determining the transition thresholds of lateral and longitudinal vehicle states are established based on the vehicle potential field model,leading to the formulation of transition rules between different states of autonomous vehicles(AVs).

基于双向目标偏置APF-informed-RRT^(*)算法的机械臂路径规划

针对当前机械臂路径规划算法存在搜索随机性大、目标偏置性差和路径曲折等问题,提出了一种基于双向目标偏置的APF-informed-RRT^(∗)算法。首先在双向informed-RRT^(∗)基础上引入概率自适应的目标偏置策略,降低搜索的随机性,提高采样效率;其次针对路径扩展在双向搜索树中融入人工势场法,减少算法的迭代次数;同时在路径生长阶段,采用动态步长生长策略,即根据搜索树的扩展趋势动态调整步长,避免出现局部最优,并且加快路径搜索时间;最后针对冗余节点采用三角不等式原理进行去除,进而通过B样条曲线对路径进行平滑处理,得到最优规划路径。通过与双向RRT^(∗)、双向informed-RRT^(∗)和双向P-RRT^(∗)等算法在三维环境下进行了仿真对比实验验证,相较于双向RRT^(∗)在时间上节约了41%,在采样点数量上减少了63%;相较于双向informed-RRT∗在时间上节约了58%,在采样数量上减少了68%;相较于双向P-RRT^(∗)在时间上节约了30%,在采样数量上减少了60%。

基于改进APF-Informed-RRT^(*)的机械臂避障路径规划

针对Informed-RRT^(*)算法在避障路径规划中缺乏目的性和方向性,存在规划时间长、迭代效率低等问题,提出了结合人工势场法和Informed-RRT^(*)算法的避障规划算法。首先,针对传统人工势场法存在目标点不可达、易与障碍物碰撞的问题,提出了改进后的人工势场法,并将其融入Informed-RRT^(*)算法中,使随机树沿势场下降的方向生长,增强其方向性;其次,依据随机树与障碍物间的距离,提出了一种自适应生长步长策略,提高了对空间的探索能力;最后,引入贪心算法的思想,在生长时直接判断随机树能否直达目标点,提高了路径规划效率。在二维和三维环境下对改进后的算法与传统算法及其衍生算法进行对比实验,仿真结果表明改进后的Informed-RRT^(*)算法相较于原始算法规划的路径长度和规划耗时分别减少了17.42%和36.21%。

基于改进APF-FMT^(*)的农业机器人路径规划算法

【目的】解决农业机器人在复杂农业环境下全局路径规划耗时过长、路径最优解求解困难的问题。【方法】提出一种基于改进人工势场法的快速行进树算法(APF-FMT^(*))。首先,在引力势场中引入相对距离,根据与目标点的距离改变引力大小,克服了人工势场法距离目标点过远时引力过大的问题;然后,将FMT^(*)算法与改进人工势场法相结合,采用三阶B样条曲线对路径进行平滑处理;最后,建立3个农业工作地图进行仿真试验。【结果】仿真结果表明,与FMT^(*)、RRT^(*)和Informed-RRT^(*)3种算法对比,在地图Map1和Map2中,APF-FMT^(*)都能快速找到良好的解,且随样本数量增加获得的路径解得到改善,搜索时间比其他3种算法减少45%以上;在有狭小通道的Map3中,APF-FMT^(*)、FMT^(*)搜索时间比RRT^(*)和Informed-RRT^(*)减少75%以上,并且获得更好的解。【结论】本研究提出的APF-FMT^(*)算法不仅克服了FMT^(*)算法冗余探索问题,还有效地解决了人工势场法目标点不可达的问题,提高了农业机器人路径规划效率和作业安全性。

改进RRT^(*)-APF-DP融合算法的机械臂路径规划

针对基本的快速拓展随机树算法(rapidly-exploring random tree,RRT^(*))存在搜索随机性大、效率低、路径非最优的缺点,提出一种引入人工势场法算法(artificial potential field method,APF)和Douglas-Peucker算法的改进RRT^(*)-APF-DP路径规划算法.在RRT*算法的采样点生成阶段引入变采样范围偏置搜索与步长自适应调整策略,融合重新设计的APF算法的引力与斥力函数,增强路径扩展导向性与绕过障碍物能力.采用重采样策略改进DP算法,优化避障代价与控制点数量.实验结果表明,本算法规划的避障路径满足机械臂的运动要求,且算法规划的避障路径代价、规划时间和路径控制节点数均得到有效改善.

基于改进D*Lite⁃APF算法的巡检机器人路径规划

针对巡检机器人在动态场景下路径规划存在非全局最优、路径不平滑及局部避障效果不佳的问题,提出一种将改进D*Lite算法和人工势场法融合的算法。首先优化D*Lite算法启发代价函数,提升规划效率,并引入Dubins曲线平滑生成的全局路径;其次改进人工势场法势场函数并添加随机半径扰动点,解决局部碰撞问题,提高避障性能;最后将两种优化算法有效融合,实现全局规划和局部避障。仿真实验结果表明,相较于单一D*Lite算法,融合算法在路径长度、时间花销、路径拐点及扩展节点数方面均表现更优,能在确保全局路径最优的情况下有效避障。

改进APF的无人机编队避障最优一致性控制方法

针对传统人工势场(Artificial Potential Field,APF)解决避障问题时出现的局部极小值、目标不可达等缺点,提出了一种结合APF和具有协同避障效果的最优一致性控制方法。基于固定无向通信拓扑的双积分器无人机编队模型,引入具有避障代价函数的最优一致性控制协议,解决APF避障的局限性问题,同时对多无人机进行编队控制,使无人机编队控制系统的一致性性能指标、控制消耗性能指标和避障性能指标达到最优解。此外,通过对每架无人机构建虚拟斥力势场,防止在避障过程中出现机间碰撞。仿真结果表明,与改进APF的非最优一致性控制相比,本文提出的改进APF的最优一致性控制能够缩短任务用时32%,且能够极大程度上保持队形完整性,减少避障所造成的一致性消耗和控制损耗。

Path Planning for AUVs Based on Improved APF-AC Algorithm

With the increase in ocean exploration activities and underwater development,the autonomous underwater vehicle(AUV)has been widely used as a type of underwater automation equipment in the detection of underwater environments.However,nowadays AUVs generally have drawbacks such as weak endurance,low intelligence,and poor detection ability.The research and implementation of path-planning methods are the premise of AUVs to achieve actual tasks.To improve the underwater operation ability of the AUV,this paper studies the typical problems of path-planning for the ant colony algorithm and the artificial potential field algorithm.In response to the limitations of a single algorithm,an optimization scheme is proposed to improve the artificial potential field ant colony(APF-AC)algorithm.Compared with traditional ant colony and comparative algorithms,the APF-AC reduced the path length by 1.57%and 0.63%(in the simple environment),8.92%and 3.46%(in the complex environment).The iteration time has been reduced by approximately 28.48%and 18.05%(in the simple environment),18.53%and 9.24%(in the complex environment).Finally,the improved APF-AC algorithm has been validated on the AUV platform,and the experiment is consistent with the simulation.Improved APF-AC algorithm can effectively reduce the underwater operation time and overall power consumption of the AUV,and shows a higher safety.

Local minima-free design of artificial coordinating fields

In order to overcome the drawbacks of conventional artificial potential fields (APF) based methods for the motion planning problems of mobile robots in dynamic uncertain environments, an artificial coordinating fields (ACF) based method has been proposed recently. This paper deals with the reachability problem of the ACF, that is, how to design and choose the parameters of the ACF and how the environment should be such that the robot can reach its goal without being trapped in local minima. Some sufficient conditions for these purposes are developed theoretically. Theoretical analyses show that, the ACF can effectively remove local minima in dynamic uncertain environments with V-shape or U-shape obstacles, and guide the mobile robot to reach its goal with some necessary environment constraints and based on the methods provided in this paper to properly choose the parameters of the ACF. Comparisons between the ACF and APF, and simulations are provided to illustrate the advantages of the ACF.

基于双向A^(*)-APF算法的船舶路径规划研究

为解决目前船舶路径规划算法中存在的全局非最优解和局部最优解等问题,在双向A^(*)算法的基础上加入了优化函数PathOptimization和IsClear,以去除冗余拐点,缩短全局路径距离;在人工势场法(artificial potential field,APF)的基础上,设定离散化步长函数、斥力感应阈值和临时终点,以避免局部最优解和震荡问题;实现两种算法的融合算法(双向A^(*)-APF算法),在MATLAB模拟的相同栅格图中,对比算法改进前后的模拟试验数据。结果表明,融合算法平均减少了50%的冗余拐点,平均减少了47.5%的算法搜索时间,平均缩短了7%的路径距离,能够同时安全规避动态障碍物和静态障碍物。研究表明,双向A^(*)-APF算法可用于解决船舶路径全局非最优解和局部最优解等问题。

考虑无人艇运动学约束的IRRT^(*)-APF路径规划算法

针对未知环境下无人艇(USV)的路径规划问题,提出了一种考虑无人艇运动学约束的改进RRT^(*)-APF路径规划算法(IRRT^(*)-APF)。通过引入改进的人工势场法(APF)提高了快速搜索随机树(RRT^(*))的避障性能,在人工势场中考虑无人艇与障碍物和目标点间的角度大小,加速了无人艇远离障碍物并接近目标点;使用曼哈顿距离法提高了RRT^(*)算法的效率。所提出的IRRT^(*)-APF方法,与滚动RRT^(*)算法和PSOFS算法进行了仿真对比实验。结果表明,提出的方法所规划的路径转折的次数和转角均显著减小,有利于实现无人艇的平稳控制,同时缩短了路径长度和规划路径的时间。在风浪环境下的进一步仿真实验结果表明,所提出的算法在有风浪干扰时依然能规划出符合无人艇运动学的轨迹,具有较强的抗风浪鲁棒性。

基于改进APF-RRT的6R机械臂避障路径规划

针对6R机械臂在复杂环境下进行避障路径规划时成功率低、效率低等问题,提出一种改进人工势场法(APF)与快速扩展随机树法(RRT)的融合算法。对于传统APF目标不可达问题,提出引入斥力调节因子优化斥力函数,使得机械臂靠近目标点时,障碍物对机械臂的斥力逐渐减小并顺利到达目标点;针对传统RRT算法随机性过强问题,提出目标导向策略进行优化,使得采样点有一定的概率向目标点扩展;当APF陷入局部最优时,采用改进RRT算法进行路径规划,当跳出局部最优时,切换为APF继续路径规划。仿真结果表明:改进APF-RRT算法能适应各种复杂环境,且相较于传统APF和RRT算法具有规划时间短、规划成功率高等优点,有效解决了APF目标不可达和局部最小值的问题。最后通过JAKA机器人实验平台进行实际环境实验,验证了改进APF-RRT融合算法的可行性。

APF与A*融合的多目标点路径规划算法

在智能餐厅环境下,针对移动机器人在多目标点路径规划时存在规划效率不高的问题,提出了一种基于A*算法与APF算法相结合的多目标点路径规划的方法。将多目标点路径规划问题转化成类旅行商问题,采用A*算法和人工势场法规划出多目标点的最优遍历顺序。首先,将若干个目标点用一个集合表示并应用在A*算法上面,实现A*算法多个目标点的路径规划;其次,引入人工势场法对多个目标点进行优先级判定,借助人工势场法计算各个目标点的势能值,之后利用人工势场法得到的势能值对目标点集进行排序,完成各个目标点之间的最优顺序;最后,对规划好的目标点集使用A*算法进行全局路径规划。为了验证该方法的有效性和先进性,将该算法进行消融实验,同时也与两种典型的多目标点规划算法进行对比。结果表明,该算法是有效的,能够在缩短路径规划时间和降低路径代价的同时规划出一条有效路径。