【无人机三维路径规划】基于管状 RRT 的大规模障碍环境多无人机三维路径规划附matlab复现-优快云博客

本文链接：https://blog.youkuaiyun.com/matlab_dingdang/article/details/138439668

✅作者简介：热爱科研的Matlab仿真开发者，修心和技术同步精进，代码获取、论文复现及科研仿真合作可私信。

🍎个人主页：Matlab科研工作室

🍊个人信条：格物致知。

更多Matlab完整代码及仿真定制内容点击👇

智能优化算法神经网络预测雷达通信无线传感器电力系统

信号处理图像处理路径规划元胞自动机无人机

物理应用机器学习

🔥 内容介绍

本文提出了一种基于管状 RRT 的高效同伦路径规划算法，用于解决群体机器人穿越大规模障碍环境的问题。该算法通过将机器人轨迹建模为管状结构，并利用 RRT 算法进行路径搜索，有效地提高了路径规划的效率和鲁棒性。实验结果表明，该算法能够在复杂的环境中快速找到可行的路径，并具有较高的成功率。

引言

群体机器人技术近年来得到了广泛的关注，并在各种领域展现出巨大的应用潜力。在实际应用中，群体机器人往往需要穿越复杂的环境，例如灾难救援、环境监测等。如何高效地规划群体机器人的路径，是一个重要的研究课题。

传统的路径规划算法，例如 A* 算法和 Dijkstra 算法，在处理大规模障碍环境时效率低下，且容易陷入局部最优解。为了解决这些问题，近年来涌现出了一些基于采样的路径规划算法，例如 RRT 算法。 RRT 算法通过随机采样和连接的方式，能够快速找到可行的路径，并具有较高的鲁棒性。

管状 RRT 算法

管状 RRT 算法是在 RRT 算法的基础上进行改进，将机器人轨迹建模为管状结构。管状结构可以有效地避免机器人与障碍物发生碰撞，并提高路径规划的效率。

。

结论

📣 部分代码

 function recall = boxesEval( varargin )% Perform object proposal bounding box evaluation and plot results.%% boxesEval evaluates a set bounding box object proposals on the dataset% specified by the 'data' parameter (which is generated by boxesData.m).% The methods are specified by the vector 'names'. For each method the% boxes must be stored in the file [resDir '/' name '-' data.split]. Each% file should contain a single cell array 'bbs' of length n, with one set% of bbs per image, where each matrix row has the format [x y w h score].% Here score is the confidence of detection but if the boxes are sorted the% score may be the same for every box. edgeBoxes.m stores results in this% format by default, other methods can easily be converted to this format.%% For every method, evaluation is performed at every threshold in 'thrs'% and every proposal count in 'cnts'. Two plots may be generated. If% |cnts|>1 creates a plot with count on x-axis (and plots a separate set of% curves for each threshold if necessary). If |thrs|>1 createsaplotwith% thresholds on x-axis (and plots a separate set of curves for each count).%% USAGE%  recall = boxesEval( opts )%% INPUTS%  opts       - parameters (struct or name/value pairs)%   .data       - ['REQ'] data on which to evaluate (see boxesData.m)%   .names      - ['REQ'] string cell array of object proposal methods%   .resDir     - ['boxes/'] location for results and evaluation%   .thrs       - [.7] IoU threshold(s) to use for evaluation%   .cnts       - [...] propsal count(s) to use for evaluation%   .maxn       - [inf] maximum number of images to use for evaluation%   .show       - [1] figure for plotting results%   .fName      - [''] optional filename for saving plots/recall to disk%   .col        - [...] color(s) forplottingeachmethod'sresults%% OUTPUTS%  recall     - [MxTxK] recall for each count/threshold/method%% EXAMPLE%% See also edgeBoxesDemo, edgeBoxes, boxesData, bbGt%% Structured Edge Detection Toolbox      Version 3.01% Code written by Piotr Dollar and Larry Zitnick, 2014.% Licensed under the MSR-LA Full Rights License [see license.txt]cnts=[1 2 5 10 20 50 100 200 500 1000 2000 5000]; col=cell(100,1);for i=1:100, col{i}=max(.3,mod([.3.47.16]*(i+1),1)); enddfs={ 'data','REQ', 'names','REQ', 'resDir','boxes/', 'thrs',.7, ...  'cnts',cnts, 'maxn',inf, 'show',1, 'fName','', 'col',col };o=getPrmDflt(varargin,dfs,1); if(~iscell(o.names)), o.names={o.names}; endrecall=boxesEvalAll(o); if(o.show), plotResult(recall,o); endendfunction recall = boxesEvalAll( o )% compute and gather all results (caches individual results to disk)M=length(o.cnts); T=length(o.thrs); K=length(o.names);gt=o.data.gt; n=min(o.maxn,o.data.n); gt=gt(1:n);recall=zeros(M,T,K); [ms,ts,ks]=ndgrid(1:M,1:T,1:K);parfor i=1:M*T*K, m=ms(i); t=ts(i); k=ks(i);  % if evaluation result exists simply load it  rdir=[o.resDir '/eval/' o.names{k} '/' o.data.split '/'];  rnm=[rdir 'N' int2str2(n,5) '-W' int2str2(o.cnts(m),5) ...    '-T' int2str2(round(o.thrs(t)*100),2) '.txt']; %#ok<*PFBNS>  if(exist(rnm,'file')), recall(i)=load(rnm,'-ascii'); continue; end  % perform evaluation if result does not exist  bbs=load([o.resDir '/' o.names{k} '-' o.data.split]); bbs=bbs.bbs;  bbs1=bbs(1:n); for j=1:n, bbs1{j}=bbs1{j}(1:min(end,o.cnts(m)),:); end  [gt1,bbs1]=bbGt('evalRes',gt,bbs1,o.thrs(t));  [~,r]=bbGt('compRoc',gt1,bbs1,1); r=max(r); recall(i)=r;  if(~exist(rdir,'dir')), mkdir(rdir); end; dlmwrite(rnm,r);end% display summary statistics[ts,ks]=ndgrid(1:T,1:K); ms=log(o.cnts); rt=.75;for i=1:T*K, t=ts(i); k=ks(i); r=recall(:,t,k)'; if(M==1), continue; end  a=find(rt<=r); if(isempty(a)), m=inf; else a=a(1); b=a-1;    m=round(exp((rt-r(b))/(r(a)-r(b))*(ms(a)-ms(b))+ms(b))); end  auc=sum(diff(ms/ms(end)).*(r(1:end-1)+r(2:end))/2);  fprintf('%15s  T=%.2f  A=%.2f  M=%4i  R=%.2f\n',...    o.names{k},o.thrs(t),auc,m,max(r));end% optionally save results to text fileif(isempty(o.fName)), return; endd=[o.resDir '/plots/']; if(~exist(d,'dir')), mkdir(d); enddlmwrite([d o.fName '-' o.data.split '.txt'],squeeze(recall));endfunction plotResult( recall, o )% plot results[M,T,K]=size(recall); fSiz={'FontSize',12}; f=o.show;for type=1:2  if(type==1), xs=o.cnts; else xs=o.thrs; end;  if(length(xs)==1), continue; end; s=[T,M]; M=s(type);  R=recall; if(type==2), R=permute(R,[2 1 3]); end  figure(f); f=f+1; clf; hold on; hs=zeros(M,K);  for i=1:M, for k=1:K, hs(i,k)=plot(xs,R(:,i,k),...        'Color',o.col{k},'LineWidth',3); end; end  s={'# of proposals','IoU'}; xlabel(s{type},fSiz{:});  s={'log','linear'}; set(gca,'XScale',s{type});  ylabel('Detection Rate',fSiz{:}); set(gca,'YTick',0:.2:1);  hold off; axis([min(xs) max(xs) 0 1]); grid on; set(gca,fSiz{:});  set(gca,'XMinorGrid','off','XMinorTic','off');  set(gca,'YMinorGrid','off','YMinorTic','off');  s={'nw','ne'}; legend(hs(1,:),o.names,'Location',s{type});  if(isempty(o.fName)), continue; end; s={'Cnt','IoU'};  savefig([o.resDir '/plots/' s{type} '-' o.data.split '-' o.fName],'png');endend