【正文】 tAbstractAnt colony algorithm is a kind of swarm intelligence optimization algorithm. It is a new intelligent evolutionary algorithm which is a similar to the process of ant munities in search of food in nature. And it is an ideal method for solving difficult discrete problems. It fully demonstrated its advantages in many applications and obtained good results in terms of improved colony algorithm has the advantage of positive feedback, selforganization, distributed, robust, easy to bine with other algorithms. But often trapped in local optimal solution, convergence is slow, the initial solution is relatively high. Theoretically, It will more quickly resolve any binatorial optimization problems, if the ant colony algorithm to make the appropriate changes. This article has been improved on hybrid ant colony algorithm and simulated annealing algorithm bines. It takes into account the objective function gradient of this factor so that global convergence to getting better. In addition, It also made related improvements in the angle optimization. For example, it takes into account the influence of the angle between the direction of the algorithm and the results have been very good.This paper put forward algorithm which is simulated annealing and ant colony hybrid algorithm based on the gradient of objective function and ant colony algorithm in the angle numerical analysis and experiment show that the improved new algorithm not only possesses the advantages of the original algorithm, but also improve the running speed of the algorithm. Applied to the problem of TSP and path planning, The superiority of the new algorithm is verified.The paper contains following tasks:1. This paper briefly introduces the background and significance of research status of ant colony algorithm, and it also describes the content and significance of the study.2. Briefly introduces the basic principles of ant colony algorithm flow algorithm, it also introduces the advantages and disadvantages of the algorithm and so on.3. First introduces the basic principle and algorithm flow of simulated annealing algorithm, Then introduces the basic principles and the algorithm flow of simulated annealing and ant colony hybrid algorithm based on the gradient of objective function, Finally, we gave the experimental results on the new algorithm for solving problems of the TSP .4. First, a brief introduction path planning problem, Then introduces the basic principles and the algorithm flow of ant colony algorithm in the angle optimization, Finally, we gave the experimental results on the new algorithm for solving problems of the path planning. Figure 13 table 1 reference 33　Keywords: ant colony algorithm, simulated annealing algorithm, gradient, angle optimizationChinese books catalog: O224IX目錄目 錄摘 要 IAbstract II插圖或附表清單 VIII引 言 IX1緒 論 1 蟻群算法生成背景和意義 1 蟻群算法的研究現(xiàn)狀 1 論文的研究意義和內(nèi)容 2 論文的研究意義 2 論文的主要內(nèi)容 22 蟻群算法的原理及過(guò)程 4 蟻群算法的基本原理 4 蟻群算法的算法流程 6 蟻群算法的優(yōu)缺點(diǎn) 93基于目標(biāo)函數(shù)梯度的模擬退火蟻群算法 11 模擬退火算法的基本原理和算法流程 11 基于目標(biāo)函數(shù)梯度的模擬退火蟻群算法 12 混合算法的基本原理 12 算法流程 13 實(shí)例與分析 164夾角優(yōu)化的蟻群算法及在路徑規(guī)劃中的應(yīng)用 18 對(duì)路徑規(guī)劃問(wèn)題的描述 18 夾角優(yōu)化的蟻群算法 18 方向夾角 19 基本原理 21 改進(jìn)后的算法流程 22 實(shí)例與分析 25總　結(jié) 27參考文獻(xiàn) 28致 謝 30作者簡(jiǎn)介及讀研期間主要科研成果 31ContentsContentsAbstract ⅠThe list of illustrations and schedule ⅧIntroduction Ⅸ1 Exordium 1 Background and significance of ant colony algorithm …….1 Research status of ant colony algorithm 1 Research significance and main research contents 2 Research significance 2 Main research contents 22 Structural principles and algorithms of ant colony algorithm 4 The basic principles of ant colony algorithm .4 Algorithm flow of ant colony algorithm 6 Advantages and disadvantages of the ant colony algorithm… 9 3 Simulated annealing and ant colony hybrid algorithm based on the gradient of objective function 11 The basic principles and algorithms of simulated annealing algorithm 11 Simulated annealing and ant colony hybrid algorithm based on the gradient of objective function 12 The basic principle of hybrid algorithm 12 Algorithm flow 13 Cases and Analysis 164 Ant colony algorithm in the angle optimization and its application 18 Path planning problem 18 Ant colony algorithm in the angle optimization 18 Orientation angle 19 Fundamental principle 21 The improved algorithm flow 22 Cases and Analysis 25Summarization 27References 28Acknowledgements 30Brief introduction of author 31插圖或附表清單插圖或附表清單相關(guān)圖：圖1：螞蟻路徑尋優(yōu)過(guò)程圖2：蟻群算法的流程圖圖3：模擬退火算法的流程圖圖4：基于目標(biāo)函數(shù)梯度的模擬退火蟻群算法流程圖圖5：改進(jìn)算法的最優(yōu)路徑圖6：改進(jìn)算法的各代最短距離和平均距離圖7：路徑規(guī)劃模型圖8：方向夾角啟發(fā)信息圖9：夾角示意圖圖10：夾角優(yōu)化蟻群算法流程圖圖11：常規(guī)蟻群算法和夾角優(yōu)化蟻群算法