arescuerobotpathplanningbasedonantcolony-資料下載頁
2025-10-15 18:10本頁面
【導(dǎo)讀】本文討論了機(jī)器人路徑規(guī)劃基於在改進(jìn)蟻群最佳化。提出的情感算法證實(shí)在一個(gè)標(biāo)準(zhǔn)的測詴平臺(tái)，機(jī)器人。機(jī)器人路徑規(guī)劃是一個(gè)機(jī)器人的重要組成部分。其主要任務(wù)是找到一。路徑規(guī)劃是智能機(jī)器人一項(xiàng)重要的能力，並有偉大的。意義去為完成機(jī)器人的任務(wù)。這些方法都非常實(shí)用，但並不適合城市道路的路徑規(guī)劃。蟻群算法可以被看作是一種搜索算法的框架參數(shù)解空間概率分佈模型。因此，在新的搜索模式將側(cè)重於品質(zhì)的搜索空間。由於收斂速度太慢，物和道路的地圖。假設(shè)G=是一個(gè)完整的加權(quán)有向圖，其。置的街道；非負(fù)重量與弧表示端點(diǎn)和端點(diǎn)之間的距離。
【正文】 ll with water, then moving to fire point to extinguish fire. 基於上述分析，本文通過 RCRSS確認(rèn)算法 (機(jī)器人世界杯救援模擬服務(wù)器 ) 。圖一是一個(gè)模擬城市地圖 RCRSS，其消防隊(duì)代理人主要任務(wù)是移動(dòng)從當(dāng)前位置到避難所去補(bǔ)水，然後移動(dòng)到火點(diǎn)滅火。 21 Simulation and Experiment (2/4) Figure 1. A simulated city map in RCRSS 22 Simulation and Experiment (3/4) ? During the simulation process, each Fire Brigade agent plans the path from refuge to fire point. The shorter the path is, the higher efficiency fire fighting will be. 在模擬過程中，每個(gè)消防代理人計(jì)劃的路徑從避難點(diǎn)到火災(zāi)點(diǎn)。較短的路徑，將是滅火效率高。 23 Simulation and Experiment (4/4) ? Fig. 2 shows the controlled fire influence curves of the primal ant colony algorithm and the proposed improved one that are applied in the agents path planning. 圖 2. 顯示了原始蟻群算法的控制火災(zāi)影響曲線和提出一個(gè)改進(jìn)適用於代理人路徑規(guī)劃。 Figure 2. The controlled fire influence curves of the two algorithms 24 Conclusion ? In this paper, by using the ant colony algorithm for global path planning, adopts the objective attraction function to guide ants’ search, which improves the search quality of the ant colony algorithm in plex and dynamic environment. By applying it in the RCRSS, the performance of this algorithm is proved in terms of validity and practicability. 本文，利用蟻群算法全局路徑規(guī)劃，採用目標(biāo)函數(shù)的吸引力引導(dǎo)螞蟻的搜索，在複雜和動(dòng)態(tài)的環(huán)境提高了蟻群算法的搜索品質(zhì)。運(yùn)用它在RCRSS，該算法的性能根據(jù)證實(shí)是有效性和實(shí)用性。 25 References ? [1] H. Kitano, S. Tadokor, and H. Noda, “Robocuprescue: Search And Rescue For Large Scale Disasters As A Domain For Multiagent Research”, Proceedings of the IEEE Conference on Systems, Men and Cyberics, Tokyo, 1999, pp. 739743. ? [2] Marshall, and L. Tarassenko, “Robot path planning using resistive grids Marshall ”, Second International Conference on Artificial Neural Networks, Bournemouth, UK, 1991, pp. 149152. ? [3] Y. Kitamura, , F. Kishino, and , “3D path planning in a dynamic environment using an octree and anartificial potential field”, Proceedings of the 1995 IEEE/RSJ International Conference on Human Robot Interaction and Cooperative Robotsapos, Pittsburgh, PA, , 1995, pp. 474481. ? [4] M. Dorigo, V. Maniezzo, and A. Colorni, “Ant system: optimization by a colony of cooperating agents”, IEEE Transactions on systems, Men and CybericsCPart B, 1996, 26(1) pp. 2941
教學(xué)課件相關(guān)推薦
鄂ICP備17016276號(hào)-1