【摘要】：靈巧手操作是極具挑戰(zhàn)的機(jī)器人控制任務(wù)之一,并且至今仍存在大量問題尚未解決。本文針對(duì)機(jī)器人靈巧手操作中抓取任務(wù),以實(shí)際Baxter機(jī)器人為平臺(tái),實(shí)現(xiàn)了一套完整的抓取控制系統(tǒng),能夠高效、自適應(yīng)的控制機(jī)械臂到達(dá)指定目標(biāo)位置和跟隨指定關(guān)節(jié)位置軌跡兩個(gè)目標(biāo),并進(jìn)行實(shí)驗(yàn)驗(yàn)證。本文主要的工作有如下幾個(gè)方面。針對(duì)抓取場(chǎng)景下目標(biāo)跟蹤問題,完成引入結(jié)構(gòu)化約束的跟蹤算法設(shè)計(jì)。跟蹤算法作為控制系統(tǒng)在運(yùn)行時(shí)的輔助模塊,為控制系統(tǒng)提供的目標(biāo)定位以及目標(biāo)形態(tài)信息。改進(jìn)后視覺跟蹤算法,提升了機(jī)器人操作場(chǎng)景中,快速移動(dòng)、光照變化、形變等問題的跟蹤效果。算法結(jié)合TLD算法框架,利用提出的交叉骨架模型和軟分割模型,開拓被跟蹤目標(biāo)的結(jié)構(gòu)信息和外貌信息。跟蹤算法測(cè)試于權(quán)威數(shù)據(jù)視覺跟蹤數(shù)據(jù)庫(kù),對(duì)比近年優(yōu)秀的跟蹤器,并獲得了不錯(cuò)的成績(jī)。針對(duì)直接訓(xùn)練神經(jīng)網(wǎng)絡(luò)策略樣本需求量大的問題,利用構(gòu)建局部控制器結(jié)合監(jiān)督學(xué)習(xí)技術(shù)訓(xùn)練神經(jīng)網(wǎng)絡(luò)策略。本文將操作任務(wù)劃分為數(shù)個(gè)簡(jiǎn)單狀態(tài),在簡(jiǎn)單狀態(tài)下,利用基于模型的傳統(tǒng)控制算法或高效的增強(qiáng)學(xué)習(xí)算法,完成局部控制器的訓(xùn)練。在得到能夠在各自獨(dú)立的簡(jiǎn)單狀態(tài)下完成任務(wù)的局部控制器后,利用成熟的監(jiān)督學(xué)習(xí)技術(shù),將多個(gè)局部控制器整合訓(xùn)練為一個(gè)全局策略。全局策略保證機(jī)器人能夠以統(tǒng)一的控制器完成整個(gè)操作任務(wù),而非機(jī)器人在每個(gè)狀態(tài)下使用不同的控制器完成任務(wù)。本文第三個(gè)重要工作就是以實(shí)際Baxter機(jī)器人為平臺(tái),實(shí)現(xiàn)實(shí)際的抓取控制系統(tǒng)�？刂扑惴ǖ姆抡鎸�(shí)現(xiàn)往往較為容易,而從仿真到現(xiàn)實(shí)世界則存在一條巨大的鴻溝。因?yàn)樵诜抡姝h(huán)境中,可以忽略現(xiàn)實(shí)世界中各種干擾因素,例如數(shù)據(jù)采集時(shí)的測(cè)量誤差、系統(tǒng)誤差、執(zhí)行器執(zhí)行精度、控制系統(tǒng)的模型差異、采樣的成本等。此外,真實(shí)系統(tǒng)上需要一套完整的系統(tǒng)提供算法運(yùn)行的基礎(chǔ)。上述任一問題未能處理得當(dāng),都足以使得整個(gè)算法在實(shí)際系統(tǒng)中失敗。本文最后,在實(shí)際抓取控制系統(tǒng)中完成兩組控制任務(wù)實(shí)驗(yàn)驗(yàn)證。分別對(duì)局部控制器和全局策略進(jìn)行測(cè)試,不同次數(shù)迭代的執(zhí)行誤差,以實(shí)驗(yàn)結(jié)果來證實(shí)整個(gè)系統(tǒng)的可用性。實(shí)驗(yàn)數(shù)據(jù)也充分展示了,控制系統(tǒng)的可靠性,為數(shù)不多的迭代次數(shù)下,即可獲得較為理想的執(zhí)行結(jié)果。
[Abstract]:Dexterous hand manipulation is one of the most challenging tasks for robot control, and a large number of problems remain unsolved. In this paper, aiming at grasping task of robot dexterous hand, taking actual Baxter robot as the platform, a complete grab control system is realized, which can be highly efficient. The adaptive control manipulator reaches the specified target position and follows the specified joint position trajectory, and the experimental results are verified. The main work of this paper is as follows. Aiming at the target tracking problem in grab scenario, the tracking algorithm with structured constraints is designed. As the auxiliary module of the control system, the tracking algorithm provides the target location and the target shape information for the control system. The improved visual tracking algorithm improves the tracking effect of robot operation scene, such as fast moving, illumination change, deformation and so on. The algorithm combines the TLD algorithm framework with the proposed cross-skeleton model and soft segmentation model to exploit the structure and appearance information of the target being tracked. The tracking algorithm is tested in the authoritative data visual tracking database, compared with the excellent tracker in recent years, and achieved good results. In order to solve the problem of large demand for direct training neural network strategies, a local controller combined with supervised learning technology is used to train neural network strategies. In this paper, the operation task is divided into several simple states. In the simple state, the local controller is trained by using the traditional model-based control algorithm or the efficient reinforcement learning algorithm. After obtaining the local controller which can complete the task independently and simply, the local controller can be integrated into a global strategy by using the mature supervised learning technology. The global strategy ensures that the robot can complete the whole task with a unified controller instead of using a different controller to complete the task in each state. The third important work of this paper is to realize the actual grab control system based on the actual Baxter robot. The simulation of control algorithm is always easy, but there is a huge gap between simulation and real world. In the simulation environment, we can ignore all kinds of interference factors in the real world, such as measurement error, system error, executive precision of actuator, model difference of control system, cost of sampling and so on. In addition, the real system needs a complete set of systems to provide the basis for the algorithm to run. Any of the above problems can not be handled properly enough to make the whole algorithm fail in the real system. Finally, two groups of control tasks are verified in the actual grab control system. The local controller and the global strategy are tested, and the error of different iterations is obtained to verify the usability of the whole system. The experimental data also fully show that the reliability of the control system and the few iterations can obtain more satisfactory results.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP242

【參考文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 李昊;非剛性目標(biāo)的跟蹤-學(xué)習(xí)-檢測(cè)算法研究[D];電子科技大學(xué);2015年

，

本文編號(hào)：2192781