控制理论与应用
控製理論與應用
공제이론여응용
CONTROL THEORY & APPLICATIONS
2010年
1期
111-115
,共5页
乔俊飞%樊瑞元%韩红桂%阮晓钢
喬俊飛%樊瑞元%韓紅桂%阮曉鋼
교준비%번서원%한홍계%원효강
移动机器人%导航%动态神经网络
移動機器人%導航%動態神經網絡
이동궤기인%도항%동태신경망락
mobile robot%navigation%dynamically structured neural network
针对Pioneer3-DX移动机器人,提出了基于强化学习的自主导航策略,完成了基于动态神经网络的移动机器人导航算法设计.动态神经网络可以根据机器人环境状态的复杂程度自动地调整其结构,实时地实现机器人的状态与其导航动作之间的映射关系,有效地解决了强化学习中状态变量表的维数爆炸问题.通过对Pioneer3-DX移动机器人导航进行仿真和实物实验,证明该方法的有效性,且导航效果明显优于人工势场法.
針對Pioneer3-DX移動機器人,提齣瞭基于彊化學習的自主導航策略,完成瞭基于動態神經網絡的移動機器人導航算法設計.動態神經網絡可以根據機器人環境狀態的複雜程度自動地調整其結構,實時地實現機器人的狀態與其導航動作之間的映射關繫,有效地解決瞭彊化學習中狀態變量錶的維數爆炸問題.通過對Pioneer3-DX移動機器人導航進行倣真和實物實驗,證明該方法的有效性,且導航效果明顯優于人工勢場法.
침대Pioneer3-DX이동궤기인,제출료기우강화학습적자주도항책략,완성료기우동태신경망락적이동궤기인도항산법설계.동태신경망락가이근거궤기인배경상태적복잡정도자동지조정기결구,실시지실현궤기인적상태여기도항동작지간적영사관계,유효지해결료강화학습중상태변량표적유수폭작문제.통과대Pioneer3-DX이동궤기인도항진행방진화실물실험,증명해방법적유효성,차도항효과명현우우인공세장법.
For the navigation of Pioneer3-DX mobile robot in unknown environment, we propose a self-navigation strategy with learning reinforcement, and develop the navigation algorithm based on the dynamical neural network. The dynamically self-organizing neural network can automatically adjust its structure according to the complexity of the work-ing environments of the mobile robot to realize the mapping between environmental states and robot actions, effectively avoiding the dimension explosion in learning reinforcement. Simulations and real robot navigation experiments are carried out; results show that the proposed method is effective in applications. It gives a better navigation performance than that of the artificial potential-field method.