Real-Time Decision Making under Uncertainty of Self-localization Results
Real-Time Decision Making under Uncertainty of Self-localization Results
复制标题
自定位结果不确定下的实时决策
DOI：
10.1007/978-3-540-45135-8_33
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
T. Arai
中科院分区：
文献类型：
--
作者：
Takeshi Fukase;Yuichi Kobayashi;R. Ueda;T. Kawabe;T. Arai
针对四足机器人传感器和运动存在较大误差的情况，提出了一种实时决策方法。考虑到机器人位置的不确定性，采用动态规划（DP）离线规划的方法建立状态-动作映射。使用该地图，机器人可以立即决定最佳行动，最大限度地减少到达目标状态的时间。观察的数量也被最小化。我们压缩这个地图与矢量量化（VQ）的实施。利用最优动作与其他动作的差值作为VQ的失真度量，使最优性的总损失最小化。
In this paper, we present a real-time decision making method for a quadruped robot whose sensor and locomotion have large errors. We make a State-Action Map by off-line planning considering the uncertainty of the robot’s location with Dynamic Programming (DP). Using this map, the robot can immediately decide optimal action that minimizes the time to reach a target state at any state. The number of observation is also minimized. We compress this map for implementation with Vector Quantization (VQ). Using the differences of the values between the optimal action and others as distortion measure of VQ minimizes the total loss of optimality.