基于不确定性分析的自主导航轨迹评测方法  

Autonomous Navigation Trajectory Evaluation Method Based on Uncertainty Analysis

作　　者：阎岩[1,2] 唐振民[2] 刘家银[2] 

机构地区：[1]中国运载火箭技术研究院研发中心,北京100076 [2]南京理工大学模式识别与人工智能研究所,江苏南京210094

出　　处：《机器人》2013年第2期194-199,共6页Robot

基　　金：国家自然科学基金重大研究计划重点资助项目(90820306)

摘　　要：为满足自主导航轨迹定性和定量评测要求,提出一种基于不确定性云模型的轨迹分析计算方法.该方法通过提取机器人自主行驶和避障行为中的运动轨迹特征,建立对应的方位偏离、方向偏差和避障安全距离轨迹特征云模型,以云模型的期望作为轨迹特征基本度量,以熵和超熵表达特征所具有的模糊性和随机性.利用云模型所具有的不确定性度量优势,反映系统自主导航过程中的瞬时状态和系统稳定性.实验结果表明,该方法能够有效评估自主导航系统轨迹数据,并能够弥补基于增强学习的方法无法直观反映系统评价稳定性的不足.In order to achieve qualitative and quantitative evaluation of autonomous navigation trajectory, a trajectory analysis method based on uncertainty cloud model is proposed. In this method, robot＇s trajectory features are extracted from autonomous driving and avoiding actions, and corresponding feature cloud models for position warp, direction warp and obstacle-avoidance safety distance trajectories are generated. In cloud model, expectation is the basic metric of trajectories, and the fuzziness and randonmess of features are expressed by entropy and hyper-entropy. By taking advantages of uncertainty metric of cloud models, the transient state and stability in autonomous navigation can be calculated. Experiment results show that this method can effectively be used in trajectory evaluation of autonomous navigation, and it can compensate shortcominzs of reinforcement learninz methods in stability evaluation.

关 键 词：轨迹评测 自主导航 不确定性分析 云模型 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]