变结构陆空机器人自主跨域越障技术研究  

Autonomous Cross-Domain Obstacle Negotiation Research of a Variable Structure Land-Air Robot

作　　者：王建中[1] 游玉 王鹤 WANG Jianzhong;YOU Yu;WANG He(School of Mechatronical Engineering,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学机电学院,北京100081

出　　处：《北京理工大学学报》2021年第8期840-846,共7页Transactions of Beijing Institute of Technology

基　　金：国家部委基础科研计划资助项目(JCKY2019602C015)。

摘　　要：陆空机器人因其灵活的机动能力而备受关注,为了更好地发挥陆空机器人的跨域越障特性,以变结构陆空机器人为平台,对深度图像进行二值化处理以提取前方障碍物的边缘轮廓,采用最小矩形匹配法对障碍物进行建模,获取障碍物的距离及高度信息.根据障碍物距离和高度的检测结果及平台地面移动越障极限,提出了一种自主跨域越障策略.试验结果表明,机器人可以准确检测判断出行驶前方障碍物的距离及高度信息并可以顺利自主跨域越障,到达目标点,提出的障碍物检测方法及自主跨域越障策略是有效的.Land and air robots have attracted much attention due to their flexible maneuverability.In order to better utilize the characteristic of cross-domain obstacle negotiation,based on the variable structure land-air robot,the depth image was binarized to extract the edge contour of the obstacle ahead,and the minimum rectangle matching method was used to model the obstacles to obtain the distance and height of the obstacles.Furthermore,the autonomous cross-domain obstacle negotiation strategy was proposed according to the obstacle detection results and obstacle negotiation performance of terrestrial locomotion.The experimental results demonstrate that the robot can detect the distance and height of the obstacles ahead accurately,and cross the obstacle to reach the target point autonomously.The obstacle detection method and autonomous cross-domain obstacle negotiation strategy proposed in this paper are effective.

关 键 词：变结构陆空机器人 深度相机 障碍物检测 自主跨域越障 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]