Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot

Sensors

Qiong Liu¹  Chao Ma¹  Kailu Luo¹  Yaguang Zhu¹  Bo Jin² 

[1] Key Laboratory of Road Construction Technology and Equipment of MOE, Chang’an University, Xi’an 710064, China;State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310028, China;

关键词: boundary information;    legged robot;    superpixel segmentation;    terrain classification;   

DOI  :  10.3390/s18092808

来源: DOAJ

【 摘 要 】

In view of terrain classification of the autonomous multi-legged walking robots, two synthetic classification methods for terrain classification, Simple Linear Iterative Clustering based Support Vector Machine (SLIC-SVM) and Simple Linear Iterative Clustering based SegNet (SLIC-SegNet), are proposed. SLIC-SVM is proposed to solve the problem that the SVM can only output a single terrain label and fails to identify the mixed terrain. The SLIC-SegNet single-input multi-output terrain classification model is derived to improve the applicability of the terrain classifier. Since terrain classification results of high quality for legged robot use are hard to gain, the SLIC-SegNet obtains the satisfied information without too much effort. A series of experiments on regular terrain, irregular terrain and mixed terrain were conducted to present that both superpixel segmentation based synthetic classification methods can supply reliable mixed terrain classification result with clear boundary information and will put the terrain depending gait selection and path planning of the multi-legged robots into practice.

【 授权许可】

Unknown