scholarly journals SURF-BRISK–Based Image Infilling Method for Terrain Classification of a Legged Robot

2019 ◽  
Vol 9 (9) ◽  
pp. 1779 ◽  
Author(s):  
Yaguang Zhu ◽  
Chaoyu Jia ◽  
Chao Ma ◽  
Qiong Liu
Keyword(s):  
Legged Robot ◽  
Terrain Classification ◽  
Walking Robot ◽  
Adaptive Locomotion ◽  
Speeded Up Robust Features ◽  
Pixel Image ◽  
Series Of Experiments ◽  
Multilegged Walking Robot ◽  
Local Image

In this study, we propose adaptive locomotion for an autonomous multilegged walking robot, an image infilling method for terrain classification based on a combination of speeded up robust features, and binary robust invariant scalable keypoints (SURF-BRISK). The terrain classifier is based on the bag-of-words (BoW) model and SURF-BRISK, both of which are fast and accurate. The image infilling method is used for identifying terrain with obstacles and mixed terrain; their features are magnified to help with recognition of different complex terrains. Local image infilling is used to improve low accuracy caused by obstacles and super-pixel image infilling is employed for mixed terrain. A series of experiments including classification of terrain with obstacles and mixed terrain were conducted and the obtained results show that the proposed method can accurately identify all terrain types and achieve adaptive locomotion.

scholarly journals Terrain classification and adaptive locomotion for a hexapod robot Qingzhui

2021 ◽  
Author(s):  
Yue Zhao ◽  
Feng Gao ◽  
Qiao Sun ◽  
Yunpeng Yin
Keyword(s):  
Legged Robots ◽  
Measurement Unit ◽  
Support Vector ◽  
Hexapod Robot ◽  
Terrain Classification ◽  
Adaptive Locomotion ◽  
Joint Torques ◽  
Active Compliance ◽  
Outdoor Environments ◽  
The Stability

AbstractLegged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays an important role in improving the stability of legged robots. A terrain classification and adaptive locomotion method for a hexapod robot named Qingzhui is proposed in this paper. First, a force-based terrain classification method is suggested. Ground contact force is calculated by collecting joint torques and inertial measurement unit information. Ground substrates are classified with the feature vector extracted from the collected data using the support vector machine algorithm. Then, an adaptive locomotion on different ground properties is proposed. The dynamic alternating tripod trotting gait is developed to control the robot, and the parameters of active compliance control change with the terrain. Finally, the method is integrated on a hexapod robot and tested by real experiments. Our method is shown effective for the hexapod robot to walk on concrete, wood, grass, and foam. The strategies and experimental results can be a valuable reference for other legged robots applied in outdoor environments.

scholarly journals Navigating by touch: haptic Monte Carlo localization via geometric sensing and terrain classification

2021 ◽  
Vol 45 (6) ◽  
pp. 843-857
Author(s):  
Russell Buchanan ◽  
Jakub Bednarek ◽  
Marco Camurri ◽  
Michał R. Nowicki ◽  
Krzysztof Walas ◽  
...  
Keyword(s):  
Monte Carlo ◽  
Estimation Error ◽  
Extreme Environments ◽  
Legged Robot ◽  
Terrain Classification ◽  
Localization Algorithm ◽  
Geometric Information ◽  
Contact Points ◽  
Monte Carlo Localization ◽  
Geometric Sensing

AbstractLegged robot navigation in extreme environments can hinder the use of cameras and lidar due to darkness, air obfuscation or sensor damage, whereas proprioceptive sensing will continue to work reliably. In this paper, we propose a purely proprioceptive localization algorithm which fuses information from both geometry and terrain type to localize a legged robot within a prior map. First, a terrain classifier computes the probability that a foot has stepped on a particular terrain class from sensed foot forces. Then, a Monte Carlo-based estimator fuses this terrain probability with the geometric information of the foot contact points. Results demonstrate this approach operating online and onboard an ANYmal B300 quadruped robot traversing several terrain courses with different geometries and terrain types over more than 1.2 km. The method keeps pose estimation error below 20 cm using a prior map with trained network and using sensing only from the feet, leg joints and IMU.

scholarly journals Terrain classification of ladar data over Haitian urban environments using a lower envelope follower and adaptive gradient operator

2010 ◽  
Author(s):  
Amy L. Neuenschwander ◽  
Melba M. Crawford ◽  
Lori A. Magruder ◽  
Christopher A. Weed ◽  
Richard Cannata ◽  
...  
Keyword(s):  
Urban Environments ◽  
Lower Envelope ◽  
Terrain Classification ◽  
Gradient Operator

scholarly journals 2A2-C06 Hopping motion of a 6-legged robot using CPG(Walking Robot)

2011 ◽  
Vol 2011 (0) ◽  
pp. _2A2-C06_1-_2A2-C06_2
Author(s):  
Masaaki Ikeda ◽  
Keigo Watanabe ◽  
Kiyotaka Izumi
Keyword(s):  
Legged Robot ◽  
Walking Robot

COMPARATIVE EVALUATION OF NEW OSTEOPLASTIC MATERIALS BASED ON THE RESULTS OF ACUTE TOXICITY STUDIES

2021 ◽  
Vol Special issue (2) ◽  
pp. 29-33
Author(s):  
А.N. Akbarov ◽  
◽  
N.S. Ziyadullaeva
Keyword(s):  
Bioactive Glass ◽  
Intraperitoneal Injection ◽  
Comparative Evaluation ◽  
Laboratory Animals ◽  
Toxic Substances ◽  
Series Of Experiments ◽  
Osteoplastic Material ◽  
Rats And Mice ◽  
Lethal Doses

Three series of experiments were carried out and lethal doses of the new osteoplastic material 47.5 V were determined by the intraperitoneal and intragastric injection of the material to laboratory animals. A comparative evaluation with Bioactive glass BG-1D was also carried out. It was found that the LD50of 47,5B was 4274.51:4770.58 mg/kg for intragastric injection and 2358.31:2895.65 mg/kg for intraperitoneal injection to rats. In animals getting Bioactive glass BG-1D, these indicators changed slightly, amounting to 3439.04:3810.53 mg/kg and 1732.77:2730.93 mg/kg, respectively. Thus, according to the classification of substances according to the degree of toxicity, these materials can be attributed to practically non-toxic substances (according to the results of intraperitoneal injection of the material suspension to rats and mice) and low-toxic substances (according to the results of intragastric injection of the material suspension to rats)

Terrain Classification of LiDAR Point Cloud Based on Multi-Scale Features and PointNet

2019 ◽  
Vol 56 (5) ◽  
pp. 052804
Author(s):  
赵中阳 Zhao Zhongyang ◽  
程英蕾 Cheng Yinglei ◽  
释小松 Shi Xiaosong ◽  
秦先祥 Qin Xianxiang ◽  
李鑫 Li Xin
Keyword(s):  
Point Cloud ◽  
Terrain Classification ◽  
Multi Scale

scholarly journals Bio-Inspired Adaptive Locomotion Control System for Online Adaptation of a Walking Robot on Complex Terrains

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 91587-91602 ◽  
Author(s):  
Potiwat Ngamkajornwiwat ◽  
Jettanan Homchanthanakul ◽  
Pitiwut Teerakittikul ◽  
Poramate Manoonpong
Keyword(s):  
Control System ◽  
Walking Robot ◽  
Locomotion Control ◽  
Adaptive Locomotion ◽  
Online Adaptation
Sign in / Sign up

Export Citation Format

Share Document