Self-Supervised Sensor Learning and Its Application: Building 3D Semantic Maps Using Terrain Classification

Chuho Yi; Donghui Song; Jungwon Cho

doi:10.1155/2014/394942

Vibration-based Terrain Classification for Mobile Robots Using Support Vector Machine

ROBOT ◽

10.3724/sp.j.1218.2012.00660 ◽

2012 ◽

Vol 34 (6) ◽

pp. 660 ◽

Cited By ~ 2

Author(s):

Qiang LI ◽

Kai XUE ◽

He XU ◽

Wenlin PAN ◽

Tianlong WANG

Keyword(s):

Support Vector Machine ◽

Mobile Robots ◽

Support Vector ◽

Terrain Classification

Download Full-text

Semantic Mapping for Mobile Robots in Indoor Scenes: A Survey

Information ◽

10.3390/info12020092 ◽

2021 ◽

Vol 12 (2) ◽

pp. 92

Author(s):

Xiaoning Han ◽

Shuailong Li ◽

Xiaohui Wang ◽

Weijia Zhou

Keyword(s):

Mobile Robots ◽

Semantic Information ◽

Semantic Mapping ◽

Human Beings ◽

Future Directions ◽

Essential Requirement ◽

Semantic Map ◽

Semantic Maps ◽

Great Progress ◽

Indoor Scenes

Sensing and mapping its surroundings is an essential requirement for a mobile robot. Geometric maps endow robots with the capacity of basic tasks, e.g., navigation. To co-exist with human beings in indoor scenes, the need to attach semantic information to a geometric map, which is called a semantic map, has been realized in the last two decades. A semantic map can help robots to behave in human rules, plan and perform advanced tasks, and communicate with humans on the conceptual level. This survey reviews methods about semantic mapping in indoor scenes. To begin with, we answered the question, what is a semantic map for mobile robots, by its definitions. After that, we reviewed works about each of the three modules of semantic mapping, i.e., spatial mapping, acquisition of semantic information, and map representation, respectively. Finally, though great progress has been made, there is a long way to implement semantic maps in advanced tasks for robots, thus challenges and potential future directions are discussed before a conclusion at last.

Download Full-text

Terrain classification and adaptive locomotion for a hexapod robot Qingzhui

Frontiers of Mechanical Engineering ◽

10.1007/s11465-020-0623-1 ◽

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.

Download Full-text

A test of airborne, side-looking synthetic-aperture radar in central Newfoundland for geological reconnaissance

Canadian Journal of Earth Sciences ◽

10.1139/e91-025 ◽

1991 ◽

Vol 28 (2) ◽

pp. 257-265 ◽

Cited By ~ 14

Author(s):

D. F. Graham ◽

D. R. Grant

Keyword(s):

Surface Roughness ◽

Synthetic Aperture Radar ◽

Three Dimensional ◽

Synthetic Aperture ◽

Structural Elements ◽

Terrain Classification ◽

Regional Trends ◽

Valuable Complement ◽

Wide Swath ◽

Aperture Radar

Side-looking, C-band synthetic-aperture radar (SAR) penetrates cloud and fog, and operates day or night, to produce pseudo-three-dimensional terrain images with enhanced topography and surface roughness. The images, which have a 20 m resolution and cover large areas, have been used to map the regional trends, patterns of lineaments, and terrain types over a 6200 km2 area of complex lithology, structure, and drift cover. Four lineament classes are differentiated. Glacial trends are clear, and bedrock structures (faults, fractures, joints, foliation, and folded bedding) with relief expression at the surface show through the drift as lineaments. They accurately reproduce most known features when compared with bedrock and Quatenary geology maps. Hitherto unrecognized structural elements are revealed. Tones and textures reflect minute surface roughness variations useful in terrain classification. SAR wide-swath-mode imagery is thus a valuable complement to aerial photography, and is superior in revealing hummocky moraine, ribbed moraine, boulder fields and stony till. Wider use of this imagery is encouraged.

Download Full-text

An entropy minimization principle for semi-supervised terrain classification

Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101) ◽

10.1109/icip.2000.899370 ◽

2002 ◽

Cited By ~ 5

Author(s):

A. Guerrero-Curieses ◽

J. Cid-Sueiro

Keyword(s):

Terrain Classification ◽

Minimization Principle ◽

Entropy Minimization

Download Full-text

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

Autonomous Robots ◽

10.1007/s10514-021-10013-w ◽

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.

Download Full-text

The use of thesauri in online retrieval

Journal of Information Science ◽

10.1177/016555158400800204 ◽

1984 ◽

Vol 8 (2) ◽

pp. 63-66 ◽

Cited By ~ 8

Author(s):

C.P.R. Dubois

Keyword(s):

Information Retrieval ◽

Data Base ◽

Case Studies ◽

Controlled Vocabulary ◽

Free Text ◽

Data Bases ◽

Online Data ◽

Controlled Vocabularies ◽

Semantic Maps ◽

Actual Use

The controlled vocabulary versus the free text approach to information retrieval is reviewed from the mid 1960s to the early 1980s. The dominance of the free text approach following the Cranfield tests is increasingly coming into question as a result of tests on existing online data bases and case studies. This is supported by two case studies on the Coffeeline data base. The differences and values of the two approaches are explored considering thesauri as semantic maps. It is suggested that the most appropriate evaluatory technique for indexing languages is to study the actual use made of various techniques in a wide variety of search environments. Such research is becoming more urgent. Economic and other reasons for the scarcity of online thesauri are reviewed and suggestions are made for methods to secure revenue from thesaurus display facilities. Finally, the promising outlook for renewed develop ment of controlled vocabularies with more effective online display techniques is mentioned, although such development must be based on firm research of user behaviour and needs.

Download Full-text