Results 61 to 70 of about 2,247,232 (285)

Mars terrain image classification using Cartesian genetic programming [PDF]

, 2012
Automatically classifying terrain such as rocks, sand and\ud gravel from images is a challenging machine vision problem.\ud In addition to human designed approaches, a great\ud deal of progress has been made using machine learning\ud techniques to ...
Förster, A., Leitner, J., Schmidhuber, J., Harding, S.   +3 more
core   +1 more source

Echinoderm‐Inspired Autonomy for Soft‐Legged Robots

Advanced Robotics Research, EarlyView.
Inspired by echinoderms, a modular soft robot achieves autonomous phototaxis without a central controller or explicit communication. Each limb independently adapts its actuation timing through local sensing and short‐term memory. Coordination emerges purely from physical interactions, demonstrating resilience to changes in morphology, environment, and ...
Harmannus A. H. Schomaker, Jelle de Vries, Johannes T. B. overvelde   +2 more
wiley   +1 more source

Research on DEM Based on Remote Sensing Classification Method in Loess Hilly Ravine Area

Shuitu baochi yanjiu, 2013
A land-cover classification method was put forward based on remote sensing image to solve the problem of low classification accuracy and lack of terrain characteristics due to the influence of complex terrain in Loess hilly Ravine area.This method uses ...
LI Xiao-man, WANG Gang
doaj  

Terrain Classification and Negotiation with a Walking Robot [PDF]

Journal of Intelligent & Robotic Systems, 2014
This paper describes a walking robot controller for negotiation of terrains with different traction characteristics. The feedback is based on three perception systems. The purpose of the presented research is to enhance the autonomy of the walking robot. The information about the class of the terrain allows the robot to work in the real world scenarios
openaire   +2 more sources

Compliant Pneumatic Feet with Real‐Time Stiffness Adaptation for Humanoid Locomotion

Advanced Robotics Research, EarlyView.
A compliant pneumatic foot with real‐time variable stiffness enables humanoid robots to adapt to changing terrains. Using onboard vision and pressure control, the foot modulates stiffness within each gait cycle, reducing impact forces and improving balance. The design, cast in soft silicone with embedded air chambers and Kevlar wrapping, offers durable,
Irene Frizza, Hiroshi Kaminaga, Philippe Fraisse, Gentiane Venture   +3 more
wiley   +1 more source

Improving Robot Mobility by Combining Downward-Looking and Frontal Cameras

Robotics, 2016
This paper presents a novel attempt to combine a downward-looking camera and a forward-looking camera for terrain classification in the field of off-road mobile robots. The first camera is employed to identify the terrain beneath the robot.
Ramon Gonzalez, Alejandro Rituerto, José J. Guerrero   +2 more
doaj   +1 more source

Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree

IEEE Access, 2020
Decision tree method has been applied to POLSAR image classification, due to its capability to interpret the scattering characteristics as well as good classification accuracy.
Qiang Yin, Jianda Cheng, Fan Zhang, Yongsheng Zhou, Luyi Shao, Wen Hong   +5 more
doaj   +1 more source

Optimum Pipeline for Visual Terrain Classification Using Improved Bag of Visual Words and Fusion Methods [PDF]

, 2017
We propose an optimum pipeline and develop the hybrid representation to produce an effective and efficient visual terrain classification system. The bag of visual words (BOVW) framework has emerged as a promising approach and effective paradigm for ...
Zihao Chen, Xudong Ren, Weihua Su, Hang Wu, Baozhen Liu, Jinggong Sun, Wenchang Zhang   +6 more
core   +1 more source

3D‐Printing Aided Rapid Prototyping of Pretensioned Tensegrity Structures for Robotic Applications

Advanced Robotics Research, EarlyView.
Printing, injection molding, and assembly (PMA) is a method for rapid prototyping mesoscale, topologically complex, and tensioned tensegrity structures. In combination with PMA method, two mold design strategies: modular mold and compact channel layout, enable efficiency and scalability for tensegrity fabrication.
Yi Sun, Jan Petrš, Omar Aloui, Dario Floreano   +3 more
wiley   +1 more source

Machine learning for automated avalanche terrain exposure scale (ATES) classification [PDF]

Natural Hazards and Earth System Sciences
Avalanche risk management is essential for backcountry safety. The Avalanche Terrain Exposure Scale (ATES) classifies mountain terrain based on its potential exposure to avalanche hazards and supports mountain visitors in their terrain assessment ...
K. Markov, K. Markov, A. Huber, A. Huber, M. Panayotov, M. Panayotov, M. Panayotov, C. Hesselbach, P. Spannring, J.-T. Fischer, M. Teich   +10 more
doaj   +1 more source