Robot ground classification method and system in dynamic environment

Abstract

The invention discloses a robot ground classification method and system in a dynamic environment, which can realize real-time and accurate ground type prediction in the dynamic environment by utilizing a vibration signal, and mainly comprises six steps of signal acquisition and segmentation, feature extraction, classifier prediction, classification result correction, classifier updating and classification result output. The vibration view is divided into the time domain and the frequency domain, and a mutual learning mechanism is realized; the classification result is corrected by using the ground sequence time correlation, so that the precision of each domain classifier is improved; meanwhile, two mechanisms of external divergence and internal divergence are introduced, a new pseudo-labeling algorithm is designed, and the algorithm has great advantages in the aspects of extracting key samples and labeling; based on the pseudo-labeling algorithm, the robot can incrementally update theclassifiers of all domains on line, so that accurate and reliable ground classification in a dynamic environment is realized.

Description

technical field [0001] The invention relates to the field of robots, in particular to a ground classification method and system for robots in a dynamic environment. Background technique [0002] Autonomous mobile robots often need to traverse various terrains such as sand, grass, gravel or clay for field tasks. Some smooth, muddy or uneven terrain may pose a threat to the robot. For example, if a wheeled robot decides to walk across sand, its wheels might get stuck in the sand. As a result, robots can only move at extremely slow speeds, or even become trapped and lose mobility. To protect robots against such non-geometric threats, mobile robots must have terrain classification capabilities. Robotic terrain classification is the process by which a mobile robot classifies the terrain it is traversing or will traverse into some predefined class. In addition to avoiding non-geometric threats, many existing works have shown that accurate terrain classification methods can sig...

AI Technical Summary

Problems solved by technology

This phenomenon of concept drift often occurs in dynamic environments, so the classifier learned from the offline training dataset will be less predictive of the online input vibration samples

Images