Abstract
To improve the accuracy of terrain classification during mobile robot operation, an adaptive online terrain classification method based on vibration signals is proposed. First, the time domain and the combined features of the time, frequency, and time–frequency domains in the original vibration signal are extracted. These are adopted as the input of the random forest algorithm to generate classification models with different dimensions. Then, by judging the relationship between the current speed of the mobile robot and its critical speed, the classification model of different dimensions is adaptively selected for online classification. Offline and online experiments are conducted for four different terrains. The experimental results show that the proposed method can effectively avoid the self-vibration interference caused by an increase in the robot’s moving speed and achieve higher terrain classification accuracy.
Highlights
With the rapid development of mobile robot technology, various mobile robots have replaced humans to complete a broad range of dangerous tasks, for example, search and rescue robots, line-tracking robots, and detection robots
In addition to the adaptive boosting (AB) algorithm, the accuracy of the remaining integrated algorithms under the two feature models had improved significantly compared with the accuracy of the single algorithm, and the median line of the accuracy of the random forest (RF) algorithm was above 80%
This article proposed an adaptive online terrain classification method based on vibration signals
Summary
With the rapid development of mobile robot technology, various mobile robots have replaced humans to complete a broad range of dangerous tasks, for example, search and rescue robots, line-tracking robots, and detection robots. The interactive method completes terrain classification through sound and tactile and vibration signals generated by the interaction between the mobile robot and the ground.[3,4,5,6] When. In the system presented following feature extraction, the original vibration signal generated a data set including m samples. As the robot traversed different terrain types, the integrated three-axis direction accelerometer of the IMU sensed changes in vibration signals and returned real-time acceleration data. The experiment used data collected at 0.3 m/s by a mobile robot as a data source and employed the full and partial feature model to compare the accuracy of the classification algorithm.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
