Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures
The exploration of remote, unknown, rough environments by autonomous robots strongly depends on the ability of the on-board system to build an accurate predictor of terrain traversability. Terrain traversability prediction can be made more cost efficient by using texture information of 2D images obt...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/4/1195 |
| _version_ | 1818298673523589120 |
|---|---|
| author | Mohammed Abdessamad Bekhti Yuichi Kobayashi |
| author_facet | Mohammed Abdessamad Bekhti Yuichi Kobayashi |
| author_sort | Mohammed Abdessamad Bekhti |
| collection | DOAJ |
| description | The exploration of remote, unknown, rough environments by autonomous robots strongly depends on the ability of the on-board system to build an accurate predictor of terrain traversability. Terrain traversability prediction can be made more cost efficient by using texture information of 2D images obtained by a monocular camera. In cases where the robot is required to operate on a variety of terrains, it is important to consider that terrains sometimes contain spiky objects that appear as non-uniform in the texture of terrain images. This paper presents an approach to estimate the terrain traversability cost based on terrain non-uniformity detection (TNUD). Terrain images undergo a multiscale analysis to determine whether a terrain is uniform or non-uniform. Terrains are represented using a texture and a motion feature computed from terrain images and acceleration signal, respectively. Both features are then combined to learn independent Gaussian Process (GP) predictors, and consequently, predict vibrations using only image texture features. The proposed approach outperforms conventional methods relying only on image features without utilizing TNUD. |
| first_indexed | 2024-12-13T04:39:04Z |
| format | Article |
| id | doaj.art-17f48c8365ec4103afd61dbf8032c1f6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-13T04:39:04Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-17f48c8365ec4103afd61dbf8032c1f62022-12-21T23:59:22ZengMDPI AGApplied Sciences2076-34172020-02-01104119510.3390/app10041195app10041195Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image TexturesMohammed Abdessamad Bekhti0Yuichi Kobayashi1Department of Information Science and Technology, Graduate School of Science and Technology, Shizuoka University, Shizuoka 432-8561, JapanDepartment of Mechanical Engineering, Faculty of Engineering, Shizuoka University, Shizuoka 432-8561, JapanThe exploration of remote, unknown, rough environments by autonomous robots strongly depends on the ability of the on-board system to build an accurate predictor of terrain traversability. Terrain traversability prediction can be made more cost efficient by using texture information of 2D images obtained by a monocular camera. In cases where the robot is required to operate on a variety of terrains, it is important to consider that terrains sometimes contain spiky objects that appear as non-uniform in the texture of terrain images. This paper presents an approach to estimate the terrain traversability cost based on terrain non-uniformity detection (TNUD). Terrain images undergo a multiscale analysis to determine whether a terrain is uniform or non-uniform. Terrains are represented using a texture and a motion feature computed from terrain images and acceleration signal, respectively. Both features are then combined to learn independent Gaussian Process (GP) predictors, and consequently, predict vibrations using only image texture features. The proposed approach outperforms conventional methods relying only on image features without utilizing TNUD.https://www.mdpi.com/2076-3417/10/4/1195terrain traversability cost predictionunknown environmentsterrain non-uniformity detectionimage texture informationvibration informationgaussian process regression |
| spellingShingle | Mohammed Abdessamad Bekhti Yuichi Kobayashi Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures Applied Sciences terrain traversability cost prediction unknown environments terrain non-uniformity detection image texture information vibration information gaussian process regression |
| title | Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures |
| title_full | Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures |
| title_fullStr | Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures |
| title_full_unstemmed | Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures |
| title_short | Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures |
| title_sort | regressed terrain traversability cost for autonomous navigation based on image textures |
| topic | terrain traversability cost prediction unknown environments terrain non-uniformity detection image texture information vibration information gaussian process regression |
| url | https://www.mdpi.com/2076-3417/10/4/1195 |
| work_keys_str_mv | AT mohammedabdessamadbekhti regressedterraintraversabilitycostforautonomousnavigationbasedonimagetextures AT yuichikobayashi regressedterraintraversabilitycostforautonomousnavigationbasedonimagetextures |