Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.05254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914671019163648 |
|---|---|
| author | Agrawal, Devansh R Govindjee, Rajiv Yu, Jiangbo Ravikumar, Anurekha Panagou, Dimitra |
| author_facet | Agrawal, Devansh R Govindjee, Rajiv Yu, Jiangbo Ravikumar, Anurekha Panagou, Dimitra |
| contents | This paper proposes two new algorithms for certified perception in safety-critical robotic applications. The first is a Certified Visual Odometry algorithm, which uses a RGBD camera with bounded sensor noise to construct a visual odometry estimate with provable error bounds. The second is a Certified Mapping algorithm which, using the same RGBD images, constructs a Signed Distance Field of the obstacle environment, always safely underestimating the distance to the nearest obstacle. This is required to avoid errors due to VO drift. The algorithms are demonstrated in hardware experiments, where we demonstrate both running online at 30FPS. The methods are also compared to state-of-the-art techniques for odometry and mapping. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05254 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Online and Certifiably Correct Visual Odometry and Mapping Agrawal, Devansh R Govindjee, Rajiv Yu, Jiangbo Ravikumar, Anurekha Panagou, Dimitra Robotics Systems and Control This paper proposes two new algorithms for certified perception in safety-critical robotic applications. The first is a Certified Visual Odometry algorithm, which uses a RGBD camera with bounded sensor noise to construct a visual odometry estimate with provable error bounds. The second is a Certified Mapping algorithm which, using the same RGBD images, constructs a Signed Distance Field of the obstacle environment, always safely underestimating the distance to the nearest obstacle. This is required to avoid errors due to VO drift. The algorithms are demonstrated in hardware experiments, where we demonstrate both running online at 30FPS. The methods are also compared to state-of-the-art techniques for odometry and mapping. |
| title | Online and Certifiably Correct Visual Odometry and Mapping |
| topic | Robotics Systems and Control |
| url | https://arxiv.org/abs/2402.05254 |