IONet: Learning to Cure the Curse of Drift in Inertial Odometry
Inertial sensors play a pivotal role in indoor localization, which in turn lays the foundation for pervasive personal applications. However, low-cost inertial sensors, as commonly found in smartphones, are plagued by bias and noise, which leads to unbounded growth in error when accelerations are dou...
| Päätekijät: | , , , |
|---|---|
| Aineistotyyppi: | Conference item |
| Julkaistu: |
Association for the Advancement of Artificial Intelligence
2018
|
| _version_ | 1826296814880423936 |
|---|---|
| author | Chen, C Lu, X Markham, A Trigoni, N |
| author_facet | Chen, C Lu, X Markham, A Trigoni, N |
| author_sort | Chen, C |
| collection | OXFORD |
| description | Inertial sensors play a pivotal role in indoor localization, which in turn lays the foundation for pervasive personal applications. However, low-cost inertial sensors, as commonly found in smartphones, are plagued by bias and noise, which leads to unbounded growth in error when accelerations are double integrated to obtain displacement. Small errors in state estimation propagate to make odometry virtually unusable in a matter of seconds. We propose to break the cycle of continuous integration, and instead segment inertial data into independent windows. The challenge becomes estimating the latent states of each window, such as velocity and orientation, as these are not directly observable from sensor data. We demonstrate how to formulate this as an optimization problem, and show how deep recurrent neural networks can yield highly accurate trajectories, outperforming state-of-the-art shallow techniques, on a wide range of tests and attachments. In particular, we demonstrate that IONet can generalize to estimate odometry for non-periodic motion, such as a shopping trolley or baby-stroller, an extremely challenging task for existing techniques. |
| first_indexed | 2024-03-07T04:22:08Z |
| format | Conference item |
| id | oxford-uuid:cb60db07-a31f-4971-a44a-b23cd311847d |
| institution | University of Oxford |
| last_indexed | 2024-03-07T04:22:08Z |
| publishDate | 2018 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | oxford-uuid:cb60db07-a31f-4971-a44a-b23cd311847d2022-03-27T07:14:23ZIONet: Learning to Cure the Curse of Drift in Inertial OdometryConference itemhttp://purl.org/coar/resource_type/c_5794uuid:cb60db07-a31f-4971-a44a-b23cd311847dSymplectic Elements at OxfordAssociation for the Advancement of Artificial Intelligence2018Chen, CLu, XMarkham, ATrigoni, NInertial sensors play a pivotal role in indoor localization, which in turn lays the foundation for pervasive personal applications. However, low-cost inertial sensors, as commonly found in smartphones, are plagued by bias and noise, which leads to unbounded growth in error when accelerations are double integrated to obtain displacement. Small errors in state estimation propagate to make odometry virtually unusable in a matter of seconds. We propose to break the cycle of continuous integration, and instead segment inertial data into independent windows. The challenge becomes estimating the latent states of each window, such as velocity and orientation, as these are not directly observable from sensor data. We demonstrate how to formulate this as an optimization problem, and show how deep recurrent neural networks can yield highly accurate trajectories, outperforming state-of-the-art shallow techniques, on a wide range of tests and attachments. In particular, we demonstrate that IONet can generalize to estimate odometry for non-periodic motion, such as a shopping trolley or baby-stroller, an extremely challenging task for existing techniques. |
| spellingShingle | Chen, C Lu, X Markham, A Trigoni, N IONet: Learning to Cure the Curse of Drift in Inertial Odometry |
| title | IONet: Learning to Cure the Curse of Drift in Inertial Odometry |
| title_full | IONet: Learning to Cure the Curse of Drift in Inertial Odometry |
| title_fullStr | IONet: Learning to Cure the Curse of Drift in Inertial Odometry |
| title_full_unstemmed | IONet: Learning to Cure the Curse of Drift in Inertial Odometry |
| title_short | IONet: Learning to Cure the Curse of Drift in Inertial Odometry |
| title_sort | ionet learning to cure the curse of drift in inertial odometry |
| work_keys_str_mv | AT chenc ionetlearningtocurethecurseofdriftininertialodometry AT lux ionetlearningtocurethecurseofdriftininertialodometry AT markhama ionetlearningtocurethecurseofdriftininertialodometry AT trigonin ionetlearningtocurethecurseofdriftininertialodometry |