Legged Robot State Estimation Using Invariant Neural-Augmented Kalman Filter with a Neural Compensator
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910002667585536 |
|---|---|
| author | Lee, Seokju Kim, Hyun-Bin Kim, Kyung-Soo |
| author_facet | Lee, Seokju Kim, Hyun-Bin Kim, Kyung-Soo |
| contents | This paper presents an algorithm to improve state estimation for legged robots. Among existing model-based state estimation methods for legged robots, the contact-aided invariant extended Kalman filter defines the state on a Lie group to preserve invariance, thereby significantly accelerating convergence. It achieves more accurate state estimation by leveraging contact information as measurements for the update step. However, when the model exhibits strong nonlinearity, the estimation accuracy decreases. Such nonlinearities can cause initial errors to accumulate and lead to large drifts over time. To address this issue, we propose compensating for errors by augmenting the Kalman filter with an artificial neural network serving as a nonlinear function approximator. Furthermore, we design this neural network to respect the Lie group structure to ensure invariance, resulting in our proposed Invariant Neural-Augmented Kalman Filter (InNKF). The proposed algorithm offers improved state estimation performance by combining the strengths of model-based and learning-based approaches. Project webpage: https://seokju-lee.github.io/innkf_webpage |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00344 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Legged Robot State Estimation Using Invariant Neural-Augmented Kalman Filter with a Neural Compensator Lee, Seokju Kim, Hyun-Bin Kim, Kyung-Soo Robotics This paper presents an algorithm to improve state estimation for legged robots. Among existing model-based state estimation methods for legged robots, the contact-aided invariant extended Kalman filter defines the state on a Lie group to preserve invariance, thereby significantly accelerating convergence. It achieves more accurate state estimation by leveraging contact information as measurements for the update step. However, when the model exhibits strong nonlinearity, the estimation accuracy decreases. Such nonlinearities can cause initial errors to accumulate and lead to large drifts over time. To address this issue, we propose compensating for errors by augmenting the Kalman filter with an artificial neural network serving as a nonlinear function approximator. Furthermore, we design this neural network to respect the Lie group structure to ensure invariance, resulting in our proposed Invariant Neural-Augmented Kalman Filter (InNKF). The proposed algorithm offers improved state estimation performance by combining the strengths of model-based and learning-based approaches. Project webpage: https://seokju-lee.github.io/innkf_webpage |
| title | Legged Robot State Estimation Using Invariant Neural-Augmented Kalman Filter with a Neural Compensator |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.00344 |