Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation
This work addresses state estimation for legged robots, particularly in challenging slip-prone environments, representing an incremental improvement over existing methods.
The paper tackles the problem of state estimation in legged robots by addressing foot slip as a major source of error, proposing an attention-based neural-augmented Kalman filter that compensates for slip-induced errors, resulting in improved performance under slip-prone conditions.
In this letter, we propose an Attention-Based Neural-Augmented Kalman Filter (AttenNKF) for state estimation in legged robots. Foot slip is a major source of estimation error: when slip occurs, kinematic measurements violate the no-slip assumption and inject bias during the update step. Our objective is to estimate this slip-induced error and compensate for it. To this end, we augment an Invariant Extended Kalman Filter (InEKF) with a neural compensator that uses an attention mechanism to infer error conditioned on foot-slip severity and then applies this estimate as a post-update compensation to the InEKF state (i.e., after the filter update). The compensator is trained in a latent space, which aims to reduce sensitivity to raw input scales and encourages structured slip-conditioned compensations, while preserving the InEKF recursion. Experiments demonstrate improved performance compared to existing legged-robot state estimators, particularly under slip-prone conditions.