Lightweight odometry plus reduced map-registration frequency cuts lidar localization compute by 27-91% while holding state-of-the-art accuracy on >100 km of real-world driving data.
Full STEAM Ahead: Exactly Sparse Gaussian Process Regression for Batch Continuous-Time Trajectory Estimation on SE(3),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Balancing Act: Trading Off Odometry and Map Registration for Efficient Lidar Localization
Lightweight odometry plus reduced map-registration frequency cuts lidar localization compute by 27-91% while holding state-of-the-art accuracy on >100 km of real-world driving data.