Search papers, labs, and topics across Lattice.
This paper introduces TACO, a tightly-coupled IMU + fine-grained Cross-View Geo-localisation (CVGL) pipeline that relies on a single initial GNSS reading and then operates solely on onboard sensing. TACO uses a closed-form cross-track error model to trigger CVGL before IMU drift becomes excessive, along with a forward-biased multi-crop search to maintain constant inference cost. Results on the KITTI dataset demonstrate a 5.9x reduction in median Absolute Trajectory Error compared to IMU-only, achieving 16.3m ATE.
Ditch the GPS: This CVGL pipeline achieves a 5.9x improvement in localization accuracy over IMU-only by intelligently fusing satellite imagery with inertial measurements, needing only a single initial GPS fix.
Cross-View Geo-localisation (CVGL) matches ground imagery against satellite tiles to give absolute position fixes, an alternative to GNSS where signals are occluded, jammed, or spoofed. Recent fine-grained CVGL methods regress sub-tile metric pose, but have only been evaluated as one-shot localisers, never as the primary fix in a live pipeline. Inertial sensing provides high-rate relative motion, but accumulates unbounded drift without an absolute anchor. We propose TACO, a tightly-coupled IMU + fine-grained CVGL pipeline that consumes a single GNSS reading at start-up and thereafter operates on onboard sensing alone. A closed-form cross-track error model triggers CVGL before IMU drift exceeds the matcher's capture radius, and a forward-biased five-point multi-crop search keeps inference cost fixed at five forward passes per fix. A yaw-residual gate rejects fixes that disagree with the onboard compass, and an anisotropic body-frame noise model scales each Unscented Kalman Filter update by per-fix confidence. A factor graph with vetted loop closures provides an offline smoothed trajectory. On the KITTI raw dataset, TACO reduces median Absolute Trajectory Error (ATE) from 97.0m (IMU-only) to 16.3m, a 5.9 times reduction, at<0.1 ms per-frame fusion cost and a 5-10% camera duty cycle. Code is available: github.com/tavisshore/TACO.
