Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
The authors develop a Recurrent Convolutional Neural Network (RCNN) architecture to perform coarse attitude initialization of known, tumbling spacecraft using temporal sequences of LiDAR-derived depth projections. Resolving directional ambiguities caused by geometric symmetries, sensor degradation, and rapid rotation is a critical prerequisite for safe autonomous proximity operations and in-orbit servicing. Simulated across multiple spacecraft geometries, ranges, and spin rates, the recurrent framework consistently achieves higher convergence rates and lower attitude estimation errors than static, single-frame CNN baselines.
Temporal recurrence breaks the pose ambiguity bottleneck in autonomous docking, enabling reliable attitude initialization on tumbling, structurally symmetric spacecraft where conventional single-frame CNNs fail.
Accurate attitude estimation is essential for autonomous in-orbit servicing and proximity operations. This work proposes a Recurrent Convolutional Neural Network (RCNN) used in coarse attitude initialization of known, possibly tumbling spacecraft using LiDAR-derived depth images. By processing temporal sequences of 2D point-cloud projections, the RCNN effectively handles symmetries, occlusions, and degraded sensing. Simulations across various spacecraft geometries, angular velocities, and ranges show that the RCNN yields lower initialization errors and higher convergence rates than conventional CNN baseline within the adopted experimental framework, with performance varying across angular velocity conditions.