自动化学报2026，Vol.52Issue(3)：430-440,11.DOI:10.16383/j.aas.c250506
融合形态特征的基于GRU的介入机器人导丝轨迹预测建模
GRU-based Modeling for Predicting Guidewire Trajectories in Interventional Robotics With Morphological Feature Fusion
摘要
Abstract
We present a causality-preserving sequential estimator for guidewire trajectory reconstruction during in-terventional navigation.Unlike generic recurrent baselines,the proposed model time-broadcasts sequence-level con-stants(including guidewire stiffness,insertion angle,and an effective friction descriptor)and concatenates them with dynamic geometric tokens(centerline coordinates and local diameter)before a two-stage feature encoder and a unidirectional gated recurrent unit decoder that emits 2D positions stepwise.To cope with variable sequence lengths,we adopt a time-step length classification training strategy with mask-based loss function,which limits pad-ding-induced invalid gradients and improves training and inference efficiency without altering the network architec-ture.On a phantom platform covering multiple guidewire types and insertion angles,the method achieves a 0.40～0.54 mm position-error range(mean 0.46 mm)while preserving strict causality;relative to a baseline without the time-step classification strategy,it reduces epochs-to-convergence by 42%,training time by 52%,and per-inference latency by 51%.These results indicate a deployable,real-time basis for guidewire trajectory estimation and intraop-erative navigation.关键词
介入机器人/导丝轨迹预测/门控循环单元/形态特征融合/时序建模Key words
interventional robotics/guidewire trajectory prediction/gated recurrent unit/morphological feature fu-sion/sequential modeling引用本文复制引用
张任飞,董林杰,王兴松,田梦倩,苏浩波..融合形态特征的基于GRU的介入机器人导丝轨迹预测建模[J].自动化学报,2026,52(3):430-440,11.基金项目
国家自然科学基金(52175005)资助Supported by National Natural Science Foundation of China(52175005) （52175005）
