Zhitao Zhu

Mr. Zhitao Zhu

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
SLShunxiang Li
Shunxiang Li
KCKewei Chen
Kewei Chen
ZZZhitao Zhu
Zhitao Zhu
LGLyu Guangqiang
Lyu Guangqiang
This study presents a CAD-free bolt pose-estimation method for robotic tightening that uses a single structured-light point cloud and requires no bolt-specific 3D CAD during inference or deployment. After point-cloud filtering and DBSCAN extraction, relaxed geometric rules generate candidate bolt top faces. Each candidate is represented by 19 scale-normalized features plus within-set mean deviations and percentile ranks, forming a 57-dimensional contextual representation. A compact 1,922-parameter dual-head multilayer perceptron is trained with ListNet ranking and soft-target binary cross-entropy. On 310 independent test frames from held-out scenes and workpiece types, M3 achieved 96.77% success, compared with 94.52% for a PointNet scorer and 74.2% for handcrafted scoring. All ten M3 failures arose from missing acceptable proposals; no ranking failure occurred when a valid candidate was retained. The complete perception pipeline required 83.138 ms per frame. In 3,366 factory tightening operations, the deployed M3 system achieved 99.67% first-pass success, with one failure attributed to perception. The results show that contextual candidate ranking can provide interpretable and low-cost pose estimation while removing bolt-specific CAD from runtime inference.