AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks

Morui Zhu, Yongqi Zhu, Song Fu, Qing Yang

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Camera Cross-Attention (CCA) (ablation)dCAP · STT4AT trailer posetranslation error ΔT: 0.632 -> 0.505Improved
add Camera Temporal Self-Attention (CTA) (ablation)dCAP · STT4AT trailer posetranslation error ΔT: 0.632 -> 0.452Improved
add both CCA and CTA (ablation)dCAP · STT4AT trailer poseRRA: 0.073 -> 0.042Improved
add CTA on top of CCA (ablation)dCAP · STT4AT trailer posetranslation error ΔT: 0.505 -> 0.452Improved
add CCA on top of CTA (ablation)dCAP · STT4AT trailer poseRRA: 0.058 -> 0.042Improved
add both CCA and CTA (ablation)dCAP + BEVFormer · STT4AT 3D detection (BEVFormer)AP: 0.084 -> 0.103Improved
add CCA alone (ablation)dCAP + BEVFormer · STT4AT 3D detection (BEVFormer)AP: 0.084 -> 0.102Improved
replace static calibration with dCAP predicted extrinsicsBEVFormer · STT4AT 3D detection (BEVFormer)AP: 0.058 -> 0.103Improved
add CTA vs CCA in high-articulation Roundabout (ablation)dCAP · STT4AT detection (Roundabout)mAP: 0.0324 -> 0.0397Improved
add CCA vs CTA in low-articulation Multi-Turn (ablation)dCAP · STT4AT detection (Multi-Turn)mAP: 0.0473 -> 0.0496Improved
add CCA vs CTA in Straight (ablation)dCAP · STT4AT detection (Straight)mAP: 0.0497 -> 0.0549Improved
add CTA vs CCA in U-turn pose estimation (ablation)dCAP · STT4AT pose (U-turn)translation error ΔT: 1.117 -> 0.706Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy