Surface-Constrained Offline Warping with Contact-Aware Online Pose Projection for Safe Robotic Trajectory Execution

arXiv cs.RO / 3/31/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

Key Points

  • The paper addresses failures of reusing nominal motion primitives on curved surfaces, where direct tiling can cause interpenetration, orientation discontinuities, and cumulative drift over repeated execution cycles.
  • It proposes a two-stage framework that decouples offline geometric embedding from online execution regulation by first warping a periodic primitive onto curved surfaces using asymmetric diffeomorphic deformation and axis-consistent orientation completion.
  • For the online stage, it introduces a contact-aware projection operator that constrains deviation from the warped reference trajectory using FSR-driven disturbance adaptation and a conic orientation safety constraint.
  • Experiments on multiple analytic surface families and real-robot tests on a sinusoidal surface show improved geometric continuity, fewer large orientation jumps, and more robust contact maintenance than direct tiling approaches.
  • The authors conclude that stable, repeatable surface-embedded trajectory execution is achievable using lightweight online projection under limited sensor feedback by separating remapping from regulation.

Abstract

Robotic manipulation tasks that require repeated tool motion along curved surfaces frequently arise in surface finishing, inspection, and guided interaction. In practice, nominal motion primitives are often designed independently of the deployment surface and later reused across varying geometries. Directly tiling such primitives onto nonplanar surfaces introduces geometric inconsistencies, leading to interpenetration, orientation discontinuities, and cumulative drift over repeated cycles. We present a two-stage framework that separates geometric embedding from execution-level regulation. An offline surface-constrained warping operator embeds a nominal periodic primitive onto curved surfaces through asymmetric diffeomorphic deformation of dual-track waypoints and axis-consistent orientation completion, producing a surface-adapted reference trajectory. An online contact-aware projection operator then enforces bounded deviation relative to this reference using FSR-driven disturbance adaptation and a conic orientation safety constraint. Experiments across multiple analytic surface families and real-robot validation on a sinusoidal surface demonstrate improved geometric continuity, reduced large orientation jumps, and robust contact maintenance compared with direct tiling. These results show that decoupling offline geometric remapping from lightweight online projection enables stable and repeatable surface-embedded trajectory execution under sensor-lite feedbacks.