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

TL;DR

This paper introduces a two-stage framework for embedding and executing robotic trajectories on curved surfaces, improving stability and contact safety during surface-constrained manipulation tasks.

Contribution

It proposes a novel offline surface warping method combined with an online contact-aware projection for robust trajectory execution on complex geometries.

Findings

Enhanced geometric continuity over multiple surface types

Reduced orientation discontinuities during repeated cycles

Validated robustness on real robotic surface manipulation

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.