Push-Wiper：迈向基于分段推送轨迹的多污渍与表面通用机器人清洁

摘要

粘性污渍因其高粘度及复杂的流变特性，一直是机器人表面清洁面临的重大挑战。传统擦拭方式往往导致污渍扩散，而刷洗方式虽能提供更强的摩擦力，却存在损伤表面的风险。本文提出Push-Wiper框架，将粘性污渍清洁重新定义为聚集问题。Push-Wiper利用海绵通过分段推挤轨迹逐步聚集污渍，随后进入后处理阶段，将聚集的污渍脱离并实现海绵自清洁。我们采用逐步策略完成污渍聚集，并利用扩散策略（Diffusion Policy）生成自适应推挤动作序列。这些序列通过我们提出的任意表面姿态插值器（ASPI）与力-位混合控制器执行，使该方法能够泛化至空间分布多样的污渍。Push-Wiper的清洁评分（CS，定义为被去除污渍面积的百分比）较基线方法最高提升130%。在无需额外训练的情况下，Push-Wiper还能以零样本方式迁移至固体残留物、液体溢出物、未见过的粘性污渍以及不同几何形状的曲面。实验结果表明，Push-Wiper具备良好的清洁效果和强大的泛化能力。项目网站：https://push-wiper.github.io/。

English

Viscous stains, characterized by high viscosity and complex rheological properties, remain a major challenge for robotic surface cleaning. Conventional wiping often spreads the stain, while scrubbing provides stronger friction but risks damaging the surface. In this paper, we propose Push-Wiper, a framework that reformulates viscous stain cleaning as an aggregation problem. Push-Wiper employs a sponge to progressively gather stains through segmented pushing trajectories, followed by a post-processing phase that detaches the aggregated material and enables sponge self-cleaning. We adopt a stepwise strategy for stain gathering and leverage Diffusion Policy to generate adaptive pushing action sequences. These sequences are executed through our Arbitrary Surface Pose Interpolator (ASPI) and a hybrid force-position controller, allowing the method to generalize to stains with diverse spatial distributions. Push-Wiper achieves a cleaning score (CS), defined as the percentage of stain area removed, up to 130% higher than baseline methods. Without additional training, Push-Wiper also transfers in a zero-shot manner to solid residues, liquid spills, unseen viscous stains, and curved surfaces with varying geometries. Our experiments demonstrate the cleaning effectiveness of Push-Wiper and its strong generalization ability. The project website is available at https://push-wiper.github.io/.