[论文解读] Learning Bimanual Scooping Policies for Food Acquisition

Jennifer Grannen, Yilin Wu+2 more|arXiv (Cornell University)|Nov 26, 2022

Soft Robotics and Applications被引用 9

一句话总结

本文提出CARBS，一种基于闭环视觉反馈和自适应稳定性的双臂机器人舀取策略，可有效减少在获取各类易碎、可变形食物时的食物破损。通过学习风险分类器与故障分类器以动态调整推杆与舀勺之间的距离，CARBS在刚性食物上实现了87.0%的成功率，相较于分析基线减少16.2%的破损率。

ABSTRACT

A robotic feeding system must be able to acquire a variety of foods. Prior bite acquisition works consider single-arm spoon scooping or fork skewering, which do not generalize to foods with complex geometries and deformabilities. For example, when acquiring a group of peas, skewering could smoosh the peas while scooping without a barrier could result in chasing the peas on the plate. In order to acquire foods with such diverse properties, we propose stabilizing food items during scooping using a second arm, for example, by pushing peas against the spoon with a flat surface to prevent dispersion. The added stabilizing arm can lead to new challenges. Critically, this arm should stabilize the food scene without interfering with the acquisition motion, which is especially difficult for easily breakable high-risk food items like tofu. These high-risk foods can break between the pusher and spoon during scooping, which can lead to food waste falling out of the spoon. We propose a general bimanual scooping primitive and an adaptive stabilization strategy that enables successful acquisition of a diverse set of food geometries and physical properties. Our approach, CARBS: Coordinated Acquisition with Reactive Bimanual Scooping, learns to stabilize without impeding task progress by identifying high-risk foods and robustly scooping them using closed-loop visual feedback. We find that CARBS is able to generalize across food shape, size, and deformability and is additionally able to manipulate multiple food items simultaneously. CARBS achieves 87.0% success on scooping rigid foods, which is 25.8% more successful than a single-arm baseline, and reduces food breakage by 16.2% compared to an analytical baseline. Videos can be found at https://sites.google.com/view/bimanualscoop-corl22/home .

研究动机与目标

• 为解决单臂舀取与穿刺在获取多样化食物类型（尤其是具有复杂几何形状与可变形性）时的局限性。
• 缓解在双臂操作易碎食物时，因舀勺与推杆之间作用力过大而导致的破损故障。
• 开发一种可泛化的自适应稳定策略，基于视觉反馈与食物风险分类实现动态调整。
• 实现对多种食物与高风险食物（如豆腐、芝士蛋糕）的有效舀取，而无需依赖硬编码的运动基元。
• 提升机器人辅助进餐系统在不同食物形状、尺寸与材料特性下的鲁棒性与泛化能力。

提出的方法

• CARBS采用双臂结构，由舀勺臂与稳定推杆臂协同工作，以在食物获取过程中实现对食物的约束与引导。
• 基于视觉的风险分类器在舀取前识别高风险、易碎食物（如豆腐、果冻），以触发自适应控制。
• 故障分类器通过分析视觉动态，检测即将发生破损的状态，并预测食物损伤的临界时刻。
• 系统动态调整稳定参数α（即推杆与舀勺之间的距离），以降低作用力并防止破损。
• 该策略利用闭环视觉反馈，持续监测食物状态，并实时调整推杆的运动。
• 通过从视觉数据中学习故障模式，该方法实现了跨食物类别的泛化，即使面对训练分布外的新食物类型亦具有效用。

实验结果

研究问题

• RQ1 能否在不依赖硬编码运动基元的前提下，使双臂舀取策略泛化于多样化食物几何形状与材料特性？
• RQ2 机器人系统如何在双臂食物获取过程中检测并预防破损故障，特别是针对易碎、可变形食物？
• RQ3 视觉反馈与学习到的分类器在提升稳定性和减少舀取过程中的食物浪费方面，能发挥多大作用？
• RQ4 单一自适应稳定策略是否能有效应对刚性与易碎食物，包括多件食物？
• RQ5 与固定参数或分析基线相比，学习型反应式稳定策略的性能表现如何？

主要发现

• CARBS在刚性食物上实现了87.0%的成功率，相较于单臂基线提升25.8%。
• 与分析基线相比，系统将食物破损率降低了16.2%，验证了自适应稳定策略的有效性。
• 相较于α=1的基线，CARBS将破损率降低了16.185%，其优异表现源于对不同食物类型动态调整α参数。
• 故障分类器成功泛化至新食物类别（如芝士蛋糕与蓝莓），尽管其仅在豆腐上进行过训练。
• 风险分类器在不同视觉外观与几何形态下均成功识别出易碎食物，支持了食物类别内的泛化能力。
• 系统在处理高粘性食物（如芝士蛋糕）时表现不佳，主要因残留物影响；在处理多个圆形物体（如蓝莓）时也因不可预测的动力学行为而受阻。