IMRL：整合视觉、物理、时间与几何表征以增强食物获取能力
IMRL: Integrating Visual, Physical, Temporal, and Geometric Representations for Enhanced Food Acquisition
AI总结：
针对机器人辅助喂食中多样食物获取与未知场景泛化难题，提出IMRL框架，融合视觉、物理、时间和几何表征增强模仿学习，真实机器人实验显示成功率最高提升35%。
摘要：
机器人辅助喂食在改善进食障碍人士生活质量方面具有显著前景。然而，在不断变化的条件下获取多样食物，并泛化至未见过的食物，带来了独特挑战。现有方法依赖从视觉线索（如颜色、形状和纹理）中获得的表层几何信息（如边界框和位姿），往往缺乏适应性和鲁棒性，尤其是在食物具有相似物理属性但视觉外观不同时。我们采用模仿学习（IL）来学习食物获取策略。现有方法使用IL或强化学习（RL），基于ResNet-50等现成图像编码器学习策略。然而，此类表征并不鲁棒，且难以在多样的获取场景中泛化。为解决这些局限，我们提出一种新颖方法IMRL（Integrated Multi-Dimensional Representation Learning，集成多维表征学习），它整合视觉、物理、时间和几何表征，以增强用于食物获取的IL的鲁棒性和泛化能力。我们的方法捕捉食物类型和物理属性（例如固体、半固体、颗粒状、液体和混合物），对获取动作的时间动态进行建模，并引入几何信息来确定最佳舀取点和评估碗内装满程度。IMRL使IL能够根据上下文自适应调整舀取策略，从而提高机器人处理多样食物获取场景的能力。在真实机器人上的实验证明了我们的方法在各种食物和碗配置下的鲁棒性与适应性，包括对未见过设置的零样本泛化。与表现最佳的基线相比，我们的方法在成功率上实现了高达35%的提升。更多细节可访问我们的网站https://ruiiu.github.io/imrl。
英文摘要：
Robotic assistive feeding holds significant promise for improving the quality of life for individuals with eating disabilities. However, acquiring diverse food items under varying conditions and generalizing to unseen food presents unique challenges. Existing methods that rely on surface-level geometric information (e.g., bounding box and pose) derived from visual cues (e.g., color, shape, and texture) often lacks adaptability and robustness, especially when foods share similar physical properties but differ in visual appearance. We employ imitation learning (IL) to learn a policy for food acquisition. Existing methods employ IL or Reinforcement Learning (RL) to learn a policy based on off-the-shelf image encoders such as ResNet-50. However, such representations are not robust and struggle to generalize across diverse acquisition scenarios. To address these limitations, we propose a novel approach, IMRL (Integrated Multi-Dimensional Representation Learning), which integrates visual, physical, temporal, and geometric representations to enhance the robustness and generalizability of IL for food acquisition. Our approach captures food types and physical properties (e.g., solid, semi-solid, granular, liquid, and mixture), models temporal dynamics of acquisition actions, and introduces geometric information to determine optimal scooping points and assess bowl fullness. IMRL enables IL to adaptively adjust scooping strategies based on context, improving the robot's capability to handle diverse food acquisition scenarios. Experiments on a real robot demonstrate our approach's robustness and adaptability across various foods and bowl configurations, including zero-shot generalization to unseen settings. Our approach achieves improvement up to $35\%$ in success rate compared with the best-performing baseline. More details can be found on our website https://ruiiu.github.io/imrl.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
