GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks

2025-10-01

AI Summary

To address high spillage rates and low reliability in robotic food scooping—caused by the dynamic and heterogeneous physical states of food—this paper proposes a spillage-aware guided diffusion policy. Methodologically, we introduce diffusion models to this task for the first time, constructing a differentiable spillage predictor grounded in physics-based simulation; its gradient signal is leveraged to guide real-time generation of safe, low-spillage trajectories. Our technical contributions are: (1) a differentiable spillage modeling framework with gradient-based policy guidance, and (2) a simulation-to-real generalization training paradigm. Trained on six food categories, the method achieves 82% task success and only 4% spillage on ten unseen food categories—reducing spillage by over 40% compared to an unguided baseline. Results demonstrate substantial improvements in robustness and safety for cross-category food manipulation.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Robotic food scooping is a critical manipulation skill for food preparation and service robots. However, existing robot learning algorithms, especially learn-from-demonstration methods, still struggle to handle diverse and dynamic food states, which often results in spillage and reduced reliability. In this work, we introduce GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks. This framework leverages guided diffusion policy to minimize food spillage during scooping and to ensure reliable transfer of food items from the initial to the target location. Specifically, we design a spillage predictor that estimates the probability of spillage given current observation and action rollout. The predictor is trained on a simulated dataset with food spillage scenarios, constructed from four primitive shapes (spheres, cubes, cones, and cylinders) with varied physical properties such as mass, friction, and particle size. At inference time, the predictor serves as a differentiable guidance signal, steering the diffusion sampling process toward safer trajectories while preserving task success. We validate GRITS on a real-world robotic food scooping platform. GRITS is trained on six food categories and evaluated on ten unseen categories with different shapes and quantities. GRITS achieves an 82% task success rate and a 4% spillage rate, reducing spillage by over 40% compared to baselines without guidance, thereby demonstrating its effectiveness.

Problem

• Minimizing food spillage during robotic scooping tasks
• Handling diverse and dynamic food states reliably
• Ensuring successful food transfer from source to target

Innovation

• Guided diffusion policy minimizes food spillage
• Spillage predictor steers diffusion sampling process
• Framework trained on simulated food spillage scenarios