Motion Generation for Food Topping Challenge 2024: Serving Salmon Roe Bowl and Picking Fried Chicken
🤖 AI Summary
Dexterous manipulation of fragile food items (e.g., salmon roe, fried chicken) in automated food production remains challenging due to high precision requirements and unstructured kitchen environments.
Method: This paper proposes a force-guided, teaching-integrated approach for high-precision, adaptive robotic manipulation. We introduce a novel four-channel bilateral teleoperation architecture enabling synchronous bidirectional transmission of position and force signals. A hybrid force/position control strategy is designed, and a motion reproduction and environment-adaptive generation model is trained on human demonstration data to ensure both fidelity and robustness.
Contribution/Results: Evaluated in the ICRA 2024 Food Topping Challenge, our system achieved first place in salmon roe placement accuracy and highest single-grasp count for fried chicken among all competitors—demonstrating state-of-the-art performance and practical efficacy in complex, non-structured culinary settings.
Application Category
📝 Abstract
Although robots have been introduced in many industries, food production robots are yet to be widely employed because the food industry requires not only delicate movements to handle food but also complex movements that adapt to the environment. Force control is important for handling delicate objects such as food. In addition, achieving complex movements is possible by making robot motions based on human teachings. Four-channel bilateral control is proposed, which enables the simultaneous teaching of position and force information. Moreover, methods have been developed to reproduce motions obtained through human teachings and generate adaptive motions using learning. We demonstrated the effectiveness of these methods for food handling tasks in the Food Topping Challenge at the 2024 IEEE International Conference on Robotics and Automation (ICRA 2024). For the task of serving salmon roe on rice, we achieved the best performance because of the high reproducibility and quick motion of the proposed method. Further, for the task of picking fried chicken, we successfully picked the most pieces of fried chicken among all participating teams. This paper describes the implementation and performance of these methods.
Problem
Research questions and friction points this paper is trying to address.
Developing robots for delicate and adaptive food handling tasks
Implementing force control for precise manipulation of fragile foods
Enhancing motion generation through human teaching and learning methods
Innovation
Methods, ideas, or system contributions that make the work stand out.
Four-channel bilateral control for teaching
Reproducing motions from human teachings
Adaptive motion generation using learning
🔎 Similar Papers
No similar papers found.
