Data-Driven Control in Contact-Rich Tasks
1. Data-Driven Model Predictive Control for the Contact-Rich Task of Food Cutting
Modelling of contact-rich tasks is challenging and cannot be entirely solved using classical control approaches due to the difficulty of constructing an analytic description of the contact dynamics. Additionally, in a manipulation task like food-cutting, purely learning-based methods such as Reinforcement Learning, require either a vast amount of data that is expensive to collect on a real robot, or a highly realistic simulation environment, which is currently not available. This paper presents a data-driven control approach that employs a recurrent neural network to model the dynamics for a Model Predictive Controller.
More information can be found in:
I. Mitsioni, Y. Karayiannidis, J. A. Stork and D. Kragic, "Data-Driven Model Predictive Control for the Contact-Rich Task of Food Cutting," 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), Toronto, ON, Canada, 2019, pp. 244-250. [link to the paper]
2. Modelling and Learning Dynamics for Robotic Food-Cutting
Data-driven approaches for modelling contact-rich tasks address many of the difficulties that analytical models bear. For real-world scenarios, the hardware capabilities constrain the available measurements and consequently, every step of the problem's formulation. In this work, we propose a formulation that encapsulates knowledge from a baseline controller for the contact-rich task of food-cutting. Based on this formulation, we employ deep networks to model the dynamics within a model predictive controller. We design a training process based on curriculum training with learning rate decay for multi-step predictions, which are essential for receding horizon control. Experimental results demonstrate that even with a simple architecture, our model achieves consistently good predictive performance on known and unknown object classes and exhibits a good understanding of the long term dynamics.
More information can be found in:
I. Mitsioni, Y. Karayiannidis and D. Kragic, "Modelling and Learning Dynamics for Robotic Food-Cutting," 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), 2021, pp. 1194-1200, doi: 10.1109/CASE49439.2021.9551558. [link to the paper]
