Knowledge-based Neural Ordinary Differential Equations for Cosserat Rod-based Soft Robots
This work addresses the problem of accurate and efficient modeling for soft robots, which is crucial for control applications, though it appears incremental as it builds on existing physics and deep learning methods.
The authors tackled the challenge of modeling soft robot dynamics by proposing KNODE-Cosserat, a framework that combines physics-based models with neural ODEs, resulting in significant improvements over baseline models in simulation and real-world experiments.
Soft robots have many advantages over rigid robots thanks to their compliant and passive nature. However, it is generally challenging to model the dynamics of soft robots due to their high spatial dimensionality, making it difficult to use model-based methods to accurately control soft robots. It often requires direct numerical simulation of partial differential equations to simulate soft robots. This not only requires an accurate numerical model, but also makes soft robot modeling slow and expensive. Deep learning algorithms have shown promises in data-driven modeling of soft robots. However, these algorithms usually require a large amount of data, which are difficult to obtain in either simulation or real-world experiments of soft robots. In this work, we propose KNODE-Cosserat, a framework that combines first-principle physics models and neural ordinary differential equations. We leverage the best from both worlds -- the generalization ability of physics-based models and the fast speed of deep learning methods. We validate our framework in both simulation and real-world experiments. In both cases, we show that the robot model significantly improves over the baseline models under different metrics.