Data-Efficient Multirobot, Multitask Transfer Learning for Trajectory Tracking
This work addresses the challenge of reducing data collection and training risks in robotics, though it is incremental as it builds on existing control methods for a specific domain.
The paper tackles the problem of data-efficient transfer learning for multirobot trajectory tracking by introducing a framework that combines adaptive control and iterative learning, achieving a 74% reduction in first-iteration tracking error on average in experiments with two quadrotor platforms and six trajectories.
Transfer learning has the potential to reduce the burden of data collection and to decrease the unavoidable risks of the training phase. In this letter, we introduce a multirobot, multitask transfer learning framework that allows a system to complete a task by learning from a few demonstrations of another task executed on another system. We focus on the trajectory tracking problem where each trajectory represents a different task, since many robotic tasks can be described as a trajectory tracking problem. The proposed multirobot transfer learning framework is based on a combined $\mathcal{L}_1$ adaptive control and an iterative learning control approach. The key idea is that the adaptive controller forces dynamically different systems to behave as a specified reference model. The proposed multitask transfer learning framework uses theoretical control results (e.g., the concept of vector relative degree) to learn a map from desired trajectories to the inputs that make the system track these trajectories with high accuracy. This map is used to calculate the inputs for a new, unseen trajectory. Experimental results using two different quadrotor platforms and six different trajectories show that, on average, the proposed framework reduces the first-iteration tracking error by 74% when information from tracking a different single trajectory on a different quadrotor is utilized.