Data-Efficient Multirobot, Multitask Transfer Learning for Trajectory Tracking
| Autor: | Mohamed K. Helwa, Angela P. Schoellig, Karime Pereida |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Control and Optimization Adaptive control Computer science Biomedical Engineering 02 engineering and technology 010501 environmental sciences 01 natural sciences Tracking error Computer Science - Robotics 020901 industrial engineering & automation Artificial Intelligence Control theory Adaptive system 0105 earth and related environmental sciences Mechanical Engineering Iterative learning control Computer Science Applications Human-Computer Interaction Control and Systems Engineering Trajectory Robot Computer Vision and Pattern Recognition Transfer of learning Algorithm Robotics (cs.RO) |
| DOI: | 10.48550/arxiv.1709.04543 |
| Popis: | 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. Comment: 9 pages, 6 figures, submitted to RA-L 2017 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|