Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks
It addresses the problem of adapting to non-stationary data for autonomous systems, but is incremental as it focuses on reviewing and comparing existing methods.
This paper reviews state-of-the-art continual learning methods for autonomous systems, analyzing algorithms that enable online learning from large sequential data with low computational and memory resources, and compares them across self-driving vehicles, unmanned aerial vehicles, and urban robots.
Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions. The purpose of this study is to review the state-of-the-art methods that allow continuous learning of computational models over time. We primarily focus on the learning algorithms that perform continuous learning in an online fashion from considerably large (or infinite) sequential data and require substantially low computational and memory resources. We critically analyze the key challenges associated with continual learning for autonomous real-world systems and compare current methods in terms of computations, memory, and network/model complexity. We also briefly describe the implementations of continuous learning algorithms under three main autonomous systems, i.e., self-driving vehicles, unmanned aerial vehicles, and urban robots. The learning methods of these autonomous systems and their strengths and limitations are extensively explored in this article.