Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

Journal of Intelligent & Robotic Systems(2022)

引用 10|浏览17
暂无评分
摘要
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.
更多
查看译文
关键词
Continual learning, Online learning, Real-world, Deep neural network, Memory, Computations, Real-time, Autonomous systems, Image recognition, Supervised learning, Reinforcement learning, Self-driving cars, Unmanned aerial vehicles, Urban robots
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要