Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning
Researchers have developed a new framework called SCE (Skill-Compositional Experts) to address catastrophic forgetting in embodied continual learning for robots. This framework decomposes task demonstrations into reusable skills, enabling robots to learn new manipulation tasks while retaining old ones. Experiments on LIBERO benchmarks and real-world tasks show that SCE significantly improves performance and retention. AI