M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning

Abstract

Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often rely on unsupervised skill discovery to construct an ever-growing skill library or distillation from multiple policies, which can lead to scalability issues as diverse manipulation tasks are continually introduced and may fail to ensure a consistent latent space throughout the learning process, leading to catastrophic forgetting of previously learned skills. In this paper, we introduce M2Distill, a multimodal distillation-based method for lifelong imitation learning focusing on preserving consistent latent space across vision, language, and action distributions throughout the learning process. By regulating the shifts in latent representations across different modalities from previous to current steps, and reducing discrepancies in Gaussian Mixture Model (GMM) policies between consecutive learning steps, we ensure that the learned policy retains its ability to perform previously learned tasks while seamlessly integrating new skills. Evaluations on the LIBERO lifelong imitation learning benchmark suites, including LIBERO-OBJECT, LIBERO-GOAL, and LIBERO-SPATIAL, demonstrate that our method consistently outperforms prior state-of-the-art methods across all evaluated metrics.