STREAK: Streaming Network for Continual Learning of Object Relocations under Household Context Drifts

TL;DR

STREAK is a continual learning framework for robots that enables long-term adaptation to changing household object routines by preventing forgetting and efficiently handling streaming data.

Contribution

It introduces a streaming graph neural network with regularization and rehearsal for continual learning in dynamic, real-world robotic environments.

Findings

Effectively prevents catastrophic forgetting in long-term household routines

Maintains generalization over 50+ days of diverse household data

Achieves time- and memory-efficient incremental learning

Abstract

In real-world settings, robots are expected to assist humans across diverse tasks and still continuously adapt to dynamic changes over time. For example, in domestic environments, robots can proactively help users by fetching needed objects based on learned routines, which they infer by observing how objects move over time. However, data from these interactions are inherently non-independent and non-identically distributed (non-i.i.d.), e.g., a robot assisting multiple users may encounter varying data distributions as individuals follow distinct habits. This creates a challenge: integrating new knowledge without catastrophic forgetting. To address this, we propose STREAK (Spatio Temporal RElocation with Adaptive Knowledge retention), a continual learning framework for real-world robotic learning. It leverages a streaming graph neural network with regularization and rehearsal techniques to mitigate context drifts while retaining past knowledge. Our method is time- and memory-efficient, enabling long-term learning without retraining on all past data, which becomes infeasible as data grows in real-world interactions. We evaluate STREAK on the task of incrementally predicting human routines over 50+ days across different households. Results show that it effectively prevents catastrophic forgetting while maintaining generalization, making it a scalable solution for long-term human-robot interactions.