Proactive robots learn routine patterns for better assistance
An Agentic Framework for Proactive Robots with Procedural Assistance Memory
Robotics
Summary
Robots that help people before being asked often guess wrong about what help is needed. The authors noticed that everyday tasks tend to follow regular patterns, so they built a system where a robot remembers routines and uses them to decide when and how to help. This memory updates after daily interactions, allowing the robot to get better with experience and adjust to changes in the user’s habits. Their approach made the robot faster and more accurate at providing helpful assistance over five days of testing.
What this means in practice
- •For robot developers: Implement robots that learn and recall user routines to improve when and how they proactively assist users.
- •For smart home integrators: Enhance home robots with memory-based task prediction to better anticipate occupants’ needs over time.
Authors
Dohyun Lee, Minho Park, Jeonghoon Park, Dongyoon Hwang, Junha Hyung, Sungwon Hwang, Byungkun Lee, Jaegul Choo
Abstract
Proactive robots should anticipate user needs and provide assistance before being explicitly asked. A straightforward approach is to infer human intentions from commonsense knowledge, but the same observed behavior can imply different needs across users, potentially leading to unwanted assistance. We observe that everyday routines in the real world exhibit recurring patterns, so learning these patterns can reduce ambiguity in proactive decisions. Based on this, we propose a memory-based agentic framework in which a VLM task predictor reads a Procedural Assistance Memory (PAM) alongside the current observation to decide when to assist and what task to perform, and a VLA executor performs the predicted task. PAM is structured as a finite-state machine over activity phases, per-state assistance rules, and event-driven transitions; a reflection VLM revises PAM from each day's interaction trace without weight updates or retraining. In our 5-day desk-assistance evaluation, memory-free baselines remain conservative, with limited recall on proactive tasks. Our system improves consistently with accumulated experience, achieving the highest precision, recall, and F1 and reducing first-fire delay from approximately 5 seconds on Day 1 to 1 second by Day 5. Our approach also adapts to changes in the user's routine through continued memory reflection, recovering from memory--routine misalignment after a single memory update. The project page is available at https://davian-robotics.github.io/PAM/