FOCUS: Object-Centric World Models for Robotics Manipulation

TL;DR

FOCUS introduces an object-centric world model for robotics manipulation, enhancing exploration and task efficiency by capturing entities and relationships, and demonstrating effectiveness both in simulation and real-world robot experiments.

Contribution

The paper presents FOCUS, a novel object-centric world model with an exploration bonus, improving robot manipulation and exploration in structured environments.

Findings

Enhanced exploration of object interactions.

Improved task-solving efficiency in manipulation tasks.

Successful deployment on real robot hardware.

Abstract

Understanding the world in terms of objects and the possible interplays with them is an important cognition ability, especially in robotics manipulation, where many tasks require robot-object interactions. However, learning such a structured world model, which specifically captures entities and relationships, remains a challenging and underexplored problem. To address this, we propose FOCUS, a model-based agent that learns an object-centric world model. Thanks to a novel exploration bonus that stems from the object-centric representation, FOCUS can be deployed on robotics manipulation tasks to explore object interactions more easily. Evaluating our approach on manipulation tasks across different settings, we show that object-centric world models allow the agent to solve tasks more efficiently and enable consistent exploration of robot-object interactions. Using a Franka Emika robot arm, we also showcase how FOCUS could be adopted in real-world settings.