TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators

TL;DR

This paper introduces TANGO, a neural model that enables mobile robots to generalize tool use in new environments by understanding scene context and leveraging knowledge-base embeddings, significantly improving task prediction accuracy.

Contribution

TANGO is a novel neural approach that encodes scene and goal information for predicting tool interactions, with enhanced generalization to unseen environments using knowledge-base embeddings.

Findings

Achieves 60.5-78.9% improvement in predicting successful plans in unseen environments.

Effectively generalizes to environments with unseen tools and objects.

Utilizes graph neural networks and knowledge-base embeddings for scene understanding.

Abstract

Robots assisting us in factories or homes must learn to make use of objects as tools to perform tasks, e.g., a tray for carrying objects. We consider the problem of learning commonsense knowledge of when a tool may be useful and how its use may be composed with other tools to accomplish a high-level task instructed by a human. We introduce a novel neural model, termed TANGO, for predicting task-specific tool interactions, trained using demonstrations from human teachers instructing a virtual robot. TANGO encodes the world state, comprising objects and symbolic relationships between them, using a graph neural network. The model learns to attend over the scene using knowledge of the goal and the action history, finally decoding the symbolic action to execute. Crucially, we address generalization to unseen environments where some known tools are missing, but alternative unseen tools are present. We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments. Experimental results show a 60.5-78.9% absolute improvement over the baseline in predicting successful symbolic plans in unseen settings for a simulated mobile manipulator.