A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions

TL;DR

This paper introduces DRAGGN, a hybrid neural network model that interprets both goal-oriented and action-oriented natural language commands for robots, improving understanding and generalization in diverse environments.

Contribution

The paper presents a novel hybrid approach that unifies goal and action command interpretation, enabling robots to better understand natural language instructions in varied settings.

Findings

Successfully interprets both command types

Generalizes to unseen environments

Enhances natural language understanding in robots

Abstract

Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands. These instructions often fall into one of two categories: those that specify a goal condition or target state, and those that specify explicit actions, or how to perform a given task. Recent approaches have used reward functions as a semantic representation of goal-based commands, which allows for the use of a state-of-the-art planner to find a policy for the given task. However, these reward functions cannot be directly used to represent action-oriented commands. We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes to unseen environments. Our robot-simulation results demonstrate that a system successfully interpreting both goal-oriented and action-oriented task specifications brings us closer to robust natural language understanding for human-robot interaction.