DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following

TL;DR

DialFRED introduces a dialogue-enabled benchmark for embodied AI, allowing agents to ask questions and interact with humans to improve task completion in navigation and manipulation tasks.

Contribution

It presents a new benchmark with a large dataset and an oracle, and proposes a questioner-performer framework for dialogue-enabled embodied agents.

Findings

The dataset contains 53K task-relevant questions and answers.

The questioner is pre-trained on human-annotated data and fine-tuned with reinforcement learning.

DialFRED is publicly available for research and evaluation.

Abstract

Language-guided Embodied AI benchmarks requiring an agent to navigate an environment and manipulate objects typically allow one-way communication: the human user gives a natural language command to the agent, and the agent can only follow the command passively. We present DialFRED, a dialogue-enabled embodied instruction following benchmark based on the ALFRED benchmark. DialFRED allows an agent to actively ask questions to the human user; the additional information in the user's response is used by the agent to better complete its task. We release a human-annotated dataset with 53K task-relevant questions and answers and an oracle to answer questions. To solve DialFRED, we propose a questioner-performer framework wherein the questioner is pre-trained with the human-annotated data and fine-tuned with reinforcement learning. We make DialFRED publicly available and encourage researchers to propose and evaluate their solutions to building dialog-enabled embodied agents.