DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
This addresses the limitation of passive command-following in embodied AI for researchers, though it is incremental as it builds on the ALFRED benchmark.
The authors tackled the problem of one-way communication in embodied AI by introducing DialFRED, a benchmark that enables agents to ask questions to humans for better task completion, resulting in a dataset with 53K annotated questions and answers and a proposed framework with pre-training and reinforcement learning.
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.