CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments

TL;DR

CAVEN introduces a conversational audio-visual navigation framework enabling an agent to interact with humans for improved localization of audio goals in noisy environments, significantly enhancing success rates.

Contribution

The paper presents CAVEN, a novel framework combining natural language interaction with audio-visual navigation, and introduces AVN-Instruct, a large dataset for training such interactive agents.

Findings

Nearly tenfold increase in success rate with conversational approach

Effective in localizing new sound sources in noisy environments

Outperforms uni-directional interaction methods

Abstract

Audio-visual navigation of an agent towards locating an audio goal is a challenging task especially when the audio is sporadic or the environment is noisy. In this paper, we present CAVEN, a Conversation-based Audio-Visual Embodied Navigation framework in which the agent may interact with a human/oracle for solving the task of navigating to an audio goal. Specifically, CAVEN is modeled as a budget-aware partially observable semi-Markov decision process that implicitly learns the uncertainty in the audio-based navigation policy to decide when and how the agent may interact with the oracle. Our CAVEN agent can engage in fully-bidirectional natural language conversations by producing relevant questions and interpret free-form, potentially noisy responses from the oracle based on the audio-visual context. To enable such a capability, CAVEN is equipped with: (i) a trajectory forecasting network that is grounded in audio-visual cues to produce a potential trajectory to the estimated goal, and (ii) a natural language based question generation and reasoning network to pose an interactive question to the oracle or interpret the oracle's response to produce navigation instructions. To train the interactive modules, we present a large scale dataset: AVN-Instruct, based on the Landmark-RxR dataset. To substantiate the usefulness of conversations, we present experiments on the benchmark audio-goal task using the SoundSpaces simulator under various noisy settings. Our results reveal that our fully-conversational approach leads to nearly an order-of-magnitude improvement in success rate, especially in localizing new sound sources and against methods that only use uni-directional interaction.