VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs

TL;DR

This paper introduces VL-LN Bench, a new benchmark for long-horizon goal-oriented navigation that incorporates active dialog to resolve ambiguity, enabling more realistic and effective embodied navigation models.

Contribution

It proposes the VL-LN benchmark and a new task, IIGN, for training dialog-enabled navigation agents in realistic, ambiguous instruction scenarios.

Findings

Dialog-enabled navigation models outperform baselines.

VL-LN dataset contains over 41k trajectories for training.

Active dialog improves navigation success in ambiguous instructions.

Abstract

In most existing embodied navigation tasks, instructions are well-defined and unambiguous, such as instruction following and object searching. Under this idealized setting, agents are required solely to produce effective navigation outputs conditioned on vision and language inputs. However, real-world navigation instructions are often vague and ambiguous, requiring the agent to resolve uncertainty and infer user intent through active dialog. To address this gap, we propose Interactive Instance Goal Navigation (IIGN), a task that requires agents not only to generate navigation actions but also to produce language outputs via active dialog, thereby aligning more closely with practical settings. IIGN extends Instance Goal Navigation (IGN) by allowing agents to freely consult an oracle in natural language while navigating. Building on this task, we present the Vision Language-Language Navigation (VL-LN) benchmark, which provides a large-scale, automatically generated dataset and a comprehensive evaluation protocol for training and assessing dialog-enabled navigation models. VL-LN comprises over 41k long-horizon dialog-augmented trajectories for training and an automatic evaluation protocol with an oracle capable of responding to agent queries. Using this benchmark, we train a navigation model equipped with dialog capabilities and show that it achieves significant improvements over the baselines. Extensive experiments and analyses further demonstrate the effectiveness and reliability of VL-LN for advancing research on dialog-enabled embodied navigation. Code and dataset: https://0309hws.github.io/VL-LN.github.io/