DialNav: Multi-turn Dialog Navigation with a Remote Guide
This addresses the problem of holistic evaluation in embodied AI for researchers, though it is incremental as it builds on prior dialog navigation work.
The authors introduced DialNav, a collaborative embodied dialog task where a Navigator and remote Guide communicate to reach a goal, and released the RAIN dataset with human-human dialog and navigation trajectories for evaluation.
We introduce DialNav, a novel collaborative embodied dialog task, where a navigation agent (Navigator) and a remote guide (Guide) engage in multi-turn dialog to reach a goal location. Unlike prior work, DialNav aims for holistic evaluation and requires the Guide to infer the Navigator's location, making communication essential for task success. To support this task, we collect and release the Remote Assistance in Navigation (RAIN) dataset, human-human dialog paired with navigation trajectories in photorealistic environments. We design a comprehensive benchmark to evaluate both navigation and dialog, and conduct extensive experiments analyzing the impact of different Navigator and Guide models. We highlight key challenges and publicly release the dataset, code, and evaluation framework to foster future research in embodied dialog.