English

Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

Robotics 2021-04-22 v1

Abstract

Deep Learning has revolutionized our ability to solve complex problems such as Vision-and-Language Navigation (VLN). This task requires the agent to navigate to a goal purely based on visual sensory inputs given natural language instructions. However, prior works formulate the problem as a navigation graph with a discrete action space. In this work, we lift the agent off the navigation graph and propose a more complex VLN setting in continuous 3D reconstructed environments. Our proposed setting, Robo-VLN, more closely mimics the challenges of real world navigation. Robo-VLN tasks have longer trajectory lengths, continuous action spaces, and challenges such as obstacles. We provide a suite of baselines inspired by state-of-the-art works in discrete VLN and show that they are less effective at this task. We further propose that decomposing the task into specialized high- and low-level policies can more effectively tackle this task. With extensive experiments, we show that by using layered decision making, modularized training, and decoupling reasoning and imitation, our proposed Hierarchical Cross-Modal (HCM) agent outperforms existing baselines in all key metrics and sets a new benchmark for Robo-VLN.

Keywords

Cite

@article{arxiv.2104.10674,
  title  = {Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation},
  author = {Muhammad Zubair Irshad and Chih-Yao Ma and Zsolt Kira},
  journal= {arXiv preprint arXiv:2104.10674},
  year   = {2021}
}

Comments

Accepted to ICRA 2021; Code and Dataset are available at https://github.com/GT-RIPL/robo-vln

R2 v1 2026-06-24T01:24:29.378Z