Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation

by   Bingqian Lin, et al.

Language instruction plays an essential role in the natural language grounded navigation tasks. However, navigators trained with limited human-annotated instructions may have difficulties in accurately capturing key information from the complicated instruction at different timesteps, leading to poor navigation performance. In this paper, we exploit to train a more robust navigator which is capable of dynamically extracting crucial factors from the long instruction, by using an adversarial attacking paradigm. Specifically, we propose a Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps. By formulating the perturbation generation as a Markov Decision Process, DR-Attacker is optimized by the reinforcement learning algorithm to generate perturbed instructions sequentially during the navigation, according to a learnable attack score. Then, the perturbed instructions, which serve as hard samples, are used for improving the robustness of the navigator with an effective adversarial training strategy and an auxiliary self-supervised reasoning task. Experimental results on both Vision-and-Language Navigation (VLN) and Navigation from Dialog History (NDH) tasks show the superiority of our proposed method over state-of-the-art methods. Moreover, the visualization analysis shows the effectiveness of the proposed DR-Attacker, which can successfully attack crucial information in the instructions at different timesteps. Code is available at


page 11

page 12

page 15


On the Evaluation of Vision-and-Language Navigation Instructions

Vision-and-Language Navigation wayfinding agents can be enhanced by expl...

Contrastive Instruction-Trajectory Learning for Vision-Language Navigation

The vision-language navigation (VLN) task requires an agent to reach a t...

(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

We demonstrate how images and sounds can be used for indirect prompt and...

CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation

Navigation guided by natural language instructions is particularly suita...

Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation

We address a practical yet challenging problem of training robot agents ...

Moment-based Adversarial Training for Embodied Language Comprehension

In this paper, we focus on a vision-and-language task in which a robot i...

Improved Instruction Ordering in Recipe-Grounded Conversation

In this paper, we study the task of instructional dialogue and focus on ...

Please sign up or login with your details

Forgot password? Click here to reset