Navigation instruction generation with bev perception and large language models

S Fan, R Liu, W Wang, Y Yang - European Conference on Computer …, 2024 - Springer
Navigation instruction generation, which requires embodied agents to describe the
navigation routes, has been of great interest in robotics and human-computer interaction …

Lana: A language-capable navigator for instruction following and generation

X Wang, W Wang, J Shao… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Recently, visual-language navigation (VLN)--entailing robot agents to follow navigation
instructions--has shown great advance. However, existing literature put most emphasis on …

Counterfactual cycle-consistent learning for instruction following and generation in vision-language navigation

H Wang, W Liang, J Shen… - Proceedings of the …, 2022 - openaccess.thecvf.com
Since the rise of vision-language navigation (VLN), great progress has been made in
instruction following--building a follower to navigate environments under the guidance of …

A review of spatial reasoning and interaction for real-world robotics

C Landsiedel, V Rieser, M Walter, D Wollherr - Advanced Robotics, 2017 - Taylor & Francis
Truly universal helper robots capable of co** with unknown, unstructured environments
must be capable of spatial reasoning, ie establishing geometric relations between objects …

Learning to follow and generate instructions for language-capable navigation

X Wang, W Wang, J Shao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Visual-language navigation (VLN) is a challenging task that requires embodied agents to
follow natural language instructions to navigate in previously unseen environments …

Multimodal estimation and communication of latent semantic knowledge for robust execution of robot instructions

J Arkin, D Park, S Roy, MR Walter… - … Journal of Robotics …, 2020 - journals.sagepub.com
The goal of this article is to enable robots to perform robust task execution following human
instructions in partially observable environments. A robot's ability to interpret and execute …

Navigational instruction generation as inverse reinforcement learning with neural machine translation

AF Daniele, M Bansal, MR Walter - Proceedings of the 2017 ACM/IEEE …, 2017 - dl.acm.org
Modern robotics applications that involve human-robot interaction require robots to be able
to communicate with humans seamlessly and effectively. Natural language provides a …

Generating landmark navigation instructions from maps as a graph-to-text problem

R Schumann, S Riezler - arxiv preprint arxiv:2012.15329, 2020 - arxiv.org
Car-focused navigation services are based on turns and distances of named streets,
whereas navigation instructions naturally used by humans are centered around physical …

Common law annotations: Investigating the stability of dialog system output annotations

S Lee, A DeLucia, N Nangia, P Ganedi… - Findings of the …, 2023 - aclanthology.org
Abstract Metrics for Inter-Annotator Agreement (IAA), like Cohen's Kappa, are crucial for
validating annotated datasets. Although high agreement is often used to show the reliability …

Visual complexity and its effects on referring expression generation

M Elsner, A Clarke, H Rohde - Cognitive science, 2018 - Wiley Online Library
Speakers' perception of a visual scene influences the language they use to describe it—
which objects they choose to mention and how they characterize the relationships between …