Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis

18 March 2024

Papers citing "Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis"

6 / 6 papers shown

Title
StreetNav: Leveraging Street Cameras to Support Precise Outdoor Navigation for Blind Pedestrians Gaurav Jain Basel Hindi Zihao Zhang Koushik Srinivasula Mingyu Xie ... Mehmet Turkcan Javad Ghaderi Z. Kostić Gil Zussman Brian A. Smith 21 5 0 30 Sep 2023
L3MVN: Leveraging Large Language Models for Visual Target Navigation Bangguo Yu H. Kasaei M. Cao LM&Ro 52 85 0 11 Apr 2023
Visual Language Maps for Robot Navigation Chen Huang Oier Mees Andy Zeng Wolfram Burgard LM&Ro 153 343 0 11 Oct 2022
LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action Dhruv Shah B. Osinski Brian Ichter Sergey Levine LM&Ro 150 436 0 10 Jul 2022
TEACh: Task-driven Embodied Agents that Chat Aishwarya Padmakumar Jesse Thomason Ayush Shrivastava P. Lange Anjali Narayan-Chen Spandana Gella Robinson Piramithu Gökhan Tür Dilek Z. Hakkani-Tür LM&Ro 163 180 0 01 Oct 2021
On the Evaluation of Vision-and-Language Navigation Instructions Mingde Zhao Peter Anderson Vihan Jain Su Wang Alexander Ku Jason Baldridge Eugene Ie 231 51 0 26 Jan 2021