Code for 'Chasing Ghosts: Instruction Following as Bayesian State Tracking' published at NeurIPS 2019

Code for sim-to-real transfer of a pretrained Vision-and-Language Navigation (VLN) agent to a robot using ROS.

Code and utilities for creating a Vision-and-Language Navigation (VLN) simulator environment from a physical space.

This repository contains completed assignments for the VLN computer programming 11 online course.

[ECCV 2022] Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation

Code for ORAR Agent for Vision and Language Navigation on Touchdown and map2seq

Official Implementation of IVLN-CE: Iterative Vision-and-Language Navigation in Continuous Environments

Contrastive-VisionVAE-Follower is a model used for multi-modal task called Vision-and-Language Navigation (VLN).

Codebase of ACL 2023 Findings "Aerial Vision-and-Dialog Navigation"

Reading list for research topics in embodied vision

This work investigates automatic hyperparameter tuning for planners such as DWA and TEB, and our navigation framework LE-Nav can be used to adjust hyperparameters of any optimization-based planner.

[ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"

A unified, agentic system for general-purpose robots, enabling multi-modal perception, mapping and localization, and autonomous mobility and manipulation, with intelligent interaction with users.

Language-Oriented Spatial Taxonomy (LOST)

[CVPR 2026] Official implementation of FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation

美团第三届低空经济飞行智能管理挑战赛

VLN synthesize data / VLN合成数据

Sparse Video Generation Model for Embodied Navigation conditioned on loose language guidance, 100% real world verification

The "AUTOSAR + Android" for Embodied AI. An OS-level framework bridging LLMs with high-frequency ROS/VLA control, enabling "Write Once, Embody Anywhere" robotics and autonomous data flywheels.

[IROS 24] Official repository of "Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation". We present the first dataset - R2R-IE-CE - to benchmark instructions errors in VLN. We then propose a method, IEDL.