Survey_EmbodiedAI

Simple but Effective: CLIP Embeddings for Embodied AI. 2022 CVPR
ZSON: Zero-shot Object-Goal Navigation using MultiModal Goal Embeddings. 2022
CLIP on Wheels: Zero-shot Object Navigation as Object Localization and Exploration. 2022
ViNG: Learning Open-World Navigation with Visual Goals. 2021 ICRA
Pre-Trained Language Models for Interactive Decision-Making. 2022
R3M: A Universal Visual Representation for Robot Manipulation. 2022 CoRL
BC-Z: Zero-shot Task Generalization with Robotic Imitation Learning. 2021 CoRL
Grounding Language with Visual Affordance over Unstructured Data. 2022
What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data. 2022
LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision and Action. 2022 CoRL
Visual Language Maps for Robot Navigation.
Do as I Can, Not as I Say: Grounding Language in Robotics Affordances.
Open-vocabulary Queryable Scene Representations for Real World Planning
Language Models as Zero-shot Planners: Extracting Actionable Knowledge for Embodied Agents.
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments. 2020 CVPR
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
SQA3D: SITUATED QUESTION ANSWERING IN 3D SCENES. 2023 ICLR
Episodic Transformer for Vision-and-Language Navigation. 2021 ICCV

Lxmert: Learning crossmodality encoder representations from transformers. 2019 EMNLP
Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. 2019 NIPS
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks.
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
Cross-modal Map Learning for Vision and Language Navigation
Airbert: In-domain Pretraining for Vision-and-Language Navigation
Instruction-Following Agents with Jointly Pre-Trained Vision-Language Models

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
LEBP — Language Expectation & Binding Policy: A Two-Stream Framework for Embodied Vision-and-Language Interaction Task Learning Agents
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents

Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning, 2017 ICRA
Semi-Parametric Topological Memory for Navigation, 2018 ICLR
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks, 2019 CVPR
Neural Topological SLAM for Visual Navigation, 2020 CVPR
Visual Graph Memory with Unsupervised Representation for Visual Navigation, 2021 ICCV
No RL, No Simulation: Learning to Navigate without Navigating, 2021 NIPS
Topological Semantic Graph Memory for Image-Goal Navigation, 2022 CoRL
Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation, 2022 CVPR
Memory-Augmented Reinforcement Learning for Image-Goal Navigation, 2022 IROS
Last-Mile Embodied Visual Navigation, 2022 CoRL
ViNG: Learning Open-World Navigation with Visual Goals, 2021 ICRA
Lifelong Topological Visual Navigation, 2022 RA-L

Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models. 2022 NIPS workshop
Scaling Robot Learning with Semantically Imagined Experience. 2023 \
Learning Universal Policies via Text-Guided Video Generation, 2023
Policy Adaptation from Foundation Model Feedback, 2023 CVPR
CLIPort: What and Where Pathways for Robotic Manipulation, 2021 CoRL
RT-1: Robotics Transformer for Real-World Control at Scale. 2022
Open-World Object Manipulation using Pre-trained Vision-Language Models. 2023
R3M: A Universal Visual Representation for Robot Manipulation. 2022 CoRL

fangzheng81 / awesom-embodied-navigation Goto Github PK