wadeKeith/Awesome-Embodied-AI

Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.

Python

248

18 commits

updated Sep 24, 2026

See the code

README

Awesome-Embodied-AI

A curated, actively maintained list of surveys, papers, datasets, simulators, benchmarks, toolkits, and project pages for embodied AI, robot learning, vision-language-action models, humanoids, and safety.

Cover

Why this repo

430+ curated resources across 10 major research and tooling tracks.
Fast entry points for newcomers and practical links for researchers and builders.
Community-maintained updates through pull requests and issue reports.

Start here

New to the field: begin with Surveys.
Looking for policy and model work: jump to Brain Models and VLA Models.
Building systems: use Simulators, Datasets, and Toolkits.
Evaluating deployment risk: read Safety.

See CONTRIBUTING.md to add a paper, fix a link, or propose a new section. If this repo is useful, please star it and cite it.

Maintainers

Cheng Yin, Chenyu Yang, Zhiwen Hu, Yunxiang Mi, Weichen Lin, Yimeng Wang.

Recent updates

2026-06-14: added WAM representation/alignment, tactile foresight, humanoid loco-manipulation/navigation, VLA social safety, and embodied benchmark automation papers.
2026-06-13: added recent WAM/VLA memory, real-time execution, force-aware manipulation, humanoid recovery, robot-learning safety, and in-context execution papers.
2026-06-12: refreshed VLA/world-model manipulation, tactile VLA, embodied planners, humanoid self-modeling, embodied safety, simulators, and datasets.
2026-03-30: added a dedicated Safety section with representative papers across perception, cognition, planning, interaction, and agentic systems.
2025-11-05: expanded robotic code-as-policy and robotic in-context learning coverage.
2025-09-07: refreshed surveys, perception, brain models, VLA models, and embodied RL entries.

Legend
Surveys
Perception
Brain Models
VLA Models
Embodied AI and RL
Robotic Code as Policy
Robotic In-Context Learning
Interaction and Humanoids
Safety
Simulators
Datasets
Toolkits
Citation
Acknowledgements

Legend

public code, dataset, benchmark, simulator, or toolkit is available.
paper only, project page only, or no maintained public repo was found.
A few foundational works appear in multiple sections when they clearly span more than one topic.

Surveys

Teleoperation of Humanoid Robots: A Survey [Paper Link] [Project Link] [2023]
Deep Learning Approaches to Grasp Synthesis: A Review [Paper Link] [Project Link] [2023]
A survey of embodied ai: From simulators to research tasks [Paper Link] [2022]
A Survey of Embodied Learning for Object-Centric Robotic Manipulation [Paper Link] [Project Link] [2024]
A Survey on Vision-Language-Action Models for Embodied AI [Paper Link] [2024]
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [Paper Link] [Project Link] [2026]
World Models for Robotic Manipulation: A Survey [Paper Link] [2026]
A Tutorial on World Models and Physical AI [Paper Link] [2026]
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends [Paper Link] [2026]
World Action Models: The Next Frontier in Embodied AI [Paper Link] [Project Link] [2026]
Embodied Intelligence Toward Future Smart Manufacturing in the Era of AI Foundation Model [Paper Link] [2024]
Towards Generalist Robot Learning from Internet Video: A Survey [Paper Link] [2024]
A Survey on Robotics with Foundation Models: toward Embodied AI [Paper Link] [2024]
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis [Paper Link] [Project Link] [2024]
Robot Learning in the Era of Foundation Models: A Survey [Paper Link] [2023]
Foundation Models in Robotics: Applications, Challenges, and the Future [Paper Link] [Project Link] [2023]
Large Language Models for Robotics: Opportunities, Challenges, and Perspectives [Paper Link] [2024]
Awesome-Embodied-Agent-with-LLMs [Project Link] [2024]
Awesome Embodied Vision [Project Link] [2024]
Awesome Touch [Project Link] [2024]
Grasp-Anything Project [Project Link] [2024]
GraspNet Project [Project Link] [2024]
Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions [Paper Link] [Project Link] [2024]
Survey of Learning-based Approaches for Robotic In-Hand Manipulation [Paper Link] [2024]
A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches [Paper Link] [2024]
Neural Scaling Laws in Robotics [Paper Link] [2025]
Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes [Paper Link] [2024]
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI [Paper Link] [Project Link] [2024]
Controllable Text Generation for Large Language Models: A Survey [Paper Link] [Project Link] [2024]
Bridging Language and Action A Survey of Language-Conditioned Robot Manipulation [Paper Link] [2023]

Perception

Brain Models

VLA Models

Embodied AI and RL

Robotic Code as Policy

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents [Paper Link] [2026]
CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity [Paper Link] [Project Link] [2025]
Embodied large language models enable robots to complete complex tasks in unpredictable environments [Paper Link] [Project Link] [2025]
Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots [Paper Link] [2025]
Code as Policies: Language Model Programs for Embodied Control [Paper Link] [Project Link] [2023]
Manipulate-Anything: Automating Real-World Robots using Vision-Language Models [Paper Link] [Project Link] [2024]

Robotic In-Context Learning

In-Context Learning Enables Robot Action Prediction in LLMs [Paper Link] [Project Link] [2025]
VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network [Paper Link] [Project Link] [2026]

Interaction and Humanoids

Safety

As embodied AI systems are deployed in safety-critical environments (autonomous driving, healthcare, household robotics), ensuring their safety becomes technically challenging and socially indispensable. This section highlights representative works on attacks and defenses across five safety layers. We intentionally select ~80 representative papers rather than the full 500+ to avoid overwhelming this repo -- for the complete collection, see Awesome-Embodied-AI-Safety.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses [Paper Link] [Project Link] [2026]
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation [Paper Link] [2026]
Safety at Scale: A Comprehensive Survey of Large Model Safety [Paper Link] [Project Link] [2025]

Perception Safety

Visual Perception — adversarial attacks and backdoors on visual recognition, detection, and tracking:

Robust physical-world attacks on deep learning visual classification [Paper Link] [2018]
Phantom of the ADAS: Securing advanced driver-assistance systems from split-second phantom attacks [Paper Link] [2020]
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning [Paper Link] [2022]
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models [Paper Link] [2023]
AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models [Paper Link] [2025]

Auditory Perception — voice command injection, audio adversarial examples, and defenses:

Hidden voice commands [Paper Link] [2016]
Devil's Whisper: A General Approach for Physical Adversarial Attacks against Commercial Black-box Speech Recognition Devices [Paper Link] [2020]
SpecPatch: Human-in-the-loop adversarial audio spectrogram patch attack on speech recognition [Paper Link] [2022]
TrojanModel: A practical trojan attack against automatic speech recognition systems [Paper Link] [2023]
Antifake: Using adversarial audio to prevent unauthorized speech synthesis [Paper Link] [2023]

Spatial Perception — LiDAR spoofing, point cloud attacks, and 3D perception robustness:

Physically realizable adversarial examples for lidar object detection [Paper Link] [2020]
Invisible for both Camera and LiDAR [Paper Link] [2021]
Exorcising "Wraith": Protecting LiDAR-based Object Detector in Automated Driving System from Appearing Attacks [Paper Link] [2023]
Adversary is on the Road: Attacks on Visual SLAM with Robust Perturbations on Point Clouds [Paper Link] [2024]
Towards Real-Time Defense against Object-Based LiDAR Attacks in Autonomous Driving [Paper Link] [2025]

Motion Perception — IMU/GPS/radar sensor spoofing and drone attacks:

Rocking drones with intentional sound noise on gyroscopic sensors [Paper Link] [2015]
WALNUT: Waging doubt on the integrity of MEMS accelerometers with acoustic injection attacks [Paper Link] [2017]
Drift with Devil: Security of Multi-Sensor Fusion based Localization in Autonomous Driving under GPS Spoofing [Paper Link] [2020]
mmSpoof: Resilient spoofing of automotive millimeter-wave radars using reflect array [Paper Link] [2023]
Paralyzing Drones via EMI Signal Injection on Sensory Communication Channels [Paper Link] [2023]

Cross-Modal Perception — attacks exploiting multi-sensor fusion inconsistencies:

Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehicles [Paper Link] [2022]
Exploring Adversarial Robustness of LiDAR-Camera Fusion Model in Autonomous Driving [Paper Link] [2023]
Malicious Attacks against Multi-Sensor Fusion in Autonomous Driving [Paper Link] [2024]
Beyond Attack Success Rate: Examining Trigger Leakage in Vision-Language Agentic Systems [Paper Link] [2026]
Not What You Asked For: Typographic Attacks in Household Robot Manipulation [Paper Link] [2026]

Cognition Safety

Instruction Understanding — attacks on embodied instruction following and VQA:

SQA3D: Situated Question Answering in 3D Scenes [Paper Link] [2023]
Can we trust embodied agents? Exploring backdoor attacks against embodied LLM-based decision-making systems [Paper Link] [2024]
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions [Paper Link] [2025]
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [Paper Link] [2025]

World Model — hallucination, robustness, and safety in learned world models:

SafeDreamer: Safe Reinforcement Learning with World Models [Paper Link] [2024]
Multi-Object Hallucination in Vision Language Models [Paper Link] [2024]
Learning Latent Dynamic Robust Representations for World Models [Paper Link] [2024]
Targeting World Models to Compromise Robot Learning Pipelines [Paper Link] [2026]

Reasoning — jailbreaking chain-of-thought and embodied reasoning:

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances [Paper Link] [2022]
Inner Monologue: Embodied Reasoning through Planning with Language Models [Paper Link] [2022]
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast [Paper Link] [2024]
H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models [Paper Link] [2025]

Planning Safety

Task Planning — jailbreaking LLM planners and backdooring robotic task plans:

Adversarial Attacks on Optimization based Planners [Paper Link] [2021]
Jailbreaking LLM-controlled robots [Paper Link] [2024]
BadRobot: Jailbreaking embodied LLMs in the physical world [Paper Link] [2024]
HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents [Paper Link] [2025]
Robo-Troj: Backdoor Attacks Against Robotic Manipulation in the Physical World [Paper Link] [2025]

Trajectory Planning — adversarial scenarios for autonomous driving trajectory prediction:

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles [Paper Link] [2022]
On adversarial robustness of trajectory prediction for autonomous vehicles [Paper Link] [2022]
AdvDo: Realistic adversarial attacks for trajectory prediction [Paper Link] [2022]
Robust inverse constrained reinforcement learning under model misspecification [Paper Link] [2024]
AdvDiffuser: Generating adversarial safety-critical driving scenarios via guided diffusion [Paper Link] [2024]

Multi-Agent Planning — Byzantine resilience and adversarial communication in swarms:

Blockchain Technology Secures Robot Swarms: A Comparison of Consensus Protocols and Their Resilience to Byzantine Robots [Paper Link] [2020]
The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning [Paper Link] [2021]
Robot Swarms Neutralize Harmful Behaviors Through Cross-Referencing [Paper Link] [2023]
Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning [Paper Link] [2024]

Action and Interaction Safety

Robot Control — adversarial RL, backdoors in policies, and safe VLA models:

Human-Agent Interaction — perceived safety and psychological risks:

Perceived Safety in Physical Human Robot Interaction -- A Survey [Paper Link] [2021]
A Taxonomy of Factors Influencing Perceived Safety in Human-Robot Interaction [Paper Link] [2023]
PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety [Paper Link] [2024]
Embedding ISO 10218 Safety Compliance in Robots via Control Barrier Functions for Human-Robot Collaboration [Paper Link] [2026]

Multi-Agent Collaboration — inter-agent infection and collusion:

When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems [Paper Link] [2025]

Agentic System Safety

Tool Use — prompt injection and skill poisoning in tool-using agents:

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis [Paper Link] [2024]
STAC: Stealthy and Targeted Attack on Code Agents [Paper Link] [2025]
Prompt Injection Attack to Tool Selection in LLM Agents [Paper Link] [2025]

Memory — memory poisoning, privacy leakage, and prompt extraction:

AgentPoison: Red-teaming LLM agents via poisoning memory or knowledge bases [Paper Link] [2024]
Ghost of the Past: Identifying and Resolving Privacy Leakage of LLM's Memory Through Proactive User Interaction [Paper Link] [2025]
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs [Paper Link] [2025]
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [Paper Link] [2026]

Self-Evolving — risks from self-improving and hallucinating agents:

Agent-SafetyBench: Evaluating the Safety of LLM Agents [Paper Link] [2024]
Embodied Red Teaming for Auditing Robotic Foundation Models [Paper Link] [2024]
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents [Paper Link] [2025]

Cascading Risks — cross-layer failures, supply chain attacks, and system-level vulnerabilities:

Spatiotemporal Attacks for Embodied Agents [Paper Link] [2020]
Secure Robotics: Nexus of Safety, Trust, and Cybersecurity [Paper Link] [2024]
SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents [Paper Link] [2024]
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems [Paper Link] [Project Link] [2026]
Automated Discovery of Semantic Attacks in Multi-Robot Navigation [Paper Link] [2025]
SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents [Paper Link] [2026]

Simulators

Datasets

Toolkits

mlx-smolvla [Project Link] [2026]
RoboSkin ROS 2 Tactile Starter Kit [Project Link] [2026]
Provael: Red-team Open Vision-Language-Action Policies in Simulation [Project Link] [2026]
PyRep: Bringing V-REP to Deep Robot Learning [Paper Link] [Project Link] [2024]
Yet Another Robotics and Reinforcement learning framework for PyTorch [Project Link] [2024]
Common Behavior Data [Project Link] [2026]

Citation

If this repo helps your work, please use the metadata in CITATION.cff or cite it as:

@misc{yin2025awesomeembodiedai,
  title        = {Awesome-Embodied-AI},
  author       = {Cheng Yin and Chenyu Yang and Zhiwen Hu and Yunxiang Mi and Weichen Lin and Yimeng Wang},
  year         = {2025},
  howpublished = {\url{https://github.com/wadeKeith/Awesome-Embodied-AI}},
  note         = {Curated repository of embodied AI resources}
}

Acknowledgements

This repo builds on and cross-links with several strong community collections:

awesome-list

datasets

embodied-ai

humanoid-robotics

physical-ai

reinforcement-learning

robotics

robot-learning

robot-manipulation

safety

simulators

vision-language-action

Similar repos

BaiShuanghao/Awesome-Robotics-Manipulation

A comprehensive list of papers about Robot Manipulation, including papers, codes, and related…

1,154

YanjieZe/Paper-List

knowledge

606

AoqunJin/Awesome-VLA-Post-Training

A collection of vision-language-action model post-training methods.

250

yueen-ma/Awesome-VLA

673

iLearn-Lab/Awesome-VLM-based-VLA-for-Robotic-Manipulation

A curated list of large VLM-based VLA models for robotic manipulation.

454

robotics-survey/Awesome-Robotics-Foundation-Models

1,411

HCPLab-SYSU/Embodied_AI_Paper_List

[Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

2,174

TianxingChen/RoboScholar

RoboScholar: A Comprehensive Paper List of Embodied AI and Robotics Research

206

Languages

Python

100.0%

wadeKeith/Awesome-Embodied-AI

Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.

Python

248

18 commits

updated Sep 24, 2026

See the code

README

Awesome-Embodied-AI

Cover

Why this repo

430+ curated resources across 10 major research and tooling tracks.
Fast entry points for newcomers and practical links for researchers and builders.
Community-maintained updates through pull requests and issue reports.

Start here

New to the field: begin with Surveys.
Looking for policy and model work: jump to Brain Models and VLA Models.
Building systems: use Simulators, Datasets, and Toolkits.
Evaluating deployment risk: read Safety.

See CONTRIBUTING.md to add a paper, fix a link, or propose a new section. If this repo is useful, please star it and cite it.

Maintainers

Cheng Yin, Chenyu Yang, Zhiwen Hu, Yunxiang Mi, Weichen Lin, Yimeng Wang.

Recent updates

2026-06-14: added WAM representation/alignment, tactile foresight, humanoid loco-manipulation/navigation, VLA social safety, and embodied benchmark automation papers.
2026-06-13: added recent WAM/VLA memory, real-time execution, force-aware manipulation, humanoid recovery, robot-learning safety, and in-context execution papers.
2026-06-12: refreshed VLA/world-model manipulation, tactile VLA, embodied planners, humanoid self-modeling, embodied safety, simulators, and datasets.
2026-03-30: added a dedicated Safety section with representative papers across perception, cognition, planning, interaction, and agentic systems.
2025-11-05: expanded robotic code-as-policy and robotic in-context learning coverage.
2025-09-07: refreshed surveys, perception, brain models, VLA models, and embodied RL entries.

Legend
Surveys
Perception
Brain Models
VLA Models
Embodied AI and RL
Robotic Code as Policy
Robotic In-Context Learning
Interaction and Humanoids
Safety
Simulators
Datasets
Toolkits
Citation
Acknowledgements

Legend

public code, dataset, benchmark, simulator, or toolkit is available.
paper only, project page only, or no maintained public repo was found.
A few foundational works appear in multiple sections when they clearly span more than one topic.

Surveys

Teleoperation of Humanoid Robots: A Survey [Paper Link] [Project Link] [2023]
Deep Learning Approaches to Grasp Synthesis: A Review [Paper Link] [Project Link] [2023]
A survey of embodied ai: From simulators to research tasks [Paper Link] [2022]
A Survey of Embodied Learning for Object-Centric Robotic Manipulation [Paper Link] [Project Link] [2024]
A Survey on Vision-Language-Action Models for Embodied AI [Paper Link] [2024]
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [Paper Link] [Project Link] [2026]
World Models for Robotic Manipulation: A Survey [Paper Link] [2026]
A Tutorial on World Models and Physical AI [Paper Link] [2026]
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends [Paper Link] [2026]
World Action Models: The Next Frontier in Embodied AI [Paper Link] [Project Link] [2026]
Embodied Intelligence Toward Future Smart Manufacturing in the Era of AI Foundation Model [Paper Link] [2024]
Towards Generalist Robot Learning from Internet Video: A Survey [Paper Link] [2024]
A Survey on Robotics with Foundation Models: toward Embodied AI [Paper Link] [2024]
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis [Paper Link] [Project Link] [2024]
Robot Learning in the Era of Foundation Models: A Survey [Paper Link] [2023]
Foundation Models in Robotics: Applications, Challenges, and the Future [Paper Link] [Project Link] [2023]
Large Language Models for Robotics: Opportunities, Challenges, and Perspectives [Paper Link] [2024]
Awesome-Embodied-Agent-with-LLMs [Project Link] [2024]
Awesome Embodied Vision [Project Link] [2024]
Awesome Touch [Project Link] [2024]
Grasp-Anything Project [Project Link] [2024]
GraspNet Project [Project Link] [2024]
Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions [Paper Link] [Project Link] [2024]
Survey of Learning-based Approaches for Robotic In-Hand Manipulation [Paper Link] [2024]
A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches [Paper Link] [2024]
Neural Scaling Laws in Robotics [Paper Link] [2025]
Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes [Paper Link] [2024]
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI [Paper Link] [Project Link] [2024]
Controllable Text Generation for Large Language Models: A Survey [Paper Link] [Project Link] [2024]
Bridging Language and Action A Survey of Language-Conditioned Robot Manipulation [Paper Link] [2023]

Perception

Brain Models

VLA Models

Embodied AI and RL

Robotic Code as Policy

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents [Paper Link] [2026]
CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity [Paper Link] [Project Link] [2025]
Embodied large language models enable robots to complete complex tasks in unpredictable environments [Paper Link] [Project Link] [2025]
Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots [Paper Link] [2025]
Code as Policies: Language Model Programs for Embodied Control [Paper Link] [Project Link] [2023]
Manipulate-Anything: Automating Real-World Robots using Vision-Language Models [Paper Link] [Project Link] [2024]

Robotic In-Context Learning

In-Context Learning Enables Robot Action Prediction in LLMs [Paper Link] [Project Link] [2025]
VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network [Paper Link] [Project Link] [2026]

Interaction and Humanoids