From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
cs.RO, cs.AI, cs.CV
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: website: https://zhangyuejoslin.github.io/WEDGE/
Code: https://github.com/zhangyuejoslin/WEDGE
Project page: https://zhangyuejoslin.github.io/WEDGE
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
- Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
- EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence
- EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
- RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
- DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
- SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
- Offline Visual Representation Learning for Embodied Navigation
- 3D Generation for Embodied AI and Robotic Simulation: A Survey
- Towards Adaptive Environment Generation for Training Embodied Agents
- EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents
- PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
- Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies