Research map / Multi-agent systems and games / Human-AI and goal-conditioned
FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI
Yuhang Peng, Yizhou Pan, Xinning He, Jihaoyu Yang, Xinyu Yin, Han Wang, Xiaoji Zheng, Chao Gao, Jiangtao Gong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| allow the human to ask follow-up questions | Human · FreeAskWorld closed-loop (Direction Inquiry) | SR: 40.2 -> 82.6 | Improved |
| fine-tune on FreeAskWorld | ETPNav · FreeAskWorld closed-loop (Direction Inquiry) | NE: 32.9 -> 31.6 | Improved |
| fine-tune on FreeAskWorld | BEVBert · FreeAskWorld closed-loop (Direction Inquiry) | NE: 31.0 -> 30.0 | Improved |
| fine-tune on FreeAskWorld | ETPNav · FreeAskWorld closed-loop (Direction Inquiry) | ONE: 28.7 -> 27.1 | Improved |
| fine-tune on FreeAskWorld | ETPNav · FreeAskWorld closed-loop (Direction Inquiry) | OSR: 0.0 -> 1.1 | Improved |
| fine-tune on FreeAskWorld | ETPNav · FreeAskWorld closed-loop (Direction Inquiry) | SR: 0.0 -> 0.0 | No clear effect |
| fine-tune on FreeAskWorld | BEVBert · FreeAskWorld closed-loop (Direction Inquiry) | SR: 0.0 -> 0.0 | No clear effect |
| fine-tune on FreeAskWorld | ETPNav and BEVBert · FreeAskWorld closed-loop (Direction Inquiry) | L2 error (open-loop): ~50% reduction in L2 error | Improved |
| fine-tune on FreeAskWorld | BEVBert · FreeAskWorld closed-loop (Direction Inquiry) | TL: 14.6 -> 18.7 | Improved |
| use Social Force Model for local avoidance in data collection | data collection agent · FreeAskWorld closed-loop (Direction Inquiry) | success rate: longer trajectories | Mixed |
Closest papers by meaning
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.89)
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots (ICLR 2024 · similarity 0.89)
- Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making (NeurIPS 2024 · similarity 0.88)
- Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (NeurIPS 2026 · similarity 0.88)
- VirtualEnv: A Platform for Embodied AI Research (AAAI 2026 · similarity 0.88)
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
