Research map / Vision-language and multimodal / Robot action and navigation
APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation
Daoxuan Zhang, Ping Chen, Xiaobo Xia, Xiu Su, Ruichen Zhen, Jianqiang Xiao, Shuo Yang
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 |
|---|---|---|---|
| add 3D dynamic grid-based map (ablation) | APEX · UAV-ON (overall) | SR: 1.67 -> 13.33 | Improved |
| add 3D dynamic grid-based map (ablation) | APEX · UAV-ON (overall) | SPL: 0.73 -> 10.14 | Improved |
| add RL-based action decision module over heuristic (ablation) | APEX · UAV-ON (overall) | SR: 12.50 -> 13.33 | Improved |
| add RL-based action decision module over heuristic (ablation) | APEX · UAV-ON (overall) | SPL: 10.11 -> 10.14 | No clear effect |
| add RL-based action decision module over heuristic (ablation) | APEX · UAV-ON (overall) | NE: 42.08 -> 54.59 | Hurt |
| add target grounding module (ablation) | APEX · UAV-ON (overall) | SR: 5.00 -> 13.33 | Improved |
| add target grounding module (ablation) | APEX · UAV-ON (overall) | SPL: 4.17 -> 10.14 | Improved |
| set alpha to 0.2 instead of 0.05 (ablation) | APEX · UAV-ON (overall) | SR: 5.83 -> 13.33 | Improved |
| set alpha to 0.2 instead of 1.0 (ablation) | APEX · UAV-ON (overall) | SR: 7.50 -> 13.33 | Improved |
| set alpha to 0.8 instead of 0.2 (ablation) | APEX · UAV-ON (overall) | SPL: 10.14 -> 11.45 | Mixed |
| use decoupled asynchronous parallel framework with RL decision module vs prior methods | APEX · UAV-ON efficiency | step latency (s): 1.26 -> 0.97 | Improved |
| use APEX instead of best baseline L3MVN-Z | APEX · UAV-ON (overall) | SR: 9.17 -> 13.33 | Improved |
Closest papers by meaning
- Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory (CVPR 2026 · similarity 0.89)
- Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (ICLR 2025 · similarity 0.89)
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.89)
- SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery (NeurIPS 2026 · similarity 0.88)
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · similarity 0.87)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.86)
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.
