Research map / Vision-language and multimodal / Robot action and navigation
RoboTrom-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction
Yufeng Zhong, Chengjian Feng, Feng Yan, Fanfan Liu, Liming Zheng, Lin Ma
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 historical observations (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 31.3 -> 42.5 | Improved |
| add position-enhanced historical features (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 2.9 decrease in SR | Improved |
| add sampling of historical observations (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 2.2 drop in SR | Improved |
| add EQA data to joint training (ObjectNavRoom) (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 42.5 -> 47.2 | Improved |
| add EQA data to joint training (ObjectNavRoom, SEL) (ablation) | RoboTron-Nav · ObjectNavRoom | SEL: 16.0 -> 21.9 | Improved |
| add EQA data to joint training (ObjectNav) (ablation) | RoboTron-Nav · ObjectNav | SR: 72.5 -> 81.1 | Improved |
| scale ObjectNav-size data (five times more samples) with EQA | RoboTron-Nav · ObjectNav vs ObjectNavRoom | SR: 47.2 -> 81.1 | Improved |
| increase window size W from 20 to 60 (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 32.6 -> 42.1 | Improved |
| increase window size W beyond 60 to 100 (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 42.1 -> 35.2 | Hurt |
| raise position threshold eps beyond 0.1 (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 42.1 -> 40.5 | Hurt |
| raise semantic threshold tau to 0.95 (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 42.1 -> 42.5 | Improved |
| raise semantic threshold tau to 0.99 (ablation) | RoboTron-Nav · ObjectNavRoom | SR: 42.5 -> 41.5 | Hurt |
Closest papers by meaning
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.91)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.90)
- Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments (ECCV 2020 · similarity 0.90)
- LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning (ECCV 2026 · similarity 0.90)
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World (NeurIPS 2025 · similarity 0.88)
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · 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.
