Research map / Vision-language and multimodal / Robot action and navigation
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use ESC's GLIP scene grounding and commonsense-guided frontier selection instead of CoW's CLIP-based exploration | Zero-shot object navigation · MP3D | SPL: 3.7 -> 14.2 | Helped |
| Use GLIP scene grounding instead of CLIP, without adding commonsense reasoning (ablation) | Zero-shot object navigation · MP3D and RoboTHOR | SPL: 3.7 -> 12.4; 16.9 -> 21.6 | Helped |
| Add commonsense-guided frontier selection rather than always selecting the nearest frontier (ablation) | GoW · MP3D and HM3D | SPL: 12.4 -> 14.2; 18.8 -> 22.3 | Helped |
| Add room-level commonsense reasoning (ablation) | ESC · MP3D | SPL: 13.8 -> 14.2 | Helped |
| Add room-level commonsense reasoning (ablation) | ESC · HM3D | SPL: 21.8 -> 22.3 | Helped |
| Add room-level commonsense reasoning (ablation) | ESC · RoboTHOR | SPL: 21.4 -> 22.2 | Mixed |
| Add object-level commonsense reasoning (ablation) | ESC · MP3D | SPL: 13.7 -> 14.2 | Helped |
| Add object-level commonsense reasoning (ablation) | ESC · HM3D | SPL: 22.3 -> 22.3 | No clear effect |
| Add object-level commonsense reasoning (ablation) | ESC · RoboTHOR | SPL: 23.1 -> 22.2 | Hurt |
| Replace Deberta with ChatGPT for object-plus-room reasoning (ablation) | ESC · HM3D | SPL: 22.3 -> 22.4 | No clear effect |
| Replace the one-hot PSL solver with ADMM (ablation) | ESC with object reasoning · MP3D | SPL: 13.7 -> 12.9 | Hurt |
| Replace the one-hot PSL solver with ADMM (ablation) | ESC with object reasoning · MP3D | Infer time: 0.25 -> 2.13 | Hurt |
Closest papers by meaning
- Augmented Commonsense Knowledge for Remote Object Grounding (AAAI 2024 · similarity 0.88)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.87)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.87)
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World (NeurIPS 2025 · similarity 0.87)
- GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance (NeurIPS 2024 · similarity 0.87)
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.