Research map / Vision-language and multimodal / Robot action and navigation
DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control
Xinyu Xu, Shengcheng Luo, Yanchao Yang, Yong-Lu Li, Cewu Lu
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 |
|---|---|---|---|
| replace cell-based scene map with differentiable scene representation (ablation) | DISCO · ALFRED valid unseen | SR: 42.7 -> 55.0 | Improved |
| add interactive affordances (openable, affordance-augmented localization) (ablation) | DISCO · ALFRED valid unseen | SR: 51.3 -> 55.0 | Improved |
| add navigability affordance instead of point-obstacle navigation (ablation) | DISCO · ALFRED valid unseen | SR: 46.0 -> 55.0 | Improved |
| add map-based coarse control (ablation) | DISCO · ALFRED valid unseen | SR: 9.1 -> 55.0 | Improved |
| add neural fine control after coarse navigation (ablation) | DISCO · ALFRED valid unseen | SR: 51.7 -> 55.0 | Improved |
| add low-level step-by-step instructions (ablation) | DISCO · ALFRED valid unseen | SR: 55.0 -> 59.1 | Improved |
| use ground-truth language parsing (ablation) | DISCO · ALFRED valid unseen | SR: 55.0 -> 64.1 | Improved |
| use ground-truth perception (ablation) | DISCO · ALFRED valid unseen | SR: 55.0 -> 66.8 | Improved |
| use ground-truth perception and language together (ablation) | DISCO · ALFRED valid unseen | SR: 55.0 -> 79.6 | Improved |
| use DISCO without step-by-step instructions versus prior methods that use them | ALFRED agents · ALFRED test unseen | SR: 46.1 (CAPEAM with instr.) -> 54.7 | Improved |
| use DISCO instead of Prompter | ALFRED agents · ALFRED test unseen | PLWSR (efficiency): 20.8 -> 36.5 | Improved |
Closest papers by meaning
- Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation (ECCV 2026 · similarity 0.89)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.88)
- ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making (NeurIPS 2026 · similarity 0.88)
- SPIN: Simultaneous Perception Interaction and Navigation (CVPR 2024 · similarity 0.88)
- Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation (AAAI 2025 · similarity 0.87)
- DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI (CVPR 2025 · 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.
