Research map / Vision-language and multimodal / Robot action and navigation
AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
Sudipta Paul, Amit Roy-Chowdhury, Anoop Cherian
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 natural-language oracle instructions through the learned query policy | AVLEN · Heard Sound | Success: +2.2% | Improved |
| Add natural-language oracle instructions through the learned query policy | AVLEN · Unheard Sound | Success: +1.4% | Improved |
| Provide ground-truth navigation actions instead of language as oracle feedback | AVLEN · Heard Sound | Success: nearly +15% | Improved |
| Provide ground-truth navigation actions instead of language as oracle feedback | AVLEN · Unheard Sound | Success: +12% | Improved |
| Use the learned query policy rather than random, uniform, or model-uncertainty triggers | AVLEN · Heard and unheard sounds | Success | Improved |
| Add oracle interaction in the presence of distractor sounds | AVLEN · Unheard sound with distractors | Success: 2.2% | Improved |
| Add oracle interaction in the presence of distractor sounds | AVLEN · Unheard sound with distractors | SWS: 2.7% | Improved |
| Replace CLIP embeddings with GloVe embeddings (ablation) | AVLEN language policy · Heard Sound | Success: 36.1; 36.2 | No clear effect |
| Replace the Transformer with a GRU (ablation) | AVLEN language policy · Heard Sound | Success: 36.1; 37.7 | No clear effect |
| Remove the instruction from the language navigation input (ablation) | VLN-b · VLN test set | Step-1: 62.8 -> 51.3 | Hurt |
| Fine-tune the language policy with collected trajectory-instruction pairs | VLN-b · VLN test set | Step-3: 37.8 -> 45.3 | Improved |
| Increase the allowed number of oracle queries | AVLEN · Unheard Sound | SPL | Improved |
Closest papers by meaning
- CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments (AAAI 2024 · similarity 0.92)
- RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation (CVPR 2024 · similarity 0.90)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.89)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.89)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.89)
- Towards Audio-Visual Navigation in Noisy Environments: A Large-Scale Benchmark Dataset and an Architecture Considering Multiple Sound-Sources (AAAI 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.
