Research map / Vision-language and multimodal / Robot action and navigation
From Woofs to Words: Towards Intelligent Robotic Guide Dogs with Verbal Communication
Yohei Hayamizu, David DeFazio, Hrudayangam Mehta, Zainab Altaweel, Jacqueline Choe, Chao Lin, Jake Juettner, Furui Xiao, Jeremy Blackburn, Shiqi Zhang
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 scene and plan verbalization (ablation) | robotic guide dog dialog · Human study (6 participants), Q1 utility | mean rating: 4.33 -> 4.83 | Improved |
| add plan verbalization on top of scene verbalization (ablation) | robotic guide dog dialog · Human study (6 participants), Q3 helpfulness vs other tools | mean rating: 4.00 -> 4.33 | Improved |
| add scene and plan verbalization (ablation) | robotic guide dog dialog · Human study (6 participants), Q5 ease of communication | mean rating: 4.33 -> 4.50 (vs minimum); 4.00 -> 4.50 (vs scene only) | Improved |
| add scene and plan verbalization (ablation) | robotic guide dog dialog · Human study (6 participants), Q4 safety | mean rating: 4.00 -> 3.83 | Hurt |
| add plan information to dialog (ablation) | LLM guide dog dialog · Simulation, planner-informed dialog (3 tasks) | navigation cost: 73.00 -> 55.17 | Improved |
| add plan information to dialog (ablation) | LLM guide dog dialog · Simulation, planner-informed dialog (3 tasks) | dialog length: 84.83 -> 115.67 | Hurt |
| add plan information to dialog (ablation) | LLM guide dog dialog · Simulation, planner-informed dialog (3 tasks) | total task time: 277.27 -> 230.15 | Improved |
| perturb user characters with 0.3 probability (noisy speech) | LLM guide dog dialog · Simulation, 77 service tasks | task accuracy: loses 5.2% accuracy | Hurt |
Closest papers by meaning
- Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks (ICLR 2024 · similarity 0.80)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.80)
- VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation (ICLR 2025 · similarity 0.80)
- Vision-Language Foundation Models as Effective Robot Imitators (ICLR 2024 · similarity 0.80)
- Language Guided Skill Discovery (ICLR 2025 · similarity 0.80)
- DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution (NeurIPS 2024 · similarity 0.80)
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.
