Research map / Multi-agent systems and games / Human-AI and goal-conditioned
That and There: Judging the Intent of Pointing Actions with Robotic Arms
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 referential rather than locating pointing | Robot pick-and-place instructions · Referential vs locating trials | correctness of interpretation: χ^2= 13.89, p = 0.00096 | Helped |
| Remove accompanying speech | Robot pointing instructions · No-speech trial | interpretation of referential and locating pointing: within any margin that is less than 5% | No clear effect |
| Change robot platform from Baxter to Kuka | Robot pointing instructions · Referential vs locating trials | interpretation of pointing: within any margin that is less than 5% | No clear effect |
| Reverse the direction of the pointing action | Robot pick-and-place instructions · Reverse task | interpretation of pointing: within any margin that is less than 5% | No clear effect |
| Explain that gravity does not exist | Locating pointing to a stack edge · Natural vs unnatural scene | correct judgments for edge placement: 9 -> 24; Fisher exact test statistic 0.0478; p < 0.05 | Helped |
| Replace put with place, push, or move | Robot spatial instructions · Locating pointing trials | distribution of correct, incorrect, and ambiguous responses: χ=0.2344 , p = 0.971; b<0.0001 , p>0.98 | No clear effect |
| Add a second candidate object at a different distance from the pointing target | Referential pointing · Cluttered scene | selection of nearer versus farther object: within about 10cm | Mixed |
| Vary referential pointing cone from 45° to 67.5° or 90° | Baxter and Kuka referential pointing · Naturalness evaluation | naturalness rating: t ≤ |1.07|, p > 0.1 | No clear effect |
Closest papers by meaning
- Infer Human’s Intentions Before Following Natural Language Instructions (AAAI 2025 · similarity 0.83)
- ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making (NeurIPS 2026 · similarity 0.83)
- ThinkBot: Embodied Instruction Following with Thought Chain Reasoning (ICLR 2025 · similarity 0.83)
- Towards Better Robot Learners: Leveraging Implicit and Explicit Human Feedback Together in Human Robot Interactions (AAAI 2025 · similarity 0.83)
- SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation (NeurIPS 2025 · similarity 0.82)
- SAW-Bench: Learning Situated Awareness in the Real World (ICML 2026 · similarity 0.82)
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.