Reactive Task-Oriented Robot-Human Handovers via Generative Hypothesis Selection
To tackle this, we propose a novel approach, GENESIS-Handover (GENErative HypotheSIS), which leverages VLM image generation to produce a variety of task-specific hand-object interaction hypotheses.
ProofPaper ↗
Key points
- When humans hand each other objects, they incorporate both geometric and semantic information into this process.
- Recent state-of-the-art methods for task-oriented robot-human handovers have progressed from modeling object geometry to incorporating object affordances.
- By leveraging VLMs as priors of plausible hand-object interactions, the method produces task-conditioned handover strategies for previously unseen object-task pairs.
- We evaluate the standalone interaction proposal module before deploying the full system on a mobile manipulator.
Sources (1)
- [1]Reactive Task-Oriented Robot-Human Handovers via Generative Hypothesis SelectionarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 09:01 AM
To tackle this, we propose a novel approach, GENESIS-Handover (GENErative HypotheSIS), which leverages VLM image generation to produce a variety of task-specific hand-object interaction hypotheses.
When humans hand each other objects, they incorporate both geometric and semantic information into this process.
Extractive summary: sentences quoted from the sources.