GROW² hierarchically grounds open-world tool affordances by using VLMs for semantic selection of objects and parts followed by geometric localization with vision foundation models.
arXiv preprint arXiv:2310.13065 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Any-ttach shows that rapid end-effector swapping combined with demonstration collection and task planning enables reliable multi-tool skills in long-horizon tasks such as sandwich making.
RoboWits benchmark with 238 tasks shows pre-trained VLAs succeed on seed tasks but fail on mutated ones, highlighting brittleness in reasoning.
A dual-layer memory and progress-aware VLA system for long-horizon chemical lab automation reports higher success rates than monolithic VLA baselines on a UR3 robot.
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
citing papers explorer
-
GROW$^2$: Grounding Which and Where for Robot Tool Use
GROW² hierarchically grounds open-world tool affordances by using VLMs for semantic selection of objects and parts followed by geometric localization with vision foundation models.
-
Any-ttach: Quick End-effector Swapping Enables Manipulation Dexterity with Simplicity
Any-ttach shows that rapid end-effector swapping combined with demonstration collection and task planning enables reliable multi-tool skills in long-horizon tasks such as sandwich making.
-
RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
RoboWits benchmark with 238 tasks shows pre-trained VLAs succeed on seed tasks but fail on mutated ones, highlighting brittleness in reasoning.
-
Long-Term Memory for VLA-based Agents in Open-World Task Execution
A dual-layer memory and progress-aware VLA system for long-horizon chemical lab automation reports higher success rates than monolithic VLA baselines on a UR3 robot.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.