Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
by Google / Everyday Robots · free · Last verified 2026-03-17
SayCan combines the semantic reasoning capabilities of large language models with learned value functions that encode physical feasibility, allowing robots to plan long-horizon tasks expressed in natural language. The approach grounds high-level language instructions in real-world robot affordances without task-specific fine-tuning.
https://arxiv.org/abs/2204.01691 ↗B+
B+—Good
Adoption: B+Quality: AFreshness: B+Citations: AEngagement: F
Specifications
- License
- Open Access
- Pricing
- free
- Capabilities
- task-planning, language-grounding, affordance-learning, long-horizon-reasoning
- Integrations
- Use Cases
- household-robotics, instruction-following, task-decomposition
- API Available
- No
- Tags
- robotics, language-grounding, llm, affordances, planning
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
70.1Adoption
78
Quality
88
Freshness
72
Citations
85
Engagement
0
Put AI to work for your business
Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.