July 31, 2024Open Access

Enhancement of Long-Horizon Task Planning via Active and Passive Modification in Large Language Model

View Full Paper

Ask AI

Bookmark

Active questioning and human feedback improve long-horizon task planning in large language models, enabling robust generation of complex multi-step action sequences for robotic systems.
Dialogue experiments across cooking tasks show that integrating one-shot dialog examples with active clarification queries resolves missing information during offline execution.
The framework supports multimodal image inputs during robot task planning, which may enable domestic robots to execute complex procedures alongside human supervisors with fewer errors.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Experimental evaluation demonstrates enhanced long-horizon robot task planning using large language models, highlighting improved robustness through active questioning and human instruction.

Cite This Study

Hori et al. (2024) studied this question.

synapsesocial.com/papers/68e5e4ddb6db643587578f7a https://doi.org/10.21203/rs.3.rs-4695355/v1

View Full Paper

Ask AI

Bookmark

Implication

Experimental evaluation demonstrates enhanced long-horizon robot task planning using large language models, highlighting improved robustness through active questioning and human instruction.

Enhancement of Long-Horizon Task Planning via Active and Passive Modification in Large Language Model

Key Points

Discussion

Implication

Cite This Study

Enhancement of Long-Horizon Task Planning via Active and Passive Modification in Large Language Model

Key Points

Discussion

Implication

Cite This Study

Keep reading

Keep reading