BROWSE
Detail
Conference Paper
A Simple Baseline for Uncertainty-Aware Language-Oriented Task Planner for Embodied Agents
Cited 0 time in 
Share 
Share
- Authors
- Hyobin Ong, Youngwoo Yoon, Jaewoo Choi, Minsu Jang
- Issue Date
- 2024-06
- Citation
- International Conference on Ubiquitous Robots (UR) 2024, pp.677-682
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Our research presents an improvement to task planning using Large Language Models (LLMs) by incorporating a simple approach to consider uncertainty in planning. This strategy, which differs from standard LLM-based planners, emphasizes quantifying uncertainty and exploring alternative paths for task execution. By establishing a method to measure uncertainty by setting appropriate thresholds on probabilities in skill selection, our planner is more capable at selecting a better path for carrying out tasks. Through our experiments in high-level planning within the ALFRED task domain, we observed an improvement in plan execution success rates by 0.96–2.41 percent points over conventional LLM-based task planners. These results demonstrate that uncertainty-aware strategies can lead to more precise and effective task planning.
- KSP Keywords
- Language model, Measure uncertainty, Plan Execution, Success rate, Task planning, task execution