Reliability-Aware LLM Reasoning: Handling Uncertainty in Robot Perception
| Author | Sobczak Ł.; Kelesoglu N.; Domańska J. |
|---|---|
| Title | Reliability-Aware LLM Reasoning: Handling Uncertainty in Robot Perception |
| Journal | IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN 2026) |
| Year | 2026 |
| Status | In Press |
| Abstract | <p>Robots operating in human environments must often make decisions based on perceptual information that<br>is uncertain, incomplete, or ambiguous. This paper proposes a reliability-aware reasoning framework that enables large<br>language models (LLMs) to account for perceptual uncertainty when selecting actions in human-robot interaction scenarios.<br>The environment is represented as a structured scene composed of detected objects enriched with confidence estimates, attribute reliability, and spatial uncertainty information. Using this representation, the LLM evaluates candidate objects through a reliability scoring mechanism that integrates multiple sources of perceptual evidence and supports uncertainty-aware decision making.The proposed approach is evaluated using perception episodes with controlled levels of uncertainty and compared with a baseline LLM-based matching strategy that ignores perceptual<br>reliability. Experimental results show that incorporating uncertainty-aware reasoning substantially improves decision<br>robustness under medium and high uncertainty conditions while reducing safety-critical behaviors caused by overconfident<br>autonomous decisions.</p> |