Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty
Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty
This research introduces an LLM-based interactive assistant designed to explain planetary rover trajectory plans generated by sampling-based planners under probabilistic uncertainty. The system pairs a simulator inspired by the NASA VIPER mission with a ReAct queryable interface, allowing users to compare alternatives and verify traceability to science objectives. Experiments on a query bank of plan comparisons, feasibility checks, and lookups show that 90.9% of the assistant's responses are faithful to the planner's outputs, representing a nearly 65% improvement over zero-shot prompting without tool access. The study demonstrates potential for trustworthy explainability in uncertainty-aware traverses but remains within simulation and does not claim operational deployment.
The paper proposes an LLM-based interactive assistant for explaining and re-running rover trajectory planners under uncertainty, evaluated on a query bank with 90.9% faithful responses compared to zero-shot prompting; results are limited to simulation and do not confirm deployment readiness.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ng of plan comparisons, feasibility, and lookup queries. Experiments show that 90.9% of the assistant's responses are faithful to the planner's outputs, a nearly 65% improvement over zero-shot prompting of the same LLM without tool access, demonstrating the potential for trustworthy explainability of uncertainty-aware traverses with an LLM-based system.
Open source S5
g loops, but we explore using them for post-planning explanation, where they are more likely to be trusted since they do not directly influence planner decisions. Our framework pairs a simulator inspired by the NASA Volatiles Investigating Polar Exploration Rover (VIPER) mission with a ReAct queryable interface that calls curated action tools and retrieval functions. We evaluate the assistant on a query bank consisti
Open source S4
arXiv:2611.13292v1 Announce Type: new Abstract: Planning planetary rover trajectories under probabilistic uncertainty is a multi-objective optimization problem that science teams currently iteratively solve and verify by hand. This process becomes impractical when timelines and constraints frequently shift throughout the mission planning phase. Sampling-based planners such as Monte Carlo tree search can speed up this
Open source S2
Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty
Open source S1
process, but their outputs do not preserve traceability to the science objectives that justify each plan, which the science team needs to verify. We propose an interactive assistant based on a large language model (LLM) that can explain planner trajectories using domain vocabulary and re-run the planner under user-specified conditions to compare alternatives. Previous work has used LLMs inside planner decision-makin
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org