New AI Helps Rockets Pick Safer Landing Spots Mid-Flight

A new arXiv paper takes on a decision challenge in aerospace systems: powered descent requires efficiently selecting a landing site while fine-scale hazards remain unresolvable until low altitude, so the actor must select a site and make corresponding actions before all information is known. The authors introduce a lightweight model of altitude-limited information in which each landing site is summarized by a mean score and a designed ambiguity proxy that contracts as the vehicle descends and senses within a cone-shaped footprint under an altitude-to-resolution schedule. Using that abstraction, they derive closed-form, risk-averse site scoring techniques — an entropic certainty-equivalent and a Gaussian Conditional Value at Risk surrogate — and pair them with greedy and exploratory planners to prioritize sites that are both high-value and robust to late-revealed terrain detail. According to the article, these rollout-free heuristics improve lower-tail landing outcomes (1st percentile and certainty-equivalent) relative to mean-based baselines, with the largest gains when refinement occurs late and unresolved detail is large. The authors also demonstrate that the methods perform comparably to or better than Monte Carlo Tree Search baselines with orders-of-magnitude faster computation, and the results are supported by numerical simulations. The paper, "Risk-Averse Lander Site Selection under Altitude-Limited Information," is by Vikas A. Patel, Mahdi Al-Husseini, Duncan Eddy, and Mykel J. Kochenderfer, submitted 22 Sep 2026.