Reliability-Asymmetric Spacecraft Autonomy: Co-Designing a Capable Learned GNC Stack with a Verified, Adaptation-Aware Runtime Shield
Deep-space missions need onboard autonomy that is both capable and certifiable. Rule-based autonomy is certifiable but brittle, while learned autonomy is capable but hard to verify. We present AMPLE-GNC, a three-tier guidance, navigation, and control stack. Its capability path combines a small foundation-model commander that maps natural language to PDDL+, a constraint-screening verifier, and a fault-adaptive controller. All three are bounded by a runtime shield with nine linear-temporal-logic invariants whose predictor soundness is machine-checked by the Kind 2 model checker. On a 6-DOF Basilisk testbed, we make three contributions. First, we deploy an edge commander. Fine-tuning a pretrained 360M model with grammar-constrained decoding gives a hard output-validity guarantee and 84% planner-executable actions. On a de-leaked test, novel-phrasing generalization is 38% exact and 51% action, rising to 48% exact after phrasing-diversity re-finetuning; we separate syntactic validity from semantic accuracy. Second, we introduce a fault-adaptive controller. Rapid Motor Adaptation infers latent actuator faults online and recovers 97.8% of actuator-sign faults and 94.4% of continuous-gain faults within the training randomization envelope. Fault-unaware PD and from-scratch end-to-end RL both score 0%, while the strongest classical-adaptive baseline reaches 55% on continuous gain. Beyond the envelope, a split-conformant retrain scores 57-67%, and adding 4x more in-regime data worsens performance, showing that randomization breadth, not data volume, drives generalization. Robustness is flat under star-tracker noise to 0.005. Third, we show that a latching safe-hold shield can suppress even a capable controller. A split-conformal recovery-deadline certificate with adaptation-aware engagement reconciles safety and recovery, keeping the controller 94.5% autonomous while still catching non-recovery.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers
Runtime assurance (RTA) protects a safety-critical system by switching from an advanced controller to a verified safe controller when a monitored condition is violated. The standard latching rule, which trips on the firs…
Spacecraft Autonomy Levels
As autonomous systems are being developed in multiple industries it has been recognized that a phased approach is needed both for technical development and user acceptance. Partially in response, the automotive and aircr…
Levels of Spacecraft Autonomy
As autonomous systems are being developed in multiple industries it has been recognized that a phased approach is needed both for technical development and user acceptance. Partially in response, the automotive and aircr…
Adversarial Machine Learning Threats to Spacecraft
Spacecraft are among the earliest autonomous systems. Their ability to function without a human in the loop have afforded some of humanity's grandest achievements. As reliance on autonomy grows, space vehicles will becom…
LLMSat: A Large Language Model-Based Goal-Oriented Agent for Autonomous Space Exploration
As spacecraft journey further from Earth with more complex missions, systems of greater autonomy and onboard intelligence are called for. Reducing reliance on human-based mission control becomes increasingly critical if …
Language ModelingLanguage ModellingLarge Language Model