Summary
Capturing and stabilizing tumbling space debris is difficult because the debris moves unpredictably and its properties are unknown. The paper shows how a single smart controller, trained with a new form of reinforcement learning, can guide a spacecraft with two arms to approach, grab, and stop the spinning debris without needing detailed prior information. The controller learns to handle different phases of the task smoothly and respects physical limits like force and collisions, even when sensing is noisy and the debris shape varies. This approach works reliably in thousands of simulated tests and adapts to new debris shapes and masses without extra training.
What this means in practice
- •For spacecraft control engineers: Develop controllers for active debris removal missions that guide robotic arms to capture and stabilize tumbling objects without prior detailed knowledge.
- •For robotic system designers: Design dual-arm free-flying robots that execute complex multi-phase tasks under physical and sensing constraints using learned policies with phase gating.
Authors
Álvaro Belmonte-Baeza, Celia Redondo-Verdú, José L. Ramón, Miguel Cazorla, Leonard Felicetti, Jorge Pomares
Abstract
Active debris removal requires a servicer spacecraft to approach a non-cooperative tumbling object, capture it, and arrest its rotation. This sequence is conventionally divided among phase-specific controllers, each depending on knowledge of the target's inertia, a dedicated grappling fixture, or a hand-designed switch at the contact-rich seam where such pipelines are most fragile. We show that a single constrained reinforcement learning policy can execute the entire mission, driving a dual-arm free-flying servicer from free-space closing through friction-based fixture-free capture to full detumbling of a target whose mass and inertia are unknown and whose state is observed only through noisy estimates. The enabling mechanism is a smooth proximity gate applied at three loci of a constrained Markov decision process. In the reward it induces the phase structure rather than imposing it; in the action space it forecloses a degenerate grab-and-pull exploit as a hard guarantee; and in the constraint set it resolves a normalization failure of constraint-based learning, in which a constraint spanning phases that load it unequally is rendered nearly inert in the phase where precision matters most. Both the failure mode and the remedy apply to any multi-phase problem of this kind. Over 1000 randomized trials the policy succeeds in 99.5% while holding its contact-force, actuator, base-reaction and collision limits throughout, transfers zero-shot to unseen geometries and centre-of-mass offsets, and extrapolates across a tenfold range of target mass.