Autonomous rendezvous system overcomes simulated spacecraft failures in lab tests
Aerospace EngineeringAstronomy
THE AI ANGLE
Replanning far-rendezvous trajectories using reinforcement learningResearchers tested an autonomous guidance framework called CORTEX that steers servicer spacecraft toward uncooperative targets. The system plans around sunlight windows and autonomously chooses whether to replan a flight path or abort when thrusters fail. Aerospace engineers gain a validated method to handle close-range orbital servicing without input from Earth.
THE TEACHING ANGLE
Engineers can evaluate how an autonomous system should weigh the risk of replanning an approach against retreating to a safe orbit when thrusters fail.Read the original at phys.org Generate teaching or study materials
More in Aerospace Engineering
- Insect-inspired flying robot bounces back after collisionsPhys.org — Technology · October 28, 2026
- Moscow could design an F-22 rival using an AI model from Russia's JPMorgan Chase — Sberbank GigaChat used its LLM for a 'generative design of a new aircraft'TechRadar · October 28, 2026
- HPE is sending its most powerful AI compute platforms to the Moon aboard an all-new lunar roverTechRadar · October 27, 2026
- ‘Autonomy, not flesh’: RAF chief outlines AI drone-powered futureThe Guardian — AI · October 27, 2026
- World's largest cargo drone packs a 50-foot wingspan and 4,000lb payload — but you'll never find a human pilot insideTechRadar · October 27, 2026