Artificial intelligence advances space robot autonomy and safety
Artificial Intelligence-Enabled Space Robot Operations: Technologies, Challenges and Prospects
Robotics
Summary
Operating robots in space is difficult because they must work for long times, touch and handle objects, and do many tasks without humans guiding them. The authors review how artificial intelligence and robot learning can make space robots smarter and more adaptable. They explain challenges like limited data, unique space conditions, and safety needs. They also outline technologies for building, training, and deploying these AI capabilities in space robots and suggest future research directions.
What this means in practice
- •For space mission planners: Design more autonomous space robot operations that safely handle complex tasks with limited human control.
- •For robotics engineers: Develop new robot control systems using AI techniques optimized for onboard resource and space environment constraints.
A survey. It maps existing work.
Authors
Zeyuan Huang, Gang Chen, Zixuan Hao, Guoqin Tang, Junyi Zong, Guoyou Ban, Jiale Wang, Haoyang Lv, Chaoqian Ren, Sitong Liu
Abstract
Space robots are increasingly expected to perform long-duration, contact-rich, and multi-stage operations with limited human intervention. Recent advances in artificial intelligence (AI), robot learning, and embodied foundation models provide new opportunities to improve the autonomy and adaptability of such systems, but their transfer to space is constrained by scarce mission data, space-specific dynamics and sensing conditions, limited onboard resources, and stringent safety requirements. This article reviews artificial intelligence-enabled space robot operations (AI-SRO) from a capability-building perspective. We first summarize representative operational scenarios, autonomy trends, and space-specific constraints. We then establish a three-layer technical framework comprising capability foundations, capability formation, and capability deployment/evolution. Within this framework, we review simulation environments, datasets and benchmarks; task and environment understanding, state perception, decision-making and planning, and action execution; and onboard deployment, ground-to-space adaptation, continual learning, and capability transfer. Finally, we propose key research directions toward trustworthy simulation and data, open-world multimodal cognition, long-horizon safe decision-making, physically constrained policy learning, and space computing infrastructures.