Space traffic is the term used to describe the increasing orbits occupied by
various objects, satellites, space debris, spacecraft, and modules of orbital space
stations, which is a growing concern. The overbearing occupation of the orbital space
increases the likelihood of a collision that may generate more debris and make that
region of orbit useless. Space Traffic Management (STM) is important for the
coordinated and efficient use of the orbits around Earth, as it involves the tracking,
monitoring, and predicting of space object collisions, and taking measures against
them. Artificial Intelligence (AI) can benefit STM in improving elements such as
tracking, collision forecasting, and decision-making. In addition, it can detect the
change in the new orbit patterns, work collision forecasts, and enable the capture and
disposal of the debris. Autonomous Space Traffic Management is an AI-based system
of orbital traffic surveillance and management akin to air traffic management in its
operations. It is predictive, provides surveillance of orbits, and coordinates techniques
for placing and removing satellites from orbit safely and efficiently. Although the STM
supports minimizing collision probabilities, enhancing traffic management, and
achieving environmental sustainability within the orbits of Earth, it still has problems
regarding data interoperability, data protection, and policy issues. Collaboration among
nations, agencies, and private companies is essential for successful STM
implementation in space operations. On-board autonomous systems with AI sensors
enable satellites to recognize, classify, and track objects independently. Real-time
anomaly detection is achievable with AI systems. This paper overviews the integration
of AI technologies in space traffic management for space exploration in detail.
Keywords: AI, ASTM, ISRO, Sensors, Space, STM.
