Unmanned autonomous systems (UASs) are intelligent systems endowed with autonomous cognition, motion planning, autonomous decision making and reasoning capabilities. Their goals are designed to perform and complete common tasks in complex, open and dynamic scenarios with limited or even no human participation. In terms of the challenges UASs faced in cross-domain collaborative tasks, such as low efficiency of collaborative perception, poor reliability of Ad Hoc network communication, slow resource scheduling, and conflict-prone task allocation, this paper explored how to combine large models and generative artificial intelligence (GAI) technology to construct the“compute-control-test”embodied cognitive intelligence framework of UASs integrating“large model + autonomous unmanned systems + artificial intelligence generated content(AIGC)”. It will provide valuable reference for advancing the technological implementation and practical deployment of UASs with embodied cognitive intelligence.

unmanned autonomous systems (UASs)  /  embodied intelligence  /  foundation models  /  generative artificial intelligence  /  general intelligent machines