Automatic encoding method for deep space exploration autonomous task planning constraint reasoning

Abstract

The invention discloses an automatic encoding method for deep space exploration autonomous task planning constraint reasoning and belongs to the technical field of aerospace deep space exploration. The method comprises the steps of analyzing model characteristics on the basis of establishing a deep space probe system model file, uniformly converting a plurality of predicate types into binary predicates, and extracting variables in predicates to form a to-be-selected variable set; matching variables in a motion with the to-be-selected variable set and screening the variables, establishing a header for describing a table constraint of the motion, inspecting a causal relation of the motion, and merging fixed variables in the header; completing construction of table constraints of the motion through instantiation of the header; converting all motion tables into the table constraints, automatically encoding a deep space probe system model into a constraint form for constraint reasoning. According to the method, the defects in an existing deep space task model that the motion relation is complicated, the workload of manual encoding is high, information input and output are inconvenient and the model is difficult to transplant and maintain in later stage can be overcome, the efficiency for autonomous task planning of a deep space probe is improved and the real-time requirement is satisfied.

Description

technical field [0001] The invention relates to an automatic coding method for deep-space exploration autonomous task planning constraint reasoning, and belongs to the technical field of aerospace deep-space exploration. Background technique [0002] In the deep space environment, based on the perception and understanding of the space environment and the capabilities and status of the deep space probe itself, the deep space probe uses computer software technology, artificial intelligence technology, etc. The selected actions and the resource constraints provided perform reasoning and automatically generate a set of time-ordered action sequences, called a "plan". Once the plan is executed, the state of the detector can be successfully transferred to the desired goal. state. [0003] At present, NASA and ESA have successfully applied autonomous planning technology to deep space probe detection missions. However, as the flight distance of deep space exploration missions has b...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem of autonomous mission planning of deep space detectors, the invention discloses an automatic coding method for deep space exploration autonomous mission planning constraint reasoning. Large workload, inconvenient information input and output, difficult to transplant and maintain later, improve the efficiency of autonomous mission planning of deep space detectors, and meet the real-time requirements of detectors

Images