A Missing Object Search Method Based on Reinforcement Learning Algorithm

Abstract

The present invention provides a missing target search method based on a reinforcement learning algorithm, which includes the following steps: Step S1, data preprocessing: including time and space discretization; Step S2, building a reinforcement learning training environment: building a reinforcement learning training environment, the training environment information includes the expected search cost of objects starting from different locations at different times at different search moments and the probability of transferring to different locations at different search moments; Step S3, Offline training of the spatiotemporal search model: self-adaptive optimization of the state and behavior definitions and models; step S4, online spatiotemporal search decision: based on the spatiotemporal search model trained in step S3, iteratively adopts a greedy strategy to determine the spatiotemporal search sequence and execute the spatiotemporal search . It effectively reduces the search cost of finding the location of the target at the target moment, and completes the target search task under the search cost constraint.

Description

technical field [0001] The invention belongs to the field of missing target searching under the constraint of crowd intelligence perception cost, and in particular relates to a missing target searching method based on a reinforcement learning algorithm. Background technique [0002] Finding missing objects (for example, cars or people) in cities is critical to city safety management. For example, a suspicious car was identified at a certain point in the past. Instructions attached figure 1 Typical application scenarios are shown. The serial numbers represent the waypoints of the vehicle's trajectory from 8:00 to 9:00 on a certain day, including the location of certain key moments (light color). By determining the location of the suspicious vehicle at a specific moment (ie, the target moment) and marking it on the map, and so on, until its approximate trajectory can be grasped. Shortly after this, the police seized the clue and intend to monitor the suspicious vehicle's w...

AI Technical Summary

Problems solved by technology

This presents a huge challenge for finding the target

Images