Road condition perception model based on adaptive dynamic path planning algorithm and time series

The traditional road condition perception model mainly uses the neural network algorithm, which ignores the impact of traffic data uncertainty, making the perception error of the road condition greater. Therefore, a road condition perception model based on adaptive dynamic path planning and time series is proposed in this paper. By acquiring the traffic information data that can represent the state of road condition, the time series algorithm is used to repair and fill the collected data, and the random data is transformed into a stationary data sequence. The traffic network is gridded to extract the spatial features of vehicles. On this basis, the adaptive dynamic path planning algorithm is used to determine the upper limit of the adaptive sensing range, and the maximum posterior probability of the road condition data is calculated to complete the construction of the road condition sensing model. The proposed model is applied to the perception of actual traffic conditions. The experimental results show that the designed model has lower perception error and better perception effect, with a perception error less than 20%.