目标运动状态量的估计方法、装置及设备、存储介质
By acquiring the target's pose information and determining the initial velocity using Kalman filtering or least squares method, and then optimizing based on state error, the problem of inaccurate estimation of target motion change state variables in autonomous driving perception is solved, and the accuracy of velocity estimation is improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI MAINLINE TECH CO LTD
- Filing Date
- 2023-03-31
- Publication Date
- 2026-07-17
AI Technical Summary
Existing autonomous driving perception systems, when tracking targets, suffer from divergent calculation results due to the filtering-based state estimation method. This leads to reduced smoothness and robustness of the state quantity estimation curve, resulting in inaccurate estimated state quantities.
By acquiring the target's pose information at M consecutive time points, the initial velocity is determined using Kalman filtering or least squares method, and the initial velocity is optimized based on the Nth state error until the target velocity at each time point is obtained.
It improves the accuracy of the state variables estimation results of target motion changes, reduces the bias in velocity estimation, and enhances the accuracy of velocity estimation.
Smart Images
Figure CN116466707B_ABST