In addition to Weibo, there is also WeChat
Please pay attention
WeChat public account
Shulou
2025-04-04 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > Servers >
Share
Shulou(Shulou.com)05/31 Report--
This article mainly introduces the relevant knowledge of the architecture of the Apollo prediction module, the content is detailed and easy to understand, the operation is simple and fast, and has a certain reference value. I believe you will gain something after reading this article on the architecture of the Apollo prediction module. Let's take a look at it.
I. brief introduction
The prediction module studies and predicts the behavior of all obstacles detected by the perception module. The prediction module receives obstacle data and basic perceptual information, including position, direction, velocity and acceleration, and then generates probabilistic prediction trajectories for these perceived obstacles.
Note: the prediction module only predicts the behavior of obstacles, not the car itself. The planning module plans the trajectory of the car itself.
II. Input
The obstacle information obtained from the perception module.
The location information obtained from the positioning module.
The planning trajectory of the previous calculation period obtained from the scale module.
III. Output
The obstacle with the predicted trajectory and its priority, because the priority of each independent scene is different, the current scheme also needs to calculate the priority of the obstacle. Priorities include: ignore, caution, and normal (default).
IV. Function
As shown in the following figure, the prediction module consists of four main functional modules: container, scene analyzer, evaluator and predictor. Containers, evaluators, and predictors are already available in Apollo 3.0. In Apollo 3.5, we have introduced the scene function module because we have adopted a multi-scene-based approach to improve the autopilot ability of Apollo.
The composition of ▲ prediction module
Container
The container stores input data from the subscription channel, and currently supported inputs include perceived obstacles, car positioning information and car planning tracks.
Scene analyzer
The prediction module also uses the output information of the positioning module and the planning module as input, and its structure is as follows:
This is the end of the article on "what is the architecture of the Apollo prediction module?" Thank you for reading! I believe you all have a certain understanding of the knowledge of "what is the architecture of the Apollo prediction module". If you want to learn more, you are welcome to follow the industry information channel.
Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.
Views: 275
*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.
Continue with the installation of the previous hadoop.First, install zookooper1. Decompress zookoope
"Every 5-10 years, there's a rare product, a really special, very unusual product that's the most un
© 2024 shulou.com SLNews company. All rights reserved.