Repository navigation
Conversation
Implement a CNN model for UAV perception that maps RGB camera images to continuous control outputs.
This script handles image preprocessing and dataset collection for UAV neural perception. It reads image paths and associated actions from a CSV file and collects data using ROS.
This script implements a dataset for image preprocessing and ROS data collection, including a custom Dataset class and a function to collect images and associated actions.
This script trains a CNN perception model for behavior cloning using a dataset specified in a CSV file. It includes functionality for training, validation, and saving the best model weights.
The script trains a CNN perception model using behavior cloning on image data. It includes data loading, model training, validation, and saving the best model weights.
Add local regression tests for model, preprocessing, and safety clipping.
Member
|
不要一个个添加，否则会受到不必要的邮件，暂时改为草稿，等做好准备后再打开 |
donghaiwang
marked this pull request as draft
October 7, 2026 13:42
Document the UAV neural perception system architecture, algorithm principles, and operational steps.
Updated the demo image link in the README file.
Enemy52
marked this pull request as ready for review
October 7, 2026 15:40
donghaiwang
requested changes
Oct 11, 2026
Member
There was a problem hiding this comment.
一般在文档中方运行效果，操作在文档中说清楚就行，而且文档应该都放在docs目录下，生成网页
| ___ | ||
|
|
||
| ## 参考文献 | ||
| - [无人机神经网络视觉感知（任务②）](./air/uav_neural_perception.md) |
Member
There was a problem hiding this comment.
提交前先用mkdocs serve 检查效果是否符合要求
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
修改概述:
新增无人机键盘飞行控制模块，支持 roslaunch 一键启动
修改的详细描述
经过了什么样的测试?
运行效果（动图、视频、图片、链接等）
修改所对应的前后效果（代码/网页）：
所使用具体的大模型声明：
使用了豆包大模型辅助生成代码与文档
第二次作业（task2）：uav_neural_perception
修改的详细描述
运行环境
经过了什么样的测试？
声明
本项目使用大模型辅助撰写，作者对全部内容负责。
