同步操作将从 ApolloAuto/apollo 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
the localization data is a experimental dataset to verify the availability of localization. It contains localization map(local_map/), vehicle params(params/), sensor recording data(records/). The specific attributes are as follows: duration: 5 mins mileage: 3km areas: city roads in Sunnyvale weather: sunny day
First check and make sure you are in development docker container before you proceed. Now you will need to build from the source.
# To make sure you start clean
bash apollo.sh clean
# Build the full system
bash apollo.sh build_opt
In the downloaded data, you can find a folder named apollo3.5. Let's assume the path of this folder as DATA_PATH.
cp -r DATA_PATH/params/* /apollo/modules/localization/msf/params/
The meaning of each file in the folder
Add config of map path in /apollo/modules/localization/conf/localization.conf
# Redefine the map_dir in global_flagfile.txt
--map_dir=DATA_PATH
This will overwrite the default config defined in global_flagfile.txt
run the script in apollo directory
cyber_launch start /apollo/modules/localization/launch/msf_localization.launch
In /apollo/data/log directory, you can see the localization log files.
cd DATA_PATH/records
cyber_recorder play -f record.*
The localization module will finish initialization and start publishing localization results after around 50 seconds.
python /apollo/scripts/record_bag.py --start
cyber_launch start /apollo/modules/localization/launch/msf_visualizer.launch
First, the visualization tool will generate a series of cache files from the localization map, which will be stored in the /apollo/cyber/data/map_visual directory.
Then it will receive the topics blew and draw them on screen.
If everything is fine, you should see this on screen.
Note:
The visualization tool will show up the windows after the localization module started to published localization msgs to topic /apollo/localization/pose. You can use command cyber_monitor to monitor the status of topics.
If you record localization result in step 6, you will also need to end the recording process:
python /apollo/scripts/record_bag.py --stop
./scripts/msf_local_evaluation.sh OUTPUT_PATH
OUTPUT_PATH is the folder stored recording bag in step 6.
This script compares the localization results of MSF mode to RTK mode.
Note:
Aware that this comparison makes sense only when the RTK mode runs well.
And we can get the statistical results like this
The first table is the statistical data of Fusion localization. The second table is the statistical result of Lidar localization.
The meaning of each row in the table
The meaning of each col in the table
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。