#ros2humble — Public Fediverse posts

@themagpi

> Raspberry Pi projects?

Solved a month long mystery!

How to manage Raspberry Pi I2C device access inside ROS2/Ubuntu/Docker container **AND** outside the container in Raspberry PiOS Bookworm?

Docker invocation must map both the bus AND the mutex lock folder /var/lock/

#RaspberryPi5 #RaspberryPiOS
#I2C #Mutex #Docker #ROS2humble #Robot #GoPiGo3

@drfootleg Another tip that has been plaguing me for a month!

If you have processes inside a Docker container and other processes outside the Docker container that need mutex protection such as I2C bus or SPI bus accesses, you need to map the bus (obviously) **and** the mutex folder!

I had the sensor access working great but could not figure out why my inside and outside "mutex protected" accesses were colliding...

#GoPiGo3 #Docker #RaspberryPiOS #mutex #ros2humble

Think I solved why my inside Docker (ROS 2) access to I2C INA219 current sensor was colliding with my outside Docker access to the device - forgot to map the /var/lock directory so the mutex is visible from both environments!

#Docker #mutex #ina219 #robot #GoPiGo3 #ros2humble

@drfootleg "XYZZY" RTABmap for now but somewhere deep in "twisty little passages all different" I hope to find:

https://labhorizons.co.uk/2024/07/can-we-learn-from-insect-navigation-to-make-better-autonomous-robots/

#GoPiGo3 #Robots #ros2humble on #RaspberryPi5 in #Docker #ColossalCave

At this reduced transfer rate, the #GoPiGo3 can make a two byte #SPI transfer in 0.0003 seconds, which means it can retrieve the left and right wheel encoder values roughly 1700 times per second - plenty fast enough for my #ros2humble robot to publish #wheelencoders and the resultant #odometry at 30 Hz.

(Again) so excited that my #ros2humble wallfollower.py node drove my #Create3 #robot “WaLI (wallfollower looking for intelligence)” to follow 17 meters of six connected walls!

So far it is subscribing to five topics /ir_intensity (range to wall and obstacle detection), /hazard_detection (bumpers), /ir_opcode (virtual wall), /kidnap_status (lifted by human), and /odom (pose), and a seven state machine managing seven motion actions/reactions.

Now to “parameterize” and “generalize” it.

#SLAM_Toolbox Mapping w/o Localization

Got slam_toolbox mapping with localization turned off, but managed to figure out how to serve up a better looking map from my house floor plan.

The weakness of dead reckoning #odometry becomes very evident with the floorplan map.

Next up - #DeadReckoning #navigation with #ros2humble #nav2 and #map_server

#Create3-Wali #Robot

Dress Rehearsal
Full Load #RaspberryPi5
Power System Test

Full load (1min 4.96): No Throttling - NO PROBLEM.

Wali with 14.4v powered USB hub inside cargo drawer:

(WaLi: Wall follower Looking for Intelligence)

The Pi5 has #ros2humble running in #Docker over PiOS 64-bit Bookworm Desktop

#ROS - #Docker - #RaspberryPi5 !!!

#slam_toolbox async mapping:
- Pi4 15% CPU (2% of RPi4)
- Pi5 5% CPU (1% of RPi5)

Much prefer configuring and running ROS 2 native on #Ubuntu22_04Lts on Pi4 than configuring Docker on Pi5.

rViz2 in Ubuntu 22.04 in VM on Mac OS showing map and path.

slam-toolbox async in Docker on PiOS 64-bit Bookworm on Pi5 (2 ssh sessions)

#GoPiGo3 #robot on Ubuntu 22.04 on Pi4 (4 ssh sessions)

All talking to each other - pretty impressed with #ros2humble