Tag: Team Status Reports

Significant Risks

• Battery life: we’re currently not seeing the expected longevity from the single pack, so may have to go to 2 packs in parallel
• Navigation Stack compiles and runs, moving on to tuning configuration parameters and sensor data for more accurate results with path planning and movement

Design Changes

• None to report on hardware side
• We have updated the Roomba library and changed the serial baud rate. This has enabled the odom topic in ROS. Seems to be good enough to get basic path planning working, but needs more testing.

Schedule/PM

• Slightly behind on test/integration, will be making use of 2 week slack time

We do have some photos to add, but sadly wordpress isn’t allowing uploads 🙁

Significant Risks

• Roomba odometry data
  • The Roomba provides very unreliable odom data. This is backed by many complaints found online about its unreliability.
  • This poses an issue for other systems that rely on odom, such as navigation, and gmapping (an alternative SLAM engine that produced worse results when compared to hector SLAM).
  • During navigation to a target goal, the Roomba would just spin in a circle.
  • We plan on using laser scans to replace odometry data.
• Transparent Objects
  • Transparent objects, such as windows, produce unreliable maps. To create better quality maps, we have blocked the bottoms of windows that are inline with our lidar system.
  • We are not sure how this will affect localization, further testing is necessary to see if windows need to be blocked during operations.

Design Changes

• Due to the aforementioned issues with Roomba odometer data, we have decided to use laser scans to produce odom data.

Collaborated on Navigation stack bring up.

• We were able to produce odom data by using the laser_scan_matcher package for ROS.

• We have successfully setup navigation on the Xavier NX. We were able to produce a global path to the target, but were unable to get the Roomba to follow the path (it just turned in a circle).

Significant Risks

• LiDAR mapping
  • When we attempted mapping HH1307, the system had trouble with recognizing windows as walls. While mapping we used tethered driving, which required us moving behinds the robot, so we may have impacted the accuracy of the map. Now that we have tele-op functionally working, we will attempt mapping again. Additionally, we will also setup our backup LiDAR system (RealSense L515) to see if it has similar issues.
• Bin CV with movement
• Ros Navigation Stack Setup
  • Need to attempt setting up navigation, but this is limited by our understanding of ROS. Additionally, navigation is limited by the map quality produced by SLAM, so mapping is a hard dependency as of now.

Design Changes

No design changes were made, but we did buy a USB network adapter so we can connect to the Jetson wirelessly if using the AGX. This will allow us to remote access for debug, monitoring, and tele-op for driving, map creation.

Photos

 

The most significant project risk at this point is successful integration of various components. We are making good progress on getting individual components working, but because there are so many hardware and software elements it will be a challenge to complete this on time. For mitigation, there’s not a ton we can do, other than adhere to the schedule and use the built-in SLACK time as necessary; though we have obtained backup items in case the Jetson Xavier AGX and/or SLAMTEC LiDAR do not meet our requirements.

There were no major changes to the overall design or its requirements since the last status report. Our current implementation details can be found in the full design report.

As a team we spent most of our time this week on the design report, so that’d be the biggest artifact produced. We have also got a POC for SLAM running  on the Jetson using ROS and hector SLAM.

Q: As you’ve now established a set of sub-systems necessary to implement your project, what new tools have your team determined will be necessary for you to learn to be able to accomplish these tasks?
A: As we have transitioned from using Matlab to ROS, the team must learn ROS as it will be the framework used for controlling the robot and implementing SLAM.