ROS Resources: Documentation | Support | Discussion Forum | Service Status | Q&A answers.ros.org

Autoware Hackathon - London

It is my pleasure to invite you to the next Autoware Hackthon, hosted at Parkopedia’s offices in London.

As usual with hackathons, there will be lots of flexibility for everyone to work on the topic that is of most interest to them. Suggested topics of interest to us are

  1. to port the minimal self-driving car stack that Parkopedia has developed in ROS1 to ROS2 and submit MR’s to Autoware.Auto.
  2. to integrate Lanelets and OSM XML maps into Autoware.ai

Feel free to propose your own topics.

Dates:
25th - 27th September

Address:
1st Floor Apex House
29-35 Long Lane
London
SE1 4PL

Please indicate if you plan to attend by replying to this thread. I need to ensure enough space is available.

On 26th (Thursday evening), feel free to join in with the London Self-Driving Car Meetup at the same venue. Please register for the event.

1 Like

Great news! Happy to participate.
Antonis

Would love to participate, but the working day dates make it impossible :frowning: Why not plan for a weekend?

Unfortunately clashes with linaro connect. Would love to attend the next one.

Most of the people working on Autoware seem to be doing so through their company, which means we are able to get more people to join during the week than on a weekend.

@yunus.caliskan, I’ve just sent you an invitation on a Parkopeda letterhead following your request. If anyone else has a similar request, please let me know as soon as possible!

1 Like

Please sign up if you plan to attend! There will be a live link for those who want to join in remotely.

In an effort to get the Autoware.Auto implementation of NDT as high quality as possible, @yunus.caliskan and I have been hard at work coming up with an initial design and supporting documents for NDT. You can find them listed below:

  1. Literature review
  2. High level design
  3. Failure analysis
  4. APIs and architecture
  5. Psuedocode/Review of Autoware.AI implementation
  6. Metrics

Of these, I would 100% recommend anyone planning on working on NDT take a look at our currently proposed API and architecture (point 4, work in progress). The psuedocode (5), and high level localization architecture/design (2) might also be useful to skim through for a higher-level overview.

Further, if anyone has suggestions for improvements in any of these documents, those are super welcome too.

Finally, based on the proposed API (which is prospective; feel free to diverge or make or suggest changes), I would like to suggest the following work packages or parts of the proposed architecture that any one person can grab:

  1. Map publisher (pcd -> publish map)
  2. Map (format) validation
  3. PointCloud2 -> NdtRepresentation
  4. Adapt voxel grid to make a plain NdtRepresentation
  5. Some kind of simple Point representation for scan
  6. Newton’s method
  7. Simple line search
  8. Gradient and hessian computation in P2D optimization problem
  9. LocalizerBase
  10. initial guess stuff
  11. LocalizerBaseNode

  1. NdtLocalizer
  2. NdtLocalizerNode

Where I would guess the first 11 or so items can be done independently, and the last two should be done jointly in the final integration.

For the map-related items (1-3), I would like to suggest the following format in PointCloud2 (there’s no other good place to document this):

// PointCloud2
fields = {
  // centroid
  PointField{"x", 8, FLOAT64, 1},
  PointField{"y", 8, FLOAT64, 1},
  PointField{"z", 8, FLOAT64, 1},
  // covariance, row major
  PointField{"cov_xx", 8, FLOAT64, 1},
  PointField{"cov_xy", 8, FLOAT64, 1},
  PointField{"cov_xz", 8, FLOAT64, 1},
  PointField{"cov_yy", 8, FLOAT64, 1},
  PointField{"cov_yz", 8, FLOAT64, 1},
  PointField{"cov_zz", 8, FLOAT64, 1},
}

@Brian_Holt @Antonis_Skardasis @esteve If you could forward this information to anyone else who you know is attending the hackathon, that would be great!

  1. to integrate Lanelets and OSM XML maps into Autoware.ai

Unfortunately, I wouldn’t be able to participate the hackathon, but if you are planning to integrate lanelets into autoware.ai, I would like to share my work that I have been working on for last few weeks.

This is the issue thread about lanelet2 integration. https://gitlab.com/autowarefoundation/autoware.ai/autoware/issues/17

and here’s my list of branches related to Lanelet2. Some are already merged into autoware.ai main repository.

messages repository
feature/lanelet2_msgs (MR merged)
Common repository
feature/lanelet2_extension_mr (This is library to handle lanelet2, MR merged)
feature/lanelet2_loader_mr (MR merged)
core_perception
feature/lanelet2_feat_proj_mr (MR under review)
feature/lanelet2_imm_ukf_track
core_planning
feature/lanelet2_decision_maker
feature/lanelet2_velocity_set
feature/lanelet2_lane_rule (MR under review)

For those who would like to join remotely, feel free on https://zoom.us/j/4048290287. I’ll keep it open as long as I can.