feat(map_based_prediction): output rich prediction paths based on lanelet map for crosswalk users

[satoshi-ota]

Description

Now, cars, motorcycles, and trucks (buses) have rich prediction paths based on lanelet map, but for other objects, they have only naïve linear prediction path based on estimated speeds and time horizon.

In this PR, I updated map_based_prediction logic in order to output map based prediction path for crosswalk users.

Related Link: #920

simplescreenrecorder-2022-05-18_14.16.20.mp4

Algorithm

Who is crosswalk users ?

• pedestrian
• bicycle

Target object (who has additional rich prediction path)

Crosswalk users who satisfies at least one of the following conditions are considered to have the intention to cross the crosswalk, and map_based_prediction node outputs additional prediction path based on map and estimated object velocity.

• move toward the crosswalk
• stop near the crosswalk

Map base prediction path for crosswalk users

The map_based_prediction node outputs additional prediction path from the target object's position to a reachable crosswalk entry point. If the target object is outside the road, the number of prediction paths are one per crosswalk.

If the target object is inside the road or crosswalk, the number of prediction paths are depend on whether object is moving or not. If the object is moving, it outputs a prediction path toward an exit that existed in the direction of movement, but if the object has stopped, it is impossible to infer which exit points the object want to go, so the node outputs prediction paths toward both side exit point.

If there are some crosswalks around the target object, multiple map based prediction paths may be output. On the other hand, even if the object is moving toward a crosswalk, the predicted path across the road is not output.

Related links

Tests performed

Notes for reviewers

Pre-review checklist for the PR author

The PR author must check the checkboxes below when creating the PR.

• I've confirmed the contribution guidelines.
• The PR follows the pull request guidelines.

In-review checklist for the PR reviewers

The PR reviewers must check the checkboxes below before approval.

• The PR follows the pull request guidelines.
• The PR has been properly tested.
• The PR has been reviewed by the code owners.

Post-review checklist for the PR author

The PR author must check the checkboxes below before merging.

• There are no open discussions or they are tracked via tickets.
• The PR is ready for merge.

After all checkboxes are checked, anyone who has write access can merge the PR.

[codecov]

Codecov Report

Merging #922 (fcf0f5f) into main (940f912) will decrease coverage by 0.06%.
The diff coverage is 0.00%.

@@           Coverage Diff            @@
##            main    #922      +/-   ##
========================================
- Coverage   9.59%   9.52%   -0.07%     
========================================
  Files       1042    1042              
  Lines      71835   72333     +498     
  Branches   15588   15588              
========================================
- Hits        6890    6889       -1     
- Misses     58707   59205     +498     
- Partials    6238    6239       +1     

Flag	Coverage Δ		*Carryforward flag
differential	0.00% <0.00%> (?)
total	9.57% <0.00%> (-0.01%)	⬇️	Carriedforward from 5a89653

*This pull request uses carry forward flags. Click here to find out more.

Impacted Files	Coverage Δ
...map_based_prediction/map_based_prediction_node.hpp	0.00% <ø> (ø)
...based_prediction/src/map_based_prediction_node.cpp	0.00% <0.00%> (ø)
...eption/map_based_prediction/src/path_generator.cpp	0.00% <0.00%> (ø)
...planning_evaluator/src/planning_evaluator_node.cpp	37.11% <0.00%> (-1.04%)	⬇️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 940f912...fcf0f5f. Read the comment docs.

[satoshi-ota]

test at odaiba

• pedestrian stops in crosswalk

• pedestrian stops in road

• pedestrian stops in sidewalk

• pedestrian walks away from crosswalk

simplescreenrecorder-2022-07-01_15.45.24.mp4

• pedestrian walks toward crosswalk

simplescreenrecorder-2022-07-01_15.44.22.mp4

• pedestrian walks in road

simplescreenrecorder-2022-07-01_15.43.45.mp4

• pedestrian walks in crosswalk

simplescreenrecorder-2022-07-01_15.43.07.mp4

[satoshi-ota]

@yukkysaito Could you review this PR ? 🙇

[github-actions]

Documentation URL: https://autowarefoundation.github.io/autoware.universe/pr-922/
Modified URLs:

• https://autowarefoundation.github.io/autoware.universe/pr-922/perception/map_based_prediction/

[satoshi-ota]

@yukkysaito I added documentation of the prediction algorithms for crosswalk user in 5a89653

[yukkysaito]

LGTM