feat(behavior_velocitiy_planner): predict front vehicle deceleration in intersection and temporarily stop

[soblin]

Description

The ego will make a temporal stop if

• the stop position of front vehicle is predicted to be in stuck area and
• the position the length of ego [m] behind that stop position is in detection area based on it

to avoid the case where the ego follows the front vehicle, then the front vehicle stops just before the crosswalk, and so the ego keeps stopping in the opposite lane, to block/collide with the upcoming vehicle after all.

Tests performed

planning simulation

[0:39]：the ego temporarily stops
[0:50]：restart

frontcar_decel_stuck_area-2022-06-28_14.04.09.mp4

Scenario simulation comparison

I prepared a case where (1) the ego and front vehicle both make a right turn (2) the vehicle decelerate and stop before the crosswalk (3) then other two vehicles enter the intersection.

Without this PR the ego collides with the upcoming vehicles.

without_PR-2022-07-05_07.52.03.mp4

With this PR:

with_PR-2022-07-05_07.45.27.mp4

Notes for reviewers

By default the flag enable_front_car_decel_prediction is set to false as of now. The parameter assumed_front_car_decel should be determined based on a real experiment.

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 #1194 (0883564) into main (99a4ea6) will decrease coverage by 0.03%.
The diff coverage is 0.00%.

@@            Coverage Diff             @@
##             main    #1194      +/-   ##
==========================================
- Coverage   10.12%   10.08%   -0.04%     
==========================================
  Files        1118     1118              
  Lines       77393    77674     +281     
  Branches    17990    18210     +220     
==========================================
  Hits         7835     7835              
- Misses      62095    62340     +245     
- Partials     7463     7499      +36     

Flag	Coverage Δ		*Carryforward flag
differential	4.63% <0.00%> (?)
total	10.10% <0.00%> (ø)		Carriedforward from 99a4ea6

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

Impacted Files	Coverage Δ
...e/scene_module/intersection/scene_intersection.hpp	0.00% <ø> (ø)
...ty_planner/src/scene_module/intersection/debug.cpp	0.00% <0.00%> (ø)
..._planner/src/scene_module/intersection/manager.cpp	0.00% <0.00%> (ø)
...c/scene_module/intersection/scene_intersection.cpp	0.00% <0.00%> (ø)
...ity_planner/src/scene_module/intersection/util.cpp	0.00% <0.00%> (ø)

---

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 aa576c0...0883564. Read the comment docs.

[kyoichi-sugahara]

Does the error accumulate because the distance is not calculated along the lane?
for example

const auto arc_position_p1 = lanelet::utils::getArcCoordinates(ego_lane_with_next_lane, p1);
const auto arc_position_p2 = lanelet::utils::getArcCoordinates(ego_lane_with_next_lane, p2);
const double delta = arc_position_p2.length - arc_position_p1.length;

[1222-takeshi]

Please change the intersection.param.yaml at tier4_planning_launch and autoware_launch.

[soblin]

@1222-takeshi I reflected your suggestions. I think it's ready to be merged

[1222-takeshi]

LGTM