Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improve dynamic_obstacle_avoidance_module #7634

Closed
8 tasks done
beyzanurkaya opened this issue Jun 23, 2024 · 1 comment
Closed
8 tasks done

Improve dynamic_obstacle_avoidance_module #7634

beyzanurkaya opened this issue Jun 23, 2024 · 1 comment
Assignees
Labels
component:planning Route planning, decision-making, and navigation. (auto-assigned)

Comments

@beyzanurkaya
Copy link
Contributor

beyzanurkaya commented Jun 23, 2024

Checklist

  • I've read the contribution guidelines.
  • I've searched other issues and no duplicate issues were found.
  • I've agreed with the maintainers that I can plan this task.

Description

The main issue: #7485

The dynamic_obstacle_avoidance_module currently has several limitations that hinder its performance and reliability. Specifically:

1. Inaccurate Drivable Area: #7684
2. Stability Issues: #7689
3. Expansion of drivable area: #7690

  • Limited avoidance: The module can only shift the vehicle up to 0.5 meters to avoid obstacles. Exceeding this limit causes the node to crash.
  • Inability to change lanes: The module cannot change lanes when necessary when avoiding dynamic objects.

Purpose

The purpose of this issue is to enhance the dynamic_obstacle_avoidance_module by addressing the current limitations. The goal is to improve the module's flexibility, reliability, and overall performance in dynamic obstacle avoidance scenarios.

Possible approaches

1. Correct cutting of the drivable area:

  • Enhancing the current algorithm to accurately trim the drivable area around dynamic obstacles.

2. Increase Stability:

  • Perform extensive testing and debugging to identify stability issues.
  • Improve the cutting algorithm of the drivable area according to the debugging result.

3. Expand Drivable Area:

  • Develop algorithms to dynamically adjust the drivable area based on obstacle detection.
  • Refactor the module to handle shifts greater than 0.5 meters without causing crashes.
  • Modify the obstacle avoidance algorithm to allow safe lane changes when avoiding dynamic obstacles.
  • Integrate the ability to expand the drivable area to accommodate larger avoidance maneuvers temporarily.
  • Ensure the expanded drivable area maintains safety and compliance with road regulations.

Definition of done

  • The module allows the EGO vehicle to safely change lanes when avoiding dynamic obstacles.
  • The module can handle shifts greater than 0.5 meters without crashing.
  • The module operates consistently and stably under a variety of dynamic obstacle scenarios.
  • The module can dynamically expand the drivable area as needed to effectively avoid obstacles.
  • Documentation is updated to reflect the changes and new capabilities of the module.

By addressing these areas, the dynamic_obstacle_avoidance_module will become more robust, flexible, and capable of handling complex dynamic obstacle scenarios effectively.

@beyzanurkaya beyzanurkaya added the component:planning Route planning, decision-making, and navigation. (auto-assigned) label Jun 23, 2024
@beyzanurkaya beyzanurkaya self-assigned this Jun 23, 2024
@beyzanurkaya beyzanurkaya changed the title Improve dynamic_obstacle_avoidance_module [Autoware Labs] Improve dynamic_obstacle_avoidance_module Jun 23, 2024
@beyzanurkaya beyzanurkaya changed the title [Autoware Labs] Improve dynamic_obstacle_avoidance_module Improve dynamic_obstacle_avoidance_module Jun 24, 2024
@brkay54 brkay54 moved this to In Progress in Autoware Labs Jun 24, 2024
@brkay54 brkay54 moved this from In Progress to Backlog in Autoware Labs Jul 28, 2024
Copy link

stale bot commented Aug 24, 2024

This pull request has been automatically marked as stale because it has not had recent activity.

@stale stale bot added the status:stale Inactive or outdated issues. (auto-assigned) label Aug 24, 2024
@stale stale bot removed the status:stale Inactive or outdated issues. (auto-assigned) label Sep 5, 2024
@mitsudome-r mitsudome-r moved this from Backlog to Done in Autoware Labs Sep 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:planning Route planning, decision-making, and navigation. (auto-assigned)
Projects
No open projects
Status: Done
Development

No branches or pull requests

1 participant