Code Monkey home page Code Monkey logo

dynamic_obstacle_detector's People

Contributors

noeperez avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

dynamic_obstacle_detector's Issues

A red dot appears near the sensor and it sometimes changes to a blue dot

Hello.
I'm trying to use this detector in a real environment, but when I look at it in rviz, I see a red dot (from the "/dynamic_obstacles/points" topic) near the sensor. The robot reacts to this dot and rotates or gets stuck. This point keeps appearing even when I disable the display of obstacles from Lidar. Also, sometimes the point changes to a blue point, which is a candidate for a dynamic obstacle. Can you tell me what causes this?
The attached image shows a red dot near the wheelchair. The sensor is mounted on the left side of the wheelchair. In the attached image, the scan data is displayed, but the dot will remain displayed even if LaserScan is unchecked in rviz.
Screenshot from 2022-01-19 15-13-44

When the dynamic close to the robot, not estimate the dynamic obstacle state

hello, I meet a problem when I use your code, when the dynamic is far away from the robot, the code can predict and estimate the dynamic obstacle state, and can display in the rviz, but the dynamic obstacle is close to the robot, the code not good, the topic of /dynamic_obstacle will not estimate the state, and the rviz not display the obstacle marker.

Thanks###

Detect non-existent pedestrian

Hello.
I recently had a question on SFWPlanner. Since you said it was most likely a recognition problem, I'll ask here. When I displayed the distance to pedestrians during the simulation, the values were generally correct, but occasionally a non-existent pedestrian was detected and the distance to that pedestrian was output. I understand that this detector is a simple one, so some false positives are inevitable, but I would like to know if there are any parameters that should be changed to reduce false positives.

Use this detector in a real environment

Hello.
When I try to use this detector in a real environment, I get a lot of blue dots on rviz. On the other hand, with the same parameters, in the simulated environment, blue dots are displayed only in the area where there are pedestrians. Is this detector not so suitable for the real environment? Or can it be solved by adjusting the parameters?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.