1
$\begingroup$

I am working on obstacle avoidance and path planning in robotics using X80SV robot. The obstacle avoidance module of the robot works well. The programming language I have used in this work is C#. Next, I wanted to visualize the real-time motion of the robot. What should be done? The robot is equipped with ultrasonic sensors, infrared sensors, camera, human sensors etc.

$\endgroup$

1 Answer 1

2
$\begingroup$

There seems to be two questions in one:

  1. How should I visualise the trajectory (planned and traversed paths)?
  2. How should I combine "ultrasonic sensors, infrared sensors, camera, human sensors etc. " into path planning?

Also, I didn't get how obstacle avoidance is working 'well' (if it is binary obstacle or a gradient based obstacle marking probability fields). While code snippets are the ideal solutions, I would suggest adding more details to the question and the attempts you have tried.

Nevertheless, I shall attempt to solve that problem.

  1. We need visualisation; So, we need an off-board computer. If we want real-time visualisation, we need to transmit data (planned and traversed path) to the off-board computer. Else, we can store this data and at the end of the run, we can just gather the data.

So, my suggestion: Use WiFi/USB/Bluetooth to transmit data back to computer.

  1. We need path planning (for this I am assuming that SLAM isn't needed because we are talking about path planning); Use any path planning technique as described in this http://ai.stanford.edu/~ddolgov/papers/dolgov_gpp_stair08.pdf (most of it assumes binary ostacles - Obstacle is either present or absent) If probabilistic obstacles are considered, it is a kind of local optimisation problem and more details are definitely necessary. https://www.researchgate.net/publication/2287847_Probabilistic_Methods_for_State_Estimation_in_Robotics

  2. How should I fuse sensor data? What is the cheapest / easiest way of detecting a person? (Because of "human sensors") https://stanford.edu/class/ee267/lectures/lecture11.pdf

  3. How do I visualise data? This is the simplest. Use Python/Octave/MATLAB and visualise. There are many plotters that use CSV format. http://lmgtfy.com/?q=visualising+3D+plots (https://in.mathworks.com/help/matlab/2-and-3d-plots.html) (You can also explore GNU Plot, Qti Plot etc)

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.