why icub will break down?

[0707yiliu]

I change the parameter in redballdemos configuration file config.ini and pf3dTracker.ini

when i give icub a red ball, it will broken down sometime.

And today its torso motor suddenly cut itself off and bacame unuseable.

[pattacini]

Hi @tKsome

For getting help on how to deal with the broken cable, you should open up a dedicated ticket at https://github.com/robotology/icub-tech-support.

For why the robot misbehaved while performing the red-ball task, there might be multiple reasons, including the ball shape, false-positive detections of the ball, the reaching offsets, the speed of the movements, wrong conf files loaded at startup, and the like.

My recommendation is always approaching the demo incrementally:

• configure the demo to use only the head by disabling the arms so that it's safer to check whether the ball gets correctly localized (it should be displayed within the iCubGui).
• check if the conf files we've customized are those actually loaded at startup.
• enable only one arm and make the robot move slowly by increasing the traj_time to something like 3.0 s.

Anyway, be always ready to press the fault-button in time to prevent the robot from colliding with itself or from doing weird things.

[0707yiliu]

This method is right. And i have complicated the first two steps.

When we were doing the red ball tracking experiment, icub sometimes wrote the red ball on its head, which lead the process broken down. In this pose, we cannot use robotmotorgui control the robotic motor.

I suspect it is the parameter configuration of tracker.

Here is my configuration ####################################

configuration file for PF3DTracker

####################################

#############

module name

############# name /pf3dTracker

#############################

parameters of the algorithm

############################# nParticles 600

nParticles number of particles used

accelStDev 30

accelStDev 50 30 15

accelStDev standard deviation of the acceleration noise

insideOutsideDiffWeight 1.5

insideOutsideDiffWeight inside-outside difference weight for the likelihood function

colorTransfPolicy 1

colorTransfPolicy [0=transform the whole image | 1=only transform the pixels you need]

#########################

port names and function

######################### inputVideoPort /pf3dTracker/video:i

inputVideoPort receives images from the grabber or the rectifying program.

outputVideoPort /pf3dTracker/video:o

outputVideoPort produces images in which the contour of the estimated ball is highlighted

outputDataPort /pf3dTracker/data:o

outputDataPort produces a stream of data in the format: X, Y, Z, likelihood, U, V, seeing_object

outputParticlePort /pf3dTracker/particles:o

outputParticlePort produces data for the plotter. it is usually not active for performance reasons.

inputParticlePort /pf3dTracker/particles:i

inputParticlePort recives hypotheses on the ball position from pf3dBottomup.

outputAttentionPort /pf3dTracker/attention:o

outputAttentionPort produces data for the attention system, in terms of a peak of saliency.

#################################

projection model and parameters

#################################

projectionModel [perspective|equidistance|unified]

projectionModel perspective

cameraContext cameraCalibration cameraFile icubEyes1.ini cameraGroup CAMERA_CALIBRATION_LEFT

#######################

tracked object models

#######################

trackedObjectType [sphere|parallelogram]

trackedObjectType sphere

trackedObjectColorTemplate models/red_ball_iit.bmp

trackedObjectColorTemplate models/red_smiley_2009_07_02.bmp

trackedObjectShapeTemplate models/initial_ball_points_36mm_20percent.csv

trackedObjectShapeTemplate models/shape_model_26_30.csv

motionModelMatrix models/motion_model_matrix.csv trackedObjectTemp current_histogram.csv

#######################

initialization method

#######################

initialization method [search|3dEstimate|2dEstimate]

initializationMethod 3dEstimate initialX 0 initialY 0 initialZ 0.5

####################

visualization mode

####################

circleVisualizationMode [0=inner and outer cirlce | 1=one circle with the correct radious] default 0. only applies to the sphere.

circleVisualizationMode 1

#########################

attention-related stuff

#########################

the tracker produces a value of likelihood at each time step. this value can be used to infer if the object it is tracking is the correct one. this is not a very robust way of doing so.

if likelihood>this value, then probably I'm tracking the object. 20Millions is good, 12Millions is the likelihood of Jonas Hornsteins's PC screen (false positive).

20Millions is a good threshold level when you have the right color model. 5M.

likelihoodThreshold 0.0004 attentionOutputMax 250 attentionOutputDecrease 0.99

##########################

image saving preferences

##########################

save images with OpenCV?

saveImagesWithOpencv false

always use the trailing slash here.

saveImagesWithOpencvDir ./graphical_results/

[0707yiliu]

I checked the cable first yestoday and found no broken cable.

When i start-up the robotinterface properly today, the robot can run normally. I guess that after pressing the emergency stop button, the robotic electrical power will lose and its body will lean forward, causing it to fall an the torso.

[pattacini]

I checked the cable first yesterday and found no broken cable.

Good 👍🏻

When I start-up the robotinterface properly today, the robot can run normally. I guess that after pressing the emergency stop button, the robotic electrical power will lose and its body will lean forward, causing it to fall and the torso.

This is actually the intended behavior.

For what's left closing in favor of #25.