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.

Sign up for GitHub

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

Jump to bottom

Pps with modulations dev multi event #32

Merged
merged 25 commits into from
Oct 20, 2016
Merged

Pps with modulations dev multi event #32

merged 25 commits into from
Oct 20, 2016

Conversation

matejhof
Copy link
Collaborator

This contains mainly:

  1. new definition of receptive fields of taxels (addressing possible bug in 1D binning and enhancement to other than 20 cm range #24), replacing spherical sector and cylindrical patch with a shifted spherical sector - that is not starting at the apex at the taxel, but with a radius currently set to 7 cm: https://github.com/robotology/peripersonal-space/blob/pps-with-modulations-devMultiEvent/lib/src/taxelPWE.cpp#L8 Receptive fields do not rise to infinity anymore.
  2. multiple events/stimuli can be handled at the same time for PPS activations. Maximum response is taken at every taxel. The representation is more efficient now - only events inside the RFs on inidividual taxels are stored in the corresponding representations. Learning was tested and works too, albeit that only for one stimulus.

fixes #27

matejhof added 24 commits August 26, 2016 12:19
@matejhof
improving projectIncomingEvents on vtRFthread side
2df867a
@matejhof
changes to respond to multi-events implemented; testing pending
6080b83
@matejhof
improved debugging outputs
5e91bb2
@matejhof
mini formatting edit
ec12cfe
@matejhof
Merge branch 'pps-with-modulations-devMultiEvent' of https://github.c…
0db2377 
…om/robotology/peripersonal-space into pps-with-modulations-devMultiEvent
@matejhof
cleaning taxels' event vector every iteration
cfbf17a
@matejhof
solved segfault with dumpedVector and improving debug outputs
107df38
@matejhof
small improvements and improving debug outputs
1697cf9
@matejhof
mini - removing unneccessary clear() command
81b343b
@matejhof
new taxel RF checking - no cylinder, only shifted positive and negati…
e80f01d 
…ve spherical sectors (not tested)
@matejhof
mini edit - debug output
453e6af
@matejhof
some fixes to insideRFcheck() - not finished yet
d1c62e2
@matejhof
making taxel RF fatter
3262ba0
@matejhof
small improvements, commented out some debug printfs
b9d3257
@matejhof
scripts cleanup - moving many to bonus so they are not installed
e345019
@matejhof
updating master script
85c88cd
@matejhof
fixed assigning multiple events if relying on memory - not immediate …
ffc861c 
…port input
@matejhof
removing saving to taxels file by default + improving some comments
0bc8c89
@matejhof
working nicely; fixed important bug in nr torso joints initialization
bf8dc50
@matejhof
renaming manageSkinEvents() to managePPSevents()
9484c20
@matejhof
training only if stimulus inside RF of corresponding taxel
84da4a4
@matejhof
keeping redundant 2nd RF check during add/remove sample as warning fo…
66714b0 
…r the moment
@matejhof
learning works - fixed important bug in IncomingEvent4TaxelPWE::getNR…
565509a 
…MTTC()
@matejhof
removing redundant insideRF check
d54c42d
This was referenced Oct 14, 2016
Open
Closed
alecive
alecive reviewed Oct 14, 2016
View reviewed changes
Copy link
Member

@alecive alecive left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I cannot obviously tell anything about the functionalities because I cannot test it, but the code inspection was fine for me. Feel free to merge!

lib/include/iCub/periPersonalSpace/taxelPWE.h
bool removeSample(IncomingEvent4TaxelPWE ie);

/**
* Check if the input sample is inside the Receptive field (i.e. the cone)
* Check if the input sample is inside the Receptive field (composed of a cone and a cylinder)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Isn't this now moved to the new represenation we discussed about (the shifted spherical sector)?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

well spotted. just committed. thanks.

@matejhof
Update taxelPWE.h
9f115f8 
updating comments in header file - new RF
@matejhof matejhof merged commit 06dde93 into pps-with-modulations Oct 20, 2016
@pattacini pattacini deleted the pps-with-modulations-devMultiEvent branch October 20, 2016 13:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@alecive alecive alecive approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@matejhof @pattacini @alecive