Releases: keenon/nimblephysics
v0.6.9 Adding C3D loader support
Debugged support for C3D loader
v0.6.8 Scaling up multi-trial autoscaling
The multi-trial autoscaling in MarkerFitter
now downsamples the input if it's faced with too many trials at once, or too many total frames of input.
v0.6.7 Multi-trial scaling for MarkerFitter
The biomechanics.MarkerFitter
object now supports jointly scaling over multiple trials simultaneously, to support that feature in BiomechNet.
v0.6.6 Adding MarkerFitter marker regularization
Bumping to v0.6.6 for MarkerFitter offset regularization
v0.6.5 Supporting rich plots in the GUI
See python/nimblephysics_examples/rich_plots.py
for example usage of the new APIs.
v0.6.4 Improvements to MarkerFitter
Improving MarkerFitter
:
- Adding confidence bounds to joint estimates
- Supporting joint axis solutions in addition to joint centers
- Exposing more sophisticated GUI methods from C++
v0.6.3.1 Bug fixes
- Fixing a hidden dependency on
pybullet
for the new PyBullet rendering support. That's now an optional import, so it's possible to usenimblephysics
withoutpybullet
. - Fixing the dimensions of default color arguments to
GUIStateMachine
to be 4-vecs, to include an alpha channel.
v0.6.3 Customizable contact + OpenSim output features
We've added an alpha API for customizing how Nimble computes contact impulses over a timestep, though we do not yet support differentiating through custom contact functions.
We've also added some OpenSim export functionality, exporting .mot's and an XML file that's readable by OpenSim's scale tool to rescale .osim files.
Adding alpha channel support to web GUI
This contains a number of minor bug fixes, and one breaking change: the web GUI now supports transparency. That means that all the setObjectColor
calls to the web GUI will require a vector of length 4, following an RGBA scheme.