Closed GiulioRomualdi closed 8 months ago
Reading just the header, I was a bit puzzled by the word
dummy
. I interpretdummy
usually as a placeholder, so it is not clear to me why you want to generate adummy
? Candummy
be removed is the resulting output is actually well formed?
Reading the cpp
I understood that the dummy
stuff is basically filled with zeros. At this point, I would simply suggest to specify this in the doc
In https://github.com/ami-iit/bipedal-locomotion-framework/pull/771/commits/ae629760046a4d5cc01c897d12846254aaa80b00 I improved the documentation regarding the dummy
Hi @paolo-viceconte and @S-Dafarra I removed the hardcoded size of the vectors in MANN https://github.com/ami-iit/bipedal-locomotion-framework/pull/771/commits/e19b84e5bf1e42e3d4318070096066e88cdcc241
Hi @S-Dafarra and @paolo-viceconte if you are fine with the changes we can merge it
This PR is the outcome of the refactoring carried out with @paolo-viceconte In detail, we implemented
MANN::generateDummyMANNOutput
andMANN::generateDummyMANNInput
in theML
component. Additionally, we restructuredMANNAutoregressive
for improved reset handling by introducing theMANNFootState
class and consolidating reset-related quantities inMANNAutoregressive::AutoregressiveState
. This simplifies the generation of the initialAutoregressiveState
required to start trajectory generation. Concurrently, we restructuredMANNTrajectoryGenerator
by eliminating the need to pass foot positions in setInitialState. We enhancedMANNTrajectoryGenerator
with reset capabilities similar toMANNAutoregressive
and corrected the position and time scaling to ensure accurate scaling of the CoM, base, and feet positions. The Python bindings have been updated accordingly.Last but not least I added two examples that show how to use
MANNAutoregressive
andMANNTrajectoryGenerator
MANNAutoregressive
MANNAutoregressive
MANNTrajectoryGenerator
MANNTrajectoryGenerator