Skip to content

refactor: optimize forward kinematics compilation in BaseSolver #275

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

Closed
lookangela wants to merge 1 commit into from
Closed

refactor: optimize forward kinematics compilation in BaseSolver #275

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions embodichain/lab/sim/solvers/base_solver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,9 +172,13 @@ def __init__(self, cfg: SolverCfg = None, device: str = None, **kwargs):
device=self.device,
)

def _fk_end_matrix(th):
return self.pk_serial_chain.forward_kinematics(
th, end_only=True
).get_matrix()

self.compiled_fk = torch.compile(
self.pk_serial_chain.forward_kinematics_tensor,
fullgraph=True,
_fk_end_matrix,
dynamic=True,
)

Expand Down Expand Up @@ -433,7 +437,7 @@ def get_fk(self, qpos: torch.tensor, **kwargs) -> torch.Tensor:
logger.log_error("Kinematic chain is not initialized.")
return torch.eye(4, device=self.device)
# Compute forward kinematics
ee_link_xpos = self.compiled_fk(qpos)[-1, :, :, :]
ee_link_xpos = self.compiled_fk(qpos)

# Ensure batch format for TCP
batch_size = qpos.shape[0]
Expand Down
Loading