Port SE2PWDDistribution from libDirectional as SE2DiracDistribution#1594
Port SE2PWDDistribution from libDirectional as SE2DiracDistribution#1594
Conversation
Agent-Logs-Url: https://github.com/FlorianPfaff/PyRecEst/sessions/cce18bd2-1848-4926-9efb-9c5c09433e9d Co-authored-by: FlorianPfaff <6773539+FlorianPfaff@users.noreply.github.com>
✅MegaLinter analysis: Success
See detailed reports in MegaLinter artifacts Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining
|
|
@copilot can you increase the tolerance to 1e-7 to prevent failure? Mismatched elements: 4 / 16 (25%) |
Agent-Logs-Url: https://github.com/FlorianPfaff/PyRecEst/sessions/223958a2-c09c-4c52-97a8-4d78688acd7d Co-authored-by: FlorianPfaff <6773539+FlorianPfaff@users.noreply.github.com>
Head branch was pushed to by a user without write access
|
@copilot Fix this linter error |
Agent-Logs-Url: https://github.com/FlorianPfaff/PyRecEst/sessions/6916cd91-31bd-4286-a043-eb37a4bb1b2e Co-authored-by: FlorianPfaff <6773539+FlorianPfaff@users.noreply.github.com>
Fixed in commit 60a69dd by adding |

Ports the MATLAB
SE2PWDDistributionfrom libDirectional to Python asSE2DiracDistribution— a particle distribution on SE(2) = S¹ × ℝ².New class:
SE2DiracDistributionInherits from
HypercylindricalDiracDistribution(bound_dim=1) andAbstractSE2Distribution.mean_4d()— weighted mean of[cos θ, sin θ, x, y]; delegates tohybrid_moment()covariance_4d()— 4×4 second-moment matrixΣ wᵢ sᵢ sᵢᵀwheresᵢ = [cos θᵢ, sin θᵢ, xᵢ, yᵢ]mean()— delegates tohybrid_mean()for interface consistency with other manifold distributionsfrom_distribution(dist, n_particles)— factory accepting anyAbstractHypercylindricalDistributionwithbound_dim=1, lin_dim=2(faithful to the MATLAB signature)Other changes
distributions/__init__.py— exportsSE2DiracDistribution