beluga
beluga copied to clipboard
A general implementation of Monte Carlo Localization (MCL) algorithms written in C++17, and a ROS package that can be used in ROS 1 and ROS 2.
### Feature description Precisely what the title says. While Beluga's API is well documented, the only reference on how to make use of the library is a ROS node and...
### Bug description We're using default options of different versions of clang-tidy between CI pipelines (noetic, humble, etc). This sometimes results in conflicting errors. **Expected behavior** All the pipelines run...
NDT-MCL
## Description This method proposes to relax the hard discretization assumption imposed by grid-based models in common MCL implementations by using a piecewise continuous normal distribution representation (NDT) of the...
## Description From _Probabilistic Robotics, Chapter 4.2.4_: > [...] the resampling process induces a loss of diversity in the particle population, which in fact manifests itself as approximation error. Such...
The nav2_amcl version present in the humble container crashes replaying the perfect odometry bagfile
### Bug description Running the perfect odometry bagfile against nav2 amcl in the Humble development container causes amcl to crash early in the bagfile. This is an issue for us...
## Description Both QuickMCL and AMCL seem to have for a long time used a formula for aggregation of the likelihood `p` that does not match the model proposed in...
### Feature description As part of #199 it was found that `std::floor` [is expensive](https://stackoverflow.com/questions/824118/why-is-floor-so-slow/825916#825916). When used in a tight loop, this extra cost can be non-negligible. This ticket is about...
### Bug description When trying to compare the results obtained by running instructions [here](https://github.com/Ekumen-OS/beluga/blob/main/beluga_benchmark/docs/BENCHMARKING.md#run-rosbag-benchmark-parameterizing-the-number-of-particles) fails because of negative data and the code tries to log-scale the data. Please note that...
### Feature description #279 uncovered a few discrepancies between our implementation of the particle degeneracy recovery algorithm and that of Nav2 AMCL. We should revisit both control flow and normalization...
### Feature description Existing estimators in Beluga for distribution mean and covariance include unweighted and weighted maximum likelihood estimators (i.e. sampling mean and covariance). These can be swayed by outlier...