Steve Macenski
Steve Macenski
If I wanted to run navigation over this longer term, when does the performance of this system start to cap out or degrade? If I set the costmap to a...
- [ ] Update landing page - [x] Improve MPPI run time performance 20% - [x] MPPI default algorithm over DWB for TB3 demo - [ ] Complete Gazebo2 migration...
From 12.7ms on average to 6.80ms on average for 10000 cycles - with full footprint checking enabled --- Validate final run-time and system performance of changes to make sure still...
Offer a simplistic Gazebo replacement which sends robot velocity commands to TF as the robot's odometry to completely remove the need for complex simulation for testing higher level behavioral attributes...
General improvements - [ ] Add in some hand-crafted trajectories into the mix via https://arxiv.org/pdf/2401.09241 (i.e. drive to goal, stop, slow, fast, even other algorithms perhaps, etc with samples) -...
In the last couple of years, I've worked to add in algorithms and systems with the idea that a global path is a general sense of a route and I...
Per https://github.com/ros-planning/navigation2/pull/4140 Angles should be able to do the trick instead: https://github.com/ros/angles
When using feasible planners, it might not be sensible to replan when things are clear within X meters of the goal. It can actually be detrimental to do so if...
Per https://github.com/ros-perception/point_cloud_transport, we can now use compressed pointcloud streams in ROS 2. We can enable those in the Costmap layers that ingest pointcloud sensor streams (i.e. obstacle, voxel) and the...
Some users have asked for a way to compute feasible paths to the goal without considering orientation. Since they're feasible paths, there's no "real" way to do this since we...