Frontend
Planner-Controller Interaction for Ackermann Navigation: A Matched Simulation and Hardware Benchmark
arXiv cs.RO0 views
arXiv:2611.24800v1 Announce Type: new Abstract: Global planners and path-tracking controllers are often evaluated independently, although their interaction determines how a vehicle follows a planned path. Whether simulation accurately predicts the performance of specific planner-controller combinations on Ackermann-steered hardware remains uncertain. This study evaluated three geometric controllers (Regulated Pure Pursuit, Stanley, and Vector Pursuit) paired with two global planners (Hybrid A* and NavFn) on a 1/10-scale Quanser QCar and in a matched Gazebo simulation. Both environments used shared custom planning and control algorithms, matched route geometry and goals, ground-truth pose references, and a common evaluation pipeline. Five runs per configuration and environment yielded 60 benchmark runs. Controller rankings for tracking accuracy and command smoothness transferred consistently between environments, with Spearman correlations of 0.77-0.94. However, planner-dependent effects showed substantially weaker agreement. In simulation, planner selection changed the root-mean-square (RMS) angular acceleration of the commanded velocities by no more than 0.030 rad/s^2, whereas Hybrid A* increased it by 0.141-0.843 rad/s^2 on hardware, depending on the controller. These differences coincided with planner-dependent achieved speeds that the simulation's idealised longitudinal response did not reproduce. Mean controller computation times remained below 0.5 ms on the Jetson TX2. The findings demonstrate that agreement in controller rankings does not guarantee accurate prediction of planner-dependent performance for specific controller pairings on hardware, highlighting the importance of physical validation.
Source:https://arxiv.org/abs/2611.24800PreviousHINT-WAM: Hindsight-Informed Training for World Action ModelsNextRoboMorpher: Scaling Robot Morphology Representations for Cross-Embodiment Action Prediction
Related posts

Java Tricky Question: Why Boxed Integers 127 == 127 but 1000 == 1000 Is false
0dev.to Java
A colleague changed one capital letter in a file name and only our Linux build could see it
0dev.to Git
I put my AI's memory in Markdown and Git: the failures I fixed along the way
0dev.to Git
1,684 awaits in our codebase, 34 places that run in parallel, and not one allSettled
0dev.to TypeScript
Keep rough size bands separate from measured area
0dev.to TypeScript
A command is a file
0dev.to TypeScript