Imitation Learning of Avoidance Modes for Efficient Multimodal Model Predictive Control
Imitation Learning of Avoidance Modes for Efficient Multimodal Model Predictive Control
This research proposes SideNet-MPC, which replaces the exponential computational cost of multimodal model predictive control (MM-MPC) with imitation learning. A graph neural network predicts the expert's minimum-cost mode, reducing the number of optimal control problems (OCPs) solved per control period. The method achieves 93% of the expert's success rate with 18.6 ms per control period, 48% faster than the expert's 35.5 ms on sixteen threads.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
control period
18.6
View original evidence
keeps this rule and substitutes the network proposal for the minimum-cost mode. Hence at most two OCPs are solved per control period, and every applied input still comes from an OCP with control barrier function constraints rather than from the network. In $100$ seed-matched closed-loop Monte Carlo runs of mixed traffic, SideNet-MPC reaches $93\%$ of the expert's success rate and needs \SI{18.6}{ms} per control peri
Open source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
keeps this rule and substitutes the network proposal for the minimum-cost mode. Hence at most two OCPs are solved per control period, and every applied input still comes from an OCP with control barrier function constraints rather than from the network. In $100$ seed-matched closed-loop Monte Carlo runs of mixed traffic, SideNet-MPC reaches $93\%$ of the expert's success rate and needs \SI{18.6}{ms} per control peri
Open source S4
od on a single thread, 48\% less than the expert's \SI{35.5}{ms} on sixteen parallel threads. In a controlled gap sweep, its proposed side reverses in the same gap interval as the expert's, whereas proposers without pairwise edges, trained on the same data, never reverse and all deadlock at the blocked gates of a deterministic scene.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org