ATRS uses a shared neural policy in a multi-agent MDP to adaptively re-split trajectory segments during parallel ADMM optimization, cutting iterations by up to 26% and time by 19.1% with zero-shot generalization.
Learning to warm- start fixed-point optimization algorithms,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
Flow-Opt combines a flow-matching DiT model with a custom differentiable safety filter and learned initialization to enable fast centralized trajectory optimization for tens of robots.
citing papers explorer
-
ATRS: Adaptive Trajectory Re-splitting via a Shared Neural Policy for Parallel Optimization
ATRS uses a shared neural policy in a multi-agent MDP to adaptively re-split trajectory segments during parallel ADMM optimization, cutting iterations by up to 26% and time by 19.1% with zero-shot generalization.
-
Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimization
Flow-Opt combines a flow-matching DiT model with a custom differentiable safety filter and learned initialization to enable fast centralized trajectory optimization for tens of robots.