ORION introduces an option-critic RL method with shared graph encoding and dual-stage cooperation for decentralized multi-agent navigation and exploration in partially known environments, scaling to 10 robots with real-world validation.
Sampling-based algorithms for optimal motion planning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2representative citing papers
Track A* is a beam-pruned A* planner on a 4D spatio-temporal grid that finds high-quality visibility-aware tracking trajectories 23x faster on average than unoptimized A* with only a 0.15 pp visibility drop.
citing papers explorer
-
ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation
ORION introduces an option-critic RL method with shared graph encoding and dual-stage cooperation for decentralized multi-agent navigation and exploration in partially known environments, scaling to 10 robots with real-world validation.
-
Track A*: Fast Visibility-Aware Trajectory Planning for Active Target Tracking
Track A* is a beam-pruned A* planner on a 4D spatio-temporal grid that finds high-quality visibility-aware tracking trajectories 23x faster on average than unoptimized A* with only a 0.15 pp visibility drop.