M2M solves the many-to-many MAPD problem with two variants and outperforms prior one-to-one methods by completing up to 22,000 more tasks on average in 8-hour warehouse simulations.
The hungarian method for the assignment problem
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
method 1polarities
use method 1representative citing papers
VCST-RCP reduces multi-robot delivery fleet travel distance by 31% on average by routing packages through a Voronoi-constrained Steiner tree relay backbone rather than direct source-to-destination paths.
DETRs learn an optimal specialist strategy via the Hungarian loss, motivating the new Object-level Calibration Error (OCE) metric and an image-level post-hoc uncertainty quantification framework.
A graph neural attention planner combined with decentralized NMPC enables scalable, safe multi-robot unlabeled motion planning under communication constraints, demonstrated in simulation and real quadrotor experiments.
ReCLIP++ rectifies class and space biases in CLIP via separate reference and positional features, logit subtraction, and a mask decoder with contrastive loss to improve unsupervised semantic segmentation on PASCAL VOC, ADE20K and other benchmarks.
NeuroMesh introduces a modular decentralized neural inference framework using dual-aggregation and parallel architecture to support heterogeneous multi-robot teams on perception, control, and task assignment tasks.
citing papers explorer
-
Many-to-Many Multi-Agent Pickup and Delivery
M2M solves the many-to-many MAPD problem with two variants and outperforms prior one-to-one methods by completing up to 22,000 more tasks on average in 8-hour warehouse simulations.
-
Relay-Based Coordination for Energy-Efficient Multi-Robot Pickup and Delivery
VCST-RCP reduces multi-robot delivery fleet travel distance by 31% on average by routing packages through a Voronoi-constrained Steiner tree relay backbone rather than direct source-to-destination paths.
-
Uncertainty Quantification in Detection Transformers: Object-Level Calibration and Image-Level Reliability
DETRs learn an optimal specialist strategy via the Hungarian loss, motivating the new Object-level Calibration Error (OCE) metric and an image-level post-hoc uncertainty quantification framework.
-
Graph Neural Planning and Predictive Control for Multi-Robot Communication-Constrained Unlabeled Motion Planning
A graph neural attention planner combined with decentralized NMPC enables scalable, safe multi-robot unlabeled motion planning under communication constraints, demonstrated in simulation and real quadrotor experiments.
-
ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
ReCLIP++ rectifies class and space biases in CLIP via separate reference and positional features, logit subtraction, and a mask decoder with contrastive loss to improve unsupervised semantic segmentation on PASCAL VOC, ADE20K and other benchmarks.
-
NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration
NeuroMesh introduces a modular decentralized neural inference framework using dual-aggregation and parallel architecture to support heterogeneous multi-robot teams on perception, control, and task assignment tasks.