← Search

Keisuke Okumura

16 accepted papers

2026

Graph Attention-Guided Search for Dense Multi-Agent Pathfinding

AAAI 2026technical

Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived from MAGAT, a neural MAPF policy with a graph attention scheme,

Cited by 0SourcePDFScholar
2026

Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding

ICLR 2026poster

Multi-Agent Path Finding (MAPF) is a representative multi-agent coordination problem, where multiple agents are required to navigate to their respective goals without collisions. Solving MAPF optimally is known to be NP-hard, leading to the adoption of learning-based approaches to alleviate the onli…

Cited by 0SourcecodeScholar
2025

Congestion Mitigation Path Planning for Large-Scale Multi-Agent Navigation in Dense Environments

RA-L 2025

In high-density environments where numerous autonomous agents move simultaneously in a distributed manner, streamlining global flows to mitigate local congestion is crucial to maintain overall navigation efficiency. This paper introduces a novel path-planning problem, <italic xmlns:mml="http://www.w

Cited by 2SourceScholar
2025

D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations

IROS 2025

This work presents an optimization method for generating kinodynamically feasible and collision-free multi-robot trajectories that exploits an incremental denoising scheme in diffusion models. Our key insight is that high-quality trajectories can be discovered merely by denoising noisy trajectories

Cited by 2SourceScholar
2025

ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordination

CoRL 2025poster

Constraint-based optimization is a cornerstone of robotics, enabling the design of controllers that reliably encode task and safety requirements such as collision avoidance or formation adherence. However, handcrafted constraints can fail in multi-agent settings that demand complex coordination. We…

Cited by 0SourceScholar
2022

Offline Time-Independent Multi-Agent Path Planning

IJCAI 2022poster

This paper studies a novel planning problem for multiple agents that cannot share holding resources, named OTIMAPP (Offline Time-Independent Multi-Agent Path Planning). Given a graph and a set of start-goal pairs, the problem consists in assigning a path to each agent such that every agent eventuall…

2021

Time-Independent Planning for Multiple Moving Agents

AAAI 2021technical

Typical Multi-agent Path Finding (MAPF) solvers assume that agents move synchronously, thus neglecting the reality gap in timing assumptions, e.g., delays caused by an imperfect execution of asynchronous moves. So far, two policies enforce a robust execution of MAPF plans taken as input: either by f…