ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation

• URL: http://arxiv.org/abs/2601.01155v2
• Date: Mon, 26 Jan 2026 08:48:21 GMT
• Title: ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation
• Abstract summary: ORION is a novel deep reinforcement learning framework for cooperative multi-agent online navigation in partially known environments.<n>At the core of ORION is an option-critic framework that learns to reason about a set of high-level cooperative modes.<n>Our simulation results show that ORION achieves high-quality, real-time decentralized cooperation over varying team sizes.
• Score: 5.834992848353096
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Existing methods for multi-agent navigation typically assume fully known environments, offering limited support for partially known scenarios such as warehouses or factory floors. There, agents may need to plan trajectories that balance their own path optimality with their ability to collect and share information about the environment that can help their teammates reach their own goals. To these ends, we propose ORION, a novel deep reinforcement learning framework for cooperative multi-agent online navigation in partially known environments. Starting from an imperfect prior map, ORION trains agents to make decentralized decisions, coordinate to reach their individual targets, and actively reduce map uncertainty by sharing online observations in a closed perception-action loop. We first design a shared graph encoder that fuses prior map with online perception into a unified representation, providing robust state embeddings under dynamic map discrepancies. At the core of ORION is an option-critic framework that learns to reason about a set of high-level cooperative modes that translate into sequences of low-level actions, allowing agents to switch between individual navigation and team-level exploration adaptively. We further introduce a dual-stage cooperation strategy that enables agents to assist teammates under map uncertainty, thereby reducing the overall makespan. Across extensive maze-like maps and large-scale warehouse environments, our simulation results show that ORION achieves high-quality, real-time decentralized cooperation over varying team sizes, outperforming state-of-the-art classical and learning-based baselines. Finally, we validate ORION on physical robot teams, demonstrating its robustness and practicality for real-world cooperative navigation.

Related papers

• Sentinel: Embodied Cooperative Spatial Reasoning and Planning [29.50555565754175]
  We study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate under dynamic environmental constraints.<n>We introduce Sentinel Challenge, a benchmark where multiple agents must communicate in natural language to agree on a mutually safe and convenient meeting point.<n>We propose CoSaR, a framework that bridges the high-level communication and planning abilities of foundation models with the precision of classical spatial navigation algorithms.
  arXiv  Detail & Related papers  (2026-05-25T18:04:41Z)
• DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation [51.978605314711835]
  Long-horizon collaborative vision-language navigation (VLN) is critical for multi-robot systems to accomplish complex tasks beyond the capability of a single agent.<n>We present Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation (DeCoNav)<n>DeCoNav is a decentralized framework that couples event-triggered dialogue with dynamic task allocation and replanning for real-time, adaptive coordination.
  arXiv  Detail & Related papers  (2026-04-14T09:11:55Z)
• Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment [5.204648436671471]
  We present a graph-based multi-agent reinforcement learning framework trained under centralized training with decentralized execution (CTDE)<n>A centralized critic and global state are available only during training, while each UAV executes a shared policy using local observations and messages from nearby neighbors.<n>Our architecture encodes local agent state and nearby entities with an agent-entity attention module, and aggregates inter-UAV messages with neighbor self-attention over a distance-limited communication graph.
  arXiv  Detail & Related papers  (2026-03-17T05:48:51Z)
• TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size [54.0714652192002]
  Physics-based humanoid control has achieved remarkable progress in enabling realistic and high-performing single-agent behaviors.<n>We present TeamHOI, a framework that enables a single decentralized policy to handle cooperative HOIs across any number of cooperating agents.
  arXiv  Detail & Related papers  (2026-03-09T05:52:13Z)
• Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation [96.88162755522342]
  Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI.<n>We introduce DACo, a planning-grounding decoupled architecture that disentangles global deliberation from local grounding.<n>By disentangling global reasoning from local action, DACo alleviates cognitive overload and improves long-horizon stability.
  arXiv  Detail & Related papers  (2026-02-21T19:19:55Z)
• Path Planning Optimisation for SParse, AwaRe and Cooperative Networked Aerial Robot Teams (SpArC-NARTs): Optimisation Tool and Ground Sensing Coverage Use Cases [1.376408511310322]
  A networked aerial robot team (NART) comprises a group of agents interconnected by wireless links.<n>Inter-agent connectivity, even if intermittent (i.e. sparse), enables data exchanges between agents and supports cooperative behaviours.<n>This paper proposes a novel path planning tool for a Sparse, Aware, and Cooperative Networked Aerial Robot Team.
  arXiv  Detail & Related papers  (2026-02-15T17:40:45Z)
• ReasonNavi: Human-Inspired Global Map Reasoning for Zero-Shot Embodied Navigation [53.95797153529148]
  Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations.<n>We introduce ReasonNavi, a human-inspired framework that operationalizes this reason-then-act paradigm by coupling Multimodal Large Language Models (MLLMs) with deterministic planners.
  arXiv  Detail & Related papers  (2026-01-26T19:09:20Z)
• IG-MCTS: Human-in-the-Loop Cooperative Navigation under Incomplete Information [22.47189812250736]
  CoNav-Maze is a simulated environment where a robot navigates with local perception while a human operator provides guidance based on an inaccurate map.<n>We propose Information Gain Monte Carlo Tree Search (IG-MCTS) to jointly optimize autonomous movement and informative communication.<n>IG-MCTS significantly reduces communication demands and yields eye-tracking metrics indicative of lower cognitive load.
  arXiv  Detail & Related papers  (2025-02-03T22:08:04Z)
• MASP: Scalable GNN-based Planning for Multi-Agent Navigation [18.70078556851899]
  Multi-Agent Scalable Graph-based Planner (MASP) is a goal-conditioned hierarchical planner for navigation tasks.<n>MASP employs a hierarchical framework to reduce space complexity by decomposing a large exploration space into multiple goal-conditioned subspaces.<n>For agent cooperation and the adaptation to varying team sizes, we model agents and goals as graphs to better capture their relationship.
  arXiv  Detail & Related papers  (2023-12-05T06:05:04Z)
• Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport [83.06265788137443]
  We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigation. Our first contribution is the design of a novel Long-HOT environment focused on deep exploration and long-horizon planning. We propose a modular hierarchical transport policy (HTP) that builds a topological graph of the scene to perform exploration with the help of weighted frontiers.
  arXiv  Detail & Related papers  (2022-10-28T05:30:49Z)
• Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation [11.868792440783055]
  We show that learning to estimate metrics quantifying the spatial relationships between an agent at a given location and a goal to reach has a high positive impact in Multi-Object Navigation settings. A learning-based agent from the literature trained with the proposed auxiliary losses was the winning entry to the Multi-Object Navigation Challenge.
  arXiv  Detail & Related papers  (2021-07-13T12:01:05Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)
• Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous [66.6895109554163]
  Underlying the human ability to align goals with other agents is their ability to predict the intentions of others and actively update their own plans. We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous.
  arXiv  Detail & Related papers  (2020-03-15T19:49:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.