Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation

• URL: http://arxiv.org/abs/2509.01838v1
• Date: Mon, 01 Sep 2025 23:42:16 GMT
• Title: Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation
• Abstract summary: We propose a reinforcement learning solution for big maritime data that can learn to find a route across multiple origin-destination pairs.<n>Agents learn to select direction and speed under continuous observations in a multi-discrete action space.<n>A reward function balances fuel efficiency, travel time, wind resistance, and route diversity, using an Automatic Identification System (AIS)-derived traffic graph with ERA5 wind fields.
• Score: 1.2773749417703923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Routing vessels through narrow and dynamic waterways is challenging due to changing environmental conditions and operational constraints. Existing vessel-routing studies typically fail to generalize across multiple origin-destination pairs and do not exploit large-scale, data-driven traffic graphs. In this paper, we propose a reinforcement learning solution for big maritime data that can learn to find a route across multiple origin-destination pairs while adapting to different hexagonal grid resolutions. Agents learn to select direction and speed under continuous observations in a multi-discrete action space. A reward function balances fuel efficiency, travel time, wind resistance, and route diversity, using an Automatic Identification System (AIS)-derived traffic graph with ERA5 wind fields. The approach is demonstrated in the Gulf of St. Lawrence, one of the largest estuaries in the world. We evaluate configurations that combine Proximal Policy Optimization with recurrent networks, invalid-action masking, and exploration strategies. Our experiments demonstrate that action masking yields a clear improvement in policy performance and that supplementing penalty-only feedback with positive shaping rewards produces additional gains.

Related papers

• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation [31.539730066120374]
  Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints.<n>We propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight.
  arXiv  Detail & Related papers  (2026-06-03T14:05:19Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation [57.399685080574756]
  Existing MLLM-based VLN methods rely on imitation learning (IL) and often use DAgger for post-training.<n>We propose ActiveVLN, a VLN framework that explicitly enables active exploration through multi-turn RL.<n>Experiments show that ActiveVLN achieves the largest performance gains over IL baselines compared to both DAgger-based and prior RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-09-16T03:31:46Z)
• Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information [6.371251946803415]
  DPRL is an end-to-end policy designed to address the challenge of high-speed autonomous UAV navigation under partially observable environmental conditions.<n>We leverage an asymmetric Actor-Critic architecture to provide the agent with privileged information during training.<n>We conduct extensive simulations across various scenarios, benchmarking our DPRL algorithm against the state-of-the-art navigation algorithms.
  arXiv  Detail & Related papers  (2024-12-09T09:05:52Z)
• Efficient Data Representation for Motion Forecasting: A Scene-Specific Trajectory Set Approach [12.335528093380631]
  This study introduces a novel approach for generating scene-specific trajectory sets tailored to different contexts.<n>A deterministic goal sampling algorithm identifies relevant map regions, while our Recursive In-Distribution Subsampling (RIDS) method enhances trajectory plausibility.<n>Experiments on the Argoverse 2 dataset demonstrate that our method achieves up to a 10% improvement in Driving Area Compliance.
  arXiv  Detail & Related papers  (2024-07-30T11:06:39Z)
• Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation [72.24964965882783]
  Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error.<n>Real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies.<n>We introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function.
  arXiv  Detail & Related papers  (2023-06-09T18:45:15Z)
• Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones [0.0]
  This paper proposes a novel approach, asynchronous multi-stage deep reinforcement learning (AMS-DRL), to train adversarial neural networks. AMS-DRL evolves adversarial agents in a pursuit-evasion game where the pursuers and the evader are asynchronously trained in a bipartite graph way. We evaluate our method in extensive simulations and show that it outperforms baselines with higher navigation success rates.
  arXiv  Detail & Related papers  (2023-04-07T01:59:16Z)
• Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation [78.17108227614928]
  We propose a benchmark environment for Safe Reinforcement Learning focusing on aquatic navigation. We consider a value-based and policy-gradient Deep Reinforcement Learning (DRL) We also propose a verification strategy that checks the behavior of the trained models over a set of desired properties.
  arXiv  Detail & Related papers  (2021-12-16T16:53:56Z)
• Deep Learning Aided Packet Routing in Aeronautical Ad-Hoc Networks Relying on Real Flight Data: From Single-Objective to Near-Pareto Multi-Objective Optimization [79.96177511319713]
  We invoke deep learning (DL) to assist routing in aeronautical ad-hoc networks (AANETs) A deep neural network (DNN) is conceived for mapping the local geographic information observed by the forwarding node into the information required for determining the optimal next hop. We extend the DL-aided routing algorithm to a multi-objective scenario, where we aim for simultaneously minimizing the delay, maximizing the path capacity, and maximizing the path lifetime.
  arXiv  Detail & Related papers  (2021-10-28T14:18:22Z)
• Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction [71.97877759413272]
  Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Recent methods have achieved strong performances using Multi-Choice Learning objectives like winner-takes-all (WTA) or best-of-many. Our work addresses two key challenges in trajectory prediction, learning outputs, and better predictions by imposing constraints using driving knowledge.
  arXiv  Detail & Related papers  (2021-04-16T17:58:56Z)
• Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars [10.080958939027363]
  In autonomous driving, navigation through unsignaled intersections is a challenging task. We propose a novel branched network G-CIL for the navigation policy learning. Our end-to-end trainable neural network outperforms the baselines with higher success rate and shorter navigation time.
  arXiv  Detail & Related papers  (2021-02-01T07:33:12Z)
• An End-to-end Deep Reinforcement Learning Approach for the Long-term Short-term Planning on the Frenet Space [0.0]
  This paper presents a novel end-to-end continuous deep reinforcement learning approach towards autonomous cars' decision-making and motion planning. For the first time, we define both states and action spaces on the Frenet space to make the driving behavior less variant to the road curvatures. The algorithm generates continuoustemporal trajectories on the Frenet frame for the feedback controller to track.
  arXiv  Detail & Related papers  (2020-11-26T02:40:07Z)
• Data Freshness and Energy-Efficient UAV Navigation Optimization: A Deep Reinforcement Learning Approach [88.45509934702913]
  We design a navigation policy for multiple unmanned aerial vehicles (UAVs) where mobile base stations (BSs) are deployed. We incorporate different contextual information such as energy and age of information (AoI) constraints to ensure the data freshness at the ground BS. By applying the proposed trained model, an effective real-time trajectory policy for the UAV-BSs captures the observable network states over time.
  arXiv  Detail & Related papers  (2020-02-21T07:29:15Z)

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.