Latent World Models with Monotone Planning Costs for Image-Goal Navigation

• URL: http://arxiv.org/abs/2608.09073v1
• Date: Mon, 10 Aug 2026 03:23:26 GMT
• Title: Latent World Models with Monotone Planning Costs for Image-Goal Navigation
• Abstract summary: We propose a latent world model built on a frozen DINO-family encoder and train it with two complementary objectives.<n>An autoregressive rollout loss reduces the gap between training and multi-step planning rollouts.<n>A Monotone Cost Ranking (MCR) loss directly encourages increasingly perturbed action sequences to receive higher planning costs.
• Score: 11.421277609989302
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image-goal navigation with latent world models requires not only accurate future prediction, but also a planning cost that reliably ranks candidate action sequences. We define the cost as the cosine distance between the predicted future embedding and the goal embedding, and show that poor cost ordering can mislead sampling-based planners such as Cross-Entropy Method (CEM). To address this, we propose a latent world model built on a frozen DINO-family encoder and train it with two complementary objectives. An autoregressive rollout loss reduces the gap between training and multi-step planning rollouts, while a Monotone Cost Ranking (MCR) loss directly encourages increasingly perturbed action sequences to receive higher planning costs. We also study InfoNCE-based action-contrastive training and find that temporal permutation negatives distort the latent geometry and degrade planning performance. On the GNM navigation dataset, our method outperforms Navigation World Models (NWM), DINO-WM, OmniVLA, and NoMaD, achieving state-of-the-art image-goal navigation performance while reducing orientation error by $2.7\times$ over the same-encoder DINO WM baseline. We also deploy the model zero-shot on a physical robot, where it follows goal-directed paths in unseen indoor and outdoor environments.

Related papers

• Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing [5.00725149774706]
  Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included.<n>We present Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding.<n>We treat each developer session as a task that can be discovered, classified, graded for difficulty, benchmarked in a production-like harness, and routed to the cheapest model able to complete it within quality and latency constraints.
  arXiv  Detail & Related papers  (2026-08-09T06:57:53Z)
• Model Predictive Planner for UAV Navigation in Non-Convex Air Corridors [1.2617078020344616]
  This work presents a motion motion framework for UAV air corridors.<n>The planner is based on a mixed-integer tracking model that enforces external feasibility.
  arXiv  Detail & Related papers  (2026-07-27T12:42:38Z)
• RAVEN: Reinforcement-Adaptive Visibility-Graph Planning for Robust Humanoid Navigation with Collision-Free MPC [11.923992019929495]
  We propose RAVEN, a hierarchical reinforcement learning framework for robust humanoid navigation.<n>RAVEN employs RL to adapt the geometric construction of a visibility-graph planner by modifying obstacle inflation and related graph parameters.<n>Results demonstrate reduced overshoot near obstacles, improved robustness in narrow passages, and more reliable navigation under delay and noise.
  arXiv  Detail & Related papers  (2026-07-17T07:23:54Z)
• PLAN-S: Bridging Planning with Latent Style Dynamics for Autonomous Driving World Models [11.0972429896041]
  We propose PLAN-S (PLANning with latent Style dynamics), a planner-facing bridge that addresses the compactness-controllability dilemma.<n>PLAN-S produces diverse cost maps, with spatially consistent variations aligned to different driving styles.
  arXiv  Detail & Related papers  (2026-06-04T11:03:20Z)
• Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement [15.002921311530374]
  Autoregressive models are a formidable baseline for end-to-end planning in autonomous driving.<n>Their performance is constrained by atemporal misalignment, as the planner must condition future actions on past sensory data.<n>We propose a Time-Invariant Alignment (TISA) module that learns to project initial environmental features into a consistent ego-centric frame.<n>We also introduce a multi-objective post-training stage using Direct Preference Optimization (DPO) to move beyond pure imitation.
  arXiv  Detail & Related papers  (2025-09-25T09:24:45Z)
• SCoTT: Strategic Chain-of-Thought Tasking for Wireless-Aware Robot Navigation in Digital Twins [78.53885607559958]
  We propose SCoTT, a wireless-aware path planning framework.<n>We show that SCoTT achieves path gains within 2% of DP-WA* while consistently generating shorter trajectories.<n>We also show the practical viability of our approach by deploying SCoTT as a ROS node within Gazebo simulations.
  arXiv  Detail & Related papers  (2024-11-27T10:45:49Z)
• Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation [64.84996994779443]
  We propose a novel Affordances-Oriented Planner for continuous vision-language navigation (VLN) task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making. Experiments on the challenging R2R-CE and RxR-CE datasets show that AO-Planner achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-07-08T12:52:46Z)
• COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL [50.385005413810084]
  Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration. $textttCOPlanner$ is a planning-driven framework for model-based methods to address the inaccurately learned dynamics model problem.
  arXiv  Detail & Related papers  (2023-10-11T06:10:07Z)
• DDPEN: Trajectory Optimisation With Sub Goal Generation Model [70.36888514074022]
  In this paper, we produce a novel Differential Dynamic Programming with Escape Network (DDPEN) We propose to utilize a deep model that takes as an input map of the environment in the form of a costmap together with the desired position. The model produces possible future directions that will lead to the goal, avoiding local minima which is possible to run in real time conditions.
  arXiv  Detail & Related papers  (2023-01-18T11:02:06Z)
• SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots [112.2491765424719]
  We present an end-to-end online motion planning framework that uses a data-driven approach to navigate a heterogeneous robot team towards a global goal. We use model predictive control (SMPC) to calculate control inputs that satisfy robot dynamics, and consider uncertainty during obstacle avoidance with chance constraints. recurrent neural networks are used to provide a quick estimate of future state uncertainty considered in the SMPC finite-time horizon solution. A Deep Q-learning agent is employed to serve as a high-level path planner, providing the SMPC with target positions that move the robots towards a desired global goal.
  arXiv  Detail & Related papers  (2021-08-03T02:56:21Z)
• End-to-end Interpretable Neural Motion Planner [78.69295676456085]
  We propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios. We design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations. We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America.
  arXiv  Detail & Related papers  (2021-01-17T14:16:12Z)

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.