The paper introduces a Trajectory Waypoint paradigm with a TSDF-guided diffusion policy and trajectory-enhanced navigator that achieves better performance on VLN-CE benchmarks by ensuring waypoint reachability and planning-execution consistency.
AstraNav-World: World Model for Foresight Control and Consistency
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
abstract
Embodied navigation in open, dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time. We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual states and action sequences within a unified probabilistic framework. Our framework integrates a diffusion-based video generator with a vision-language policy, enabling synchronized rollouts where predicted scenes and planned actions are updated simultaneously. Training optimizes two complementary objectives: generating action-conditioned multi-step visual predictions and deriving trajectories conditioned on those predicted visuals. This bidirectional constraint makes visual predictions executable and keeps decisions grounded in physically consistent, task-relevant futures, mitigating cumulative errors common in decoupled "envision-then-plan" pipelines. Experiments across diverse embodied navigation benchmarks show improved trajectory accuracy and higher success rates. Ablations confirm the necessity of tight vision-action coupling and unified training, with either branch removal degrading both prediction quality and policy reliability. In real-world testing, AstraNav-World demonstrated exceptional zero-shot capabilities, adapting to previously unseen scenarios without any real-world fine-tuning. These results suggest that AstraNav-World captures transferable spatial understanding and planning-relevant navigation dynamics, rather than merely overfitting to simulation-specific data distribution. Overall, by unifying foresight vision and control within a single generative model, we move closer to reliable, interpretable, and general-purpose embodied agents that operate robustly in open-ended real-world settings.
citation-role summary
background 3
other 1
citation-polarity summary
years
2026 11representative citing papers
NavWM unifies latent world tokens and anchor-based multimodal trajectory forecasting into a closed-loop planner that improves future state generation and zero-shot navigation.
AsyncShield restores VLA geometric intent from latency via kinematic pose mapping and uses PPO-Lagrangian to balance tracking with LiDAR safety constraints in a plug-and-play module.
MVP-Nav reconstructs explicit 3D physical occupancy from monocular RGB using foundation models and integrates it with semantic priorities via a Multi-layer Value Map for grounded planning in zero-shot object navigation.
FutureNav proposes a 4B-scale VLM that jointly optimizes action prediction, inverse/forward dynamics, and future state generation for VLN and reports SOTA results on multiple benchmarks.
MV-WAM reports 55.7% simulation and 77.5% real-world success rates by aligning heterogeneous visual and action manifolds through causal masking and value-guided rollback.
StereoNav reaches new benchmark highs on R2R-CE and RxR-CE and improves real-robot reliability by supplying persistent target-location priors and stereo-derived geometry that stay stable under lighting changes and blur.
Navigation system transfers image generation models to embodied tasks via BEV-based traversability mask generation from language and cross-view localization for odometry correction, shown on a UAV completing 160m outdoor navigation.
ABot-Explorer unifies online exploration and hierarchical semantic memory construction via VLM-distilled navigational affordances for improved embodied navigation efficiency.
Matrix-Game 3.0 delivers 720p real-time video generation at 40 FPS with minute-scale memory consistency by combining residual self-correction training, camera-aware memory injection, and DMD-based autoregressive distillation on a 5B model.
citing papers explorer
-
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
The paper introduces a Trajectory Waypoint paradigm with a TSDF-guided diffusion policy and trajectory-enhanced navigator that achieves better performance on VLN-CE benchmarks by ensuring waypoint reachability and planning-execution consistency.
-
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
NavWM unifies latent world tokens and anchor-based multimodal trajectory forecasting into a closed-loop planner that improves future state generation and zero-shot navigation.
-
AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation
AsyncShield restores VLA geometric intent from latency via kinematic pose mapping and uses PPO-Lagrangian to balance tracking with LiDAR safety constraints in a plug-and-play module.
-
MVP-Nav: Multi-layer Value Map Planner Navigator
MVP-Nav reconstructs explicit 3D physical occupancy from monocular RGB using foundation models and integrates it with semantic priorities via a Multi-layer Value Map for grounded planning in zero-shot object navigation.
-
FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
FutureNav proposes a 4B-scale VLM that jointly optimizes action prediction, inverse/forward dynamics, and future state generation for VLN and reports SOTA results on multiple benchmarks.
-
MV-WAM: Manifold-Aware World Action Model with Value Augmentation
MV-WAM reports 55.7% simulation and 77.5% real-world success rates by aligning heterogeneous visual and action manifolds through causal masking and value-guided rollback.
-
What Limits Vision-and-Language Navigation ?
StereoNav reaches new benchmark highs on R2R-CE and RxR-CE and improves real-robot reliability by supplying persistent target-location priors and stereo-derived geometry that stay stable under lighting changes and blur.
-
PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation
Navigation system transfers image generation models to embodied tasks via BEV-based traversability mask generation from language and cross-view localization for odometry correction, shown on a UAV completing 160m outdoor navigation.
-
Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents
ABot-Explorer unifies online exploration and hierarchical semantic memory construction via VLM-distilled navigational affordances for improved embodied navigation efficiency.
-
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Matrix-Game 3.0 delivers 720p real-time video generation at 40 FPS with minute-scale memory consistency by combining residual self-correction training, camera-aware memory injection, and DMD-based autoregressive distillation on a 5B model.
- Dual-Anchoring: Addressing State Drift in Vision-Language Navigation