aiqbench analysis
NavWAM advances robotics by integrating visual foresight directly into control policies via diffusion-transformer architectures, eliminating the need for separate external planners. This approach allows robots to execute goal-conditioned navigation in real-time using shared latent sequences that jointly optimize prediction and action generation. The method demonstrates improved performance over planning-based baselines while operating without computationally expensive search procedures like CEM on both simulated environments and physical hardware.
NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation
arXiv:2606.13494v1 Announce Type: new Abstract: Goal-conditioned visual navigation requires a robot to act under partial observability by anticipating how its motion will change the future egocentric view and whether that change brings it closer to the goal. Navigation world models provide such visual foresight, but they remain prediction modules that require an external planner to convert predicted futures into closed-loop control. We propose Navigation World Action Model (NavWAM), a diffusion-transformer policy that turns navigation world-model prediction into executable action by representing future observations, goal-progress values, and action chunks in a shared latent sequence. By learning future prediction jointly with the action and value targets that determine closed-loop behavior, NavWAM makes visual foresight directly usable for robot control. We build NavWAM through simulation pretraining and real-robot adaptation, and evaluate it on image-goal navigation against planning-based world models and a representative direct navigation policy. Across offline benchmarks and closed-loop real-robot deployment, NavWAM improves over planning-based world-model baselines in our evaluations while using the default policy mode without CEM-style action search. Project page: https://dachii-azm.github.io/navwam/
Abstract:Goal-conditioned visual navigation requires a robot to act under partial observability by anticipating how its motion will change the future egocentric view and whether that change brings it closer to the goal. Navigation world models provide such visual foresight, but they remain prediction modules that require an external planner to convert predicted futures into closed-loop control. We propose Navigation World Action Model (NavWAM), a diffusion-transformer policy that turns navigation world-model prediction into executable action by representing future observations, goal-progress values, and action chunks in a shared latent sequence. By learning future prediction jointly with the action and value targets that determine closed-loop behavior, NavWAM makes visual foresight directly usable for robot control. We build NavWAM through simulation pretraining and real-robot adaptation, and evaluate it on image-goal navigation against planning-based world models and a representative direct navigation policy. Across offline benchmarks and closed-loop real-robot deployment, NavWAM improves over planning-based world-model baselines in our evaluations while using the default policy mode without CEM-style action search. Project page: this https URL
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2606.13494 [cs.RO]
(or arXiv:2606.13494v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.13494 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 267 words
Related coverage
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026
WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
arXiv · Jun 16, 2026
WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
arXiv · Jun 4, 2026