MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight

• URL: http://arxiv.org/abs/2608.04657v2
• Date: Thu, 06 Aug 2026 12:11:22 GMT
• Title: MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
• Abstract summary: MobileWAM is a mixture-of-transformers architecture that fuses a pretrained video diffusion transformer with a lightweight action expert.<n>MobileWAM surpasses state-of-the-art mobile manipulation policies on ManiSkill-HAB and fine-tunes to a real ARX Lift2 mobile manipulator.
• Score: 30.838499233332684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World action models (WAMs) built on video generation backbones are a rising recipe for robot learning, yet remain confined to tabletop manipulation. Mobile manipulation demands simultaneous locomotion and whole-body manipulation amid scene-scale dynamics, yet is still dominated by dynamics-blind visual encoders with hand-crafted coordination. We bridge this gap with MobileWAM, a mixture-of-transformers architecture that fuses a pretrained video diffusion transformer with a lightweight action expert through layerwise joint attention, translating internet-scale motion priors into whole-body control. To reconcile the heterogeneous dynamics of moving and manipulating, each feed-forward layer of the action expert becomes a three-expert mixture of shared, locomotion, and manipulation experts, softly routed by the motion intent in the action tokens. To densify supervision, we further propose Chain-of-Foresight (CoF): intermediate representations sequentially predict a chain of future latent chunks, each step conditioned on its predecessor. CoF pairs naturally with our decoupled video--action denoising scheme. At deployment, the WAM serves as a pure current-frame encoder; foresight acts only through gradients, so at inference the foresight chain and video generation are discarded, leaving only policy-level cost. MobileWAM surpasses state-of-the-art mobile manipulation policies on ManiSkill-HAB and fine-tunes to a real ARX Lift2 mobile manipulator across diverse tasks with strong generalization. Code will be released soon.

Related papers

• MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control [63.85634404397772]
  MobileVLA-R1 2.0 is an RL-enhanced vision-language-action framework for mobile robots.<n>It learns multi-granularity reasoning over embodied trajectories through supervised Chain-of-Thought (CoT) alignment and reinforcement learning.<n>We conduct evaluations on language-guided navigation, quadruped control, and humanoid mobile manipulation, covering VLN-CE, QUARD, and real-world deployments on Unitree Go2 and G1 robots.
  arXiv  Detail & Related papers  (2026-09-05T20:31:14Z)
• DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation [9.154987050049268]
  We introduce DECOWAM, a whole-body world-action model that separates camera ego-motion from base and arm actions.<n>On a fixed replay protocol, DECOWAM improved both future-video and action prediction over FastWAM, reducing action MSE by 21.7% with 25.95M trainable adaptation parameters.<n>These results show that embodiment-aware factorization can support parameter-efficient joint visual prediction and whole-body control under moving viewpoints.
  arXiv  Detail & Related papers  (2026-08-20T14:44:11Z)
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model [27.262271208923995]
  ABot-M0.5 is built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency.<n> Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy.
  arXiv  Detail & Related papers  (2026-07-01T09:21:20Z)
• MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation [17.392786435444062]
  We present MotionWAM, a real-time WAM that drives autonomous humanoid loco-manipulation from a single egocentric camera.<n>A three-stage learning framework progressively adapts the video world model to egocentric visual dynamics.
  arXiv  Detail & Related papers  (2026-06-08T08:50:14Z)
• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• Astra: General Interactive World Model with Autoregressive Denoising [73.6594791733982]
  Astra is an interactive general world model that generates real-world futures for diverse scenarios.<n>We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations.<n>Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions.
  arXiv  Detail & Related papers  (2025-12-09T18:59:57Z)
• FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video Generation [50.39748673817223]
  We introduce two training-free, inference-time techniques that fully exploit explicit action parameters in robot video generation.<n>First, action-scaled classifier-free guidance dynamically modulates guidance strength in proportion to action magnitude, enhancing controllability over motion intensity.<n>Second, action-scaled noise truncation adjusts the distribution of initially sampled noise to better align with the desired motion dynamics.
  arXiv  Detail & Related papers  (2025-09-29T03:30:40Z)
• Precise Action-to-Video Generation Through Visual Action Prompts [62.951609704196485]
  Action-driven video generation faces a precision-generality trade-off.<n>Agent-centric action signals provide precision at the cost of cross-domain transferability.<n>We "render" actions into precise visual prompts as domain-agnostic representations.
  arXiv  Detail & Related papers  (2025-08-18T17:12:28Z)
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining [65.8971623698511]
  We build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR)<n>PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining.<n>Experiments on the ManiSkill benchmark show that PAR achieves a 100% success rate on the PushCube task.
  arXiv  Detail & Related papers  (2025-08-13T13:54:51Z)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)
• Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics [79.4785166021062]
  We introduce Puppet-Master, an interactive video generator that captures the internal, part-level motion of objects.<n>We demonstrate that Puppet-Master learns to generate part-level motions, unlike other motion-conditioned video generators.<n>Puppet-Master generalizes well to out-of-domain real images, outperforming existing methods on real-world benchmarks.
  arXiv  Detail & Related papers  (2024-08-08T17:59:38Z)

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.