arXiv AI
AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 31
OceanGym: A Benchmark Environment for Underwater Embodied Agents
OceanGym is the first comprehensive benchmark for underwater embodied agents, featuring eight realistic task domains and a unified agent framework powered by Multi‑modal Large Language Models (MLLMs). It challenges agents to process optical and sonar data, navigate complex environments, and achieve long‑horizon goals amid low visibility and dynamic currents. Experiments show significant performance gaps between current MLLM agents and human experts, underscoring the difficulty of perception, planning, and adaptability in ocean settings.
arXiv Machine Learning
Jun 15
FlowMo-WM: A World Model with Object Momentum and Hidden Ambient Drift
arXiv:2606. 13817v1 Announce Type: cross Abstract: World models in robot learning predict future states from visual observations and actions, enabling agents to reason about the consequences of their controls.
arXiv AI
Sep 25
Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage
Underwater C³-JEPA is an object‑centric, cross‑view predictive world model designed for near‑field heavy‑load ROV salvage. It encodes synchronized multi‑camera RGB observations and vehicle control signals into task‑object and context tokens, fuses cross‑camera evidence via held‑out‑view attention, and predicts future states conditioned on control without using contact sensors. The model demonstrates superior transfer of task‑relevant information to downstream probes compared to a reconstruction‑free baseline, supports model‑predictive control and imagined‑rollout training, and validates its effectiveness on real underwater video by accurately recovering withheld camera states and maintaining predictive lead over persistence.
arXiv Computer Vision
Sep 16
World-Action Models for Robot Learning and Control: A Survey
The survey "World-Action Models for Robot Learning and Control" reviews recent advances in coupling future world prediction with executable action generation for robots in open environments. It clarifies the scope of World-Action Models (WAMs) relative to conventional world models, model-based RL, and Vision‑Language‑Action policies, and organizes existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. The paper also surveys applications in manipulation, navigation, and autonomous driving, summarizes datasets, benchmarks, and metrics, and discusses key challenges such as action alignment, spatial consistency, long‑horizon memory, and efficient inference.
arXiv AI
Aug 21
DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
arXiv:2608. 20114v1 Announce Type: new Abstract: Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control.
arXiv AI
Jun 6
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
arXiv:2606. 05979v1 Announce Type: cross Abstract: We propose world-language-action (WLA) models as a new class of embodied foundation models.