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:2609.33299v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the...
arXiv:2506. 22174v3 Announce Type: replace-cross Abstract: The transport industry has recently shown significant interest in unmanned surface vehicles (USVs), specifically for port and inland waterway transport.
arXiv:2505. 08222v3 Announce Type: replace-cross Abstract: Autonomous vehicles (AVs) offer a cost-effective solution for scientific missions such as underwater tracking.
The paper introduces an extension to the OceanSim underwater perception simulator, adding a Synthetic Data Generation pipeline that produces large, automatically labeled, photorealistic datasets with configurable scene and sensor settings. The authors evaluate this pipeline on a real-world sea urchin detection task, examining how different synthetic scene variations influence sim-to-real performance. They discuss the pipeline’s findings, limitations, and future directions for improving rendering fidelity, scene diversity, and sim-to-real generalization.
arXiv:2606. 08513v1 Announce Type: cross Abstract: Autonomous Underwater Vehicles (AUVs) traditionally rely on complex, heavily engineered pipelines for perception, path planning, and motion control.
arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and...
arXiv:2609.24526v2 Announce Type: replace Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints...
Mem2Ego introduces a vision‑language model for embodied navigation that combines global memory with egocentric visual inputs. By adaptively retrieving task‑relevant cues from a global memory module and aligning them with local perception, the framework improves spatial reasoning and decision‑making over long horizons. The method outperforms prior state‑of‑the‑art approaches on the HSSD and HM3D benchmarks and shows strong performance on a real robot.
arXiv:2606. 14397v1 Announce Type: new Abstract: As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities.
arXiv:2606.14397v4 Announce Type: replace Abstract: As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capab...
SonarLLM is a multimodal large language model that treats sonar as a native perceptual modality, combining a sonar‑specific encoder, physics‑aware feature enhancement, and reliability‑aware hierarchical fusion to align acoustic structure with optical semantics. The authors introduce SonarBench, a benchmark covering recognition, counting, visual question answering, and captioning across sonar‑only, optical‑only, and fusion settings, enabling controlled measurement of cross‑modal complementarity. SonarLLM achieves 72.0% macro accuracy on sonar‑only tasks and 68.7% under fusion, outperforming baselines by significant margins and demonstrating increasing fusion gains as optical visibility degrades.
arXiv:2601.13247v2 Announce Type: replace-cross Abstract: Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural ground...