Manipulation, locomotion, sim-to-real transfer and autonomous driving: learning systems that have to survive physics.
arXiv:2609.13083v2 Announce Type: replace-cross Abstract: In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and c...
arXiv:2609.16864v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks bec...
The paper introduces LCAP, a method for adapting photonic neural networks to real hardware by learning a shared correction from a population of chips and then personalizing each chip using only 32 fixed output probes. LCAP decomposes adaptation into a transferable population correction and a probe‑inferred latent personalization, allowing feed‑forward calibration without device‑specific optimization. Experiments on a simulated three‑layer 64‑mode MZI network show accuracy improvements from 80.4% to 93.4% and significant gains on unseen chips.
arXiv:2609.16186v1 Announce Type: cross Abstract: Autonomous soft-tissue cancer surgery has been limited to interventions on organ surfaces, because current systems cannot perceive and adapt to anato...
DGSG-Mind introduces a hybrid instance-aware 3D Gaussian dynamic scene graph system that integrates open‑vocabulary semantic information into dynamic 3D scene representations. By coupling a probabilistic voxel grid with explicit 3D Gaussians, it achieves robust cross‑modal instance fusion, incremental semantic mapping, and dynamic change handling through Gaussian‑based relocalization and masked refinement. The system builds a hierarchical scene graph and a 3D Gaussian Mind for multimodal reasoning, achieving state‑of‑the‑art zero‑shot 3D visual grounding and strong performance in open‑vocabulary semantic segmentation and scene reconstruction, and is demonstrated on real‑world robots.
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.
SlotDiT introduces a text-guided Diffusion Transformer that operates in a slot-based latent space, decomposing scenes into object-centric slots and autoregressively denoising future slot trajectories to predict scene dynamics. The model is conditioned on a reference image and a language instruction, enabling it to generate video content that reflects both visual context and textual guidance. Experiments comparing slot-based representations to VAE-based and semantics-aligned alternatives show that SlotDiT achieves competitive video generation quality while improving task-completion rates across four robotic datasets and offering a more computationally efficient latent representation.
arXiv:2609.16852v1 Announce Type: new Abstract: Industrial IoT environments increasingly deploy autonomous mobile robots for tasks such as material handling, product assembly, or infrastructure inspe...
Mem-World introduces a memory‑augmented action‑conditioned world model for robot manipulation, featuring W‑VMem—a 4D wrist‑view‑centered surfel‑indexed memory that anchors historical observations to evolving surface elements. By explicitly modeling when and where scene elements are observed, the system retrieves geometry‑aware history frames during generation, providing informative, non‑redundant context for future action predictions. Experiments demonstrate that Mem‑World produces persistent rollouts, improves policy evaluation reliability (14.5 % higher Pearson correlation with real‑world performance), and boosts long‑horizon task success rates from 58 % to 72 % using synthetic data generation.
arXiv:2609.16697v1 Announce Type: cross Abstract: World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interv...
TARC (Time‑Adaptive Robotic Control) is a reinforcement‑learning framework that lets a policy predict both a control action and how long it should be applied, thereby learning temporally extended actions. By optimizing task performance under constraints on the number of control switches, TARC can adapt its control rate online, using high‑frequency feedback only when necessary. Experiments on a high‑speed RC car, a Unitree Go1 quadruped, and a vision‑language action model show that TARC matches the performance of high‑frequency discrete‑time controllers while operating at less than half their control frequency.
arXiv:2609.16075v1 Announce Type: cross Abstract: Flexible robotic production requires joint decisions on process progression, material routing, resource assignment, temporary cooperation, and simult...
arXiv:2512.15708v2 Announce Type: replace Abstract: Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature represen...
arXiv:2609.16319v1 Announce Type: cross Abstract: Dexterous grasping is usually conducted for specific tasks, leading to heterogeneous constraints such as specific approach directions, desired contac...
arXiv:2609.16686v1 Announce Type: cross Abstract: Estimating deformable object states remains a fundamental challenge in robotics and simulation. We propose a novel factor graph-based framework for p...
arXiv:2609.17387v1 Announce Type: new Abstract: Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-chang...
GeoLAM is a framework that learns geometry‑grounded latent actions from unlabeled human videos. It uses future‑frame reconstruction with a frozen geometric feature hierarchy and motion supervision from a 4D geometry teacher to capture 3D displacement, image‑plane motion, and surface‑orientation changes. After pretraining, the representation serves as transition targets for a world‑action model trained on robot demonstrations, enabling denoised latent actions and executable action chunks without requiring hand‑pose annotations or future‑video generation during deployment.
arXiv:2609.17419v1 Announce Type: new Abstract: Long-horizon LLM agents must maintain task state across extended sequences of observations, actions, tool calls, and intermediate beliefs. We study the...
MEgoVista is an offline pipeline that converts a single unprepared egocentric video into metric two‑hand and head motion within a gravity‑aligned world frame. It uniquely reconstructs motion in environments beyond studio volumes, uses calibrated stereo for absolute scale, and evaluates its outputs against independent optical capture to audit accuracy. The system thus expands the settings where high‑fidelity hand‑motion labels can be generated from natural, head‑worn recordings.
EventEgoHands++ is a new framework for reconstructing 3D hand meshes from egocentric event-based cameras. It introduces a Hand Detector that provides instance-level bounding boxes and masks for left and right hands, and an Adaptive Attention module that uses these detections to model spatial relationships and interactions. The authors extend the synthetic N-HOT3D dataset and create EEH‑R, a large real-world event-based egocentric hand dataset with about 1 million annotated frames, and show that their method outperforms existing baselines on both synthetic and real data.