Reglamento (UE) 2023/1230 de máquinas
Sustituye a la Directiva de Máquinas. Será aplicable desde el 20 de enero de 2027 e incorpora requisitos sobre software de seguridad, ciberseguridad y máquinas con comportamiento autónomo.
Fuente oficialObservatorio de Robótica
Robótica: investigación al día y normativa explicada
Robots industriales, colaborativos, móviles, humanoides y drones: lo que se publica cada día y las normas que debes cumplir.
Regulación y normas
Última revisión: octubre de 2026. Explicación propia; no sustituye al texto oficial.
Reglamento (UE) 2024/1689 de IA
Los sistemas de IA que actúan como componente de seguridad de productos del Anexo I (como las máquinas) se consideran de alto riesgo, con obligaciones aplicables según su calendario.
Fuente oficialISO 10218-1 e ISO 10218-2 (2025)
Requisitos de seguridad para robots industriales y para su integración en células. La edición de 2025 incorpora los requisitos de robótica colaborativa de la antigua ISO/TS 15066.
Fuente oficialRadar de investigación en robótica
Información actualizada a: 9 oct 2026, 21:16· Fuente: arXiv · Robótica (cs.RO)· 40 elementos guardadosSe actualiza automáticamente
- cs.RO· Jiayu Wang, Yue Yu, Bin Zhu et al.
SpatialHarness: Test-Time Spatial Scaffolding for Fine Robotic Manipulation
Frontier multimodal foundation models (e.g., GPT-6 Astra) have recently shown strong potential for direct robotic control, yet their performance on fine manipulation remains limited. We argue that an important source of failure is not necessarily insufficient policy capability, but insufficient spatial observability…
Leer en arXiv - cs.RO· Dechen Gao, Yue Yang, Ben Abbatematteo et al.
Generative Neural Retargeting for Human-to-Robot Dexterous Manipulation
Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed directly on robots. Inverse kinematics (IK) retargets human motion to robots efficiently but ignores dynamics, often producing infeasible motions.
Leer en arXiv - cs.RO· Zhiwei Xue, Jia Yue Kam, Jinhang Qiu et al.
Control-Ready Uncertainty for Trajectory Diffusion
Diffusion models can represent complex, multimodal trajectory distributions, but extracting uncertainty from them typically requires costly Monte Carlo sampling. This limits their use in real-time control, where robots must rapidly assess risk and maintain safety margins.
Leer en arXiv - cs.RO· Qi Zhang, Xikun Liu, Qijun Qin et al.
GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial, and GNSS measurements. Existing fusion methods, however, share a scan-to-map front-end with two failure modes.
Leer en arXiv - cs.RO· Chen Cai, Steven Liu
A Physics-Informed Collision Learning Framework for Collaborative Robot Motion Generation
Close-proximity multi-arm manipulation requires collision models that are both geometrically accurate and differentiable enough for real-time optimization. Classical geometry checkers provide reliable distances but are difficult to use inside gradient-based model predictive control, while conservative proxy models c…
Leer en arXiv - cs.RO· Gokul Puthumanaillam, Tao Sun, Elie Aljalbout et al.
ARC: A Reasoning Recipe for Robot Foundation Models
The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale. We show that there exists an effective and efficient complementary approach: the right reasoning recipe can substantially improve the zero-shot task performance of exi…
Leer en arXiv - cs.RO· Kairui Hu, Siyuan Hu, Fangzhou Hong et al.
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time. We propose a different view: the embodied world is an Embodied Turing Machine, whose tape is the robot and environment …
Leer en arXiv - cs.RO· Linkai Liu, Yuntian Zhang, Zhenshan Bing et al.
LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild
Direct visual navigation policies generate trajectories efficiently but do not explicitly evaluate their future consequences. Generative navigation world models provide this foresight through visual rollouts, which are costly when evaluating multiple candidates.
Leer en arXiv - cs.RO· Yu Liu, Hetian Guo, Tianlv Huang et al.
PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies
Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future representation is modeled and how it conditions action generation. We introduce PLaW-VLA, which models task-relevant future states…
Leer en arXiv - cs.RO· Adrian Fuhrer, Joseph Church, Oliver Fischer et al.
Toward Lunar Legged Robots: Field Deployment Lessons at LUNA
Legged robots are promising candidates for future lunar surface missions because they can traverse steep, loose, and obstacle-rich terrain that challenges conventional wheeled rovers. However, readiness for lunar deployment is limited by uncertainties in foot-regolith interaction, dust generation, illumination-drive…
Leer en arXiv - cs.RO· Bjoern-Felix Dettmar, Arne Roennau
Walking on Roofs: Exploring the Potential of Walking Robots for Construction Work on Roofs
This paper investigates the feasibility of deploying quadruped walking robots for the automation of work in roof environments. While quadrupeds have demonstrated versatility across various domains, their large-scale deployment remains limited, partly due to lack of application-specific designs.
Leer en arXiv - cs.RO· Eran Iceland, Alexander Tuisov, Oren Gal et al.
Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods
We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rather than introducing a new planner, we construct a unified benchmark in which representative classical and learning-based methods face the same environments, motion co…
Leer en arXiv - cs.RO· Bowen Yang, Xinliang Xiao, Wenjing Zhang et al.
Fixed-Reference Pose Residuals for Measuring Cross-Dataset Cue Transfer in Human-Robot Interaction Anticipation
Social and service robots in public spaces need to anticipate which nearby person is about to approach and touch them, so that a response can be prepared before contact. It is largely unknown which cues support this anticipation when a model trained with one robot is used on another robot at a different site.
Leer en arXiv - cs.RO· Junjie Xie, Chuxuan He, Junkai Huang et al.
From Language to Motion: Task-Conditioned Focal-Stack Trajectory Integration for Microscopic Robots
Microscopic robots require accurate task geometry despite changes in language, parts, and focus. We present a semantic-to-physical framework that maps instructions to constrained geometric operators, reuses frozen open-vocabulary perception, and integrates locally reliable focal-plane trajectories by confidence weig…
Leer en arXiv - cs.RO· Yuchen Zhou, Jiacheng You, Weikang Wan et al.
Residual Modeling Closes the Regression and Generative Policy Gap in Robot Learning
Learning from demonstration has enabled impressive robot behaviors. A common choice for policy learning is to use diffusion or flow matching (Flow-Policies), which often outperforms direct action regression trained with mean squared error (MSE-Policies).
Leer en arXiv - cs.RO· Cody Sheltraw, Tsimafei Lazouski, Maani Ghaffari et al.
Sim-to-Real RL for ASVs using SysID
Autonomous Surface Vehicles (ASVs) operating in dynamic marine environments require robust control policies for tasks such as path following and station keeping, making reinforcement learning (RL) a promising alternative to classical controllers. However, existing ASV simulators rarely support parallel environments …
Leer en arXiv - cs.RO· Weizhan Huang, Cheng Hu, Edoardo Ghignone et al.
MAP2: Model- and Acceleration-Based Pursuit with MPC and Gaussian Process Residual Learning for Autonomous Racing
Autonomous racing requires accurate trajectory tracking near the handling limits of a vehicle while maintaining low computational latency. Geometric controllers are computationally efficient, but the Ackermann steering geometry becomes invalid under limit-handling conditions.
Leer en arXiv - cs.RO· Jie Chen, Ruofei Bai, Yuxin Cai et al.
MiniWAM: Learning Compact Future Targets for Efficient World-Action Modeling
World modeling has emerged as an effective co-training objective for robot policies, giving rise to World Action Models (WAMs) that jointly predict actions and future states. However, most WAMs predict future states in the native representation space of pretrained visual backbones, resulting in high-dimensional targ…
Leer en arXiv - cs.RO· Yuxin Chen, Senqiao Yang, Zixuan Wang et al.
RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control
Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery methods based on repeated vision-language reasoning or iterative online optimization can incur substantial latency, delaying intervention.
Leer en arXiv - cs.RO· Minye Wu, Zehao Wang, Tinne Tuytelaars
Unifying Policy Learning and State Prediction through Spatial Language Modeling
Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial Language Modeling, which represents scene contours, goals, action targets, and future states with a shared vocabulary of discrete coordinates and semantic tokens.
Leer en arXiv