intellimentis / Fields / Robotics
Ro · Robotics
Robots that move, grasp and learn: the research and the first real deployments.
Nations agree to ‘elaborate’ on rules for AI-run ‘killer robots’ by 2028Al Jazeera English‘The doom of humanity’: will the quest to make robotic hands render us obsolete?The GuardianThe future of FijiCAL AI talented people... 114 youths, robotic talentedZDNet KoreaStart-up Sightera: How cool would that be if we could make the first cancer pill with AI here in Belgium?De StandaardNewsblog on AI: Rules for killer robots: States agree only on minimal compromiseSüddeutsche ZeitungForget rogue robots, it’s tech billionaires and AI cricket that should really terrify us | Barney RonayThe GuardianNASA’s Curiosity Mars Rover Collects SamplesNASAThe robot that lie for humans, 80 years ago, “AI Awakening”Chosun IlboRussia stalls UN bid to regulate AI 'killer robots' as talks near deadlineEuronewsRobot revolution comes to Roedean as historic school hosts UK-first demonstrationSussex ExpressThey called in about your friend's origins, but they're messing with him for a reason, says Emily Genatowski, who lives with his Chinese robot.HVGMuse’s Matt Bellamy wants an AI guitar – but still calls for human-made art and live performanceNMEDon't Lose the Future: Latent-Aware 4-Bit Quantization of World Action ModelsarXivControlling the Humanoid Robot H1-2 With a Simulated Biologically Plausible NetworkarXivMAWAM: A Multi-Agent World-Action Model for Coordinated ManipulationarXivVG-Steer: Visual-Geometric Policy Steering from In-Context Aligned AbstractionsarXivBridging vision-language reasoning and learned control for legged navigation in the wildarXivPlan your Self-Adaptation! Ontology-Mediated Task and Architecture Co-adaptation Planning for RobotsarXivDemonstration-Free Skill Composition for Navigation and ManipulationarXivCoachSI: Self-Improvement of Robot Policies with a Language CoacharXivFlashX: Scaling Robotic Experience Reuse for Embodied Agents with CBA-Based NAND FlasharXivBeyond Easy Clients: Difficulty- and Improvement-Aware Aggregation for Federated Reinforcement Learning in Robot NavigationarXivSAM 3 Sees More Than It Detects: Promptable Concept Maps Beyond CategoriesarXivCollision-Free Is Not Enough: Passage-Conditioned Navigation for Wheeled-Legged RobotsarXivAwaken-HI: Scaling Humanoid Intelligence with Whole-Body Human ExperiencearXivMind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic ManipulationarXivPGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-ManipulationarXivKairos: A Unified PDDL Planner for Robots: Plans in Milliseconds, with a Guarantee for Every AnswerarXivTopology-Driven Anti-Entanglement Control for Soft RobotsarXivImplicit Neural Representations of Individual BehaviorarXivTransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic MicrosurgeryarXivVision-Language-Action Models: A Life-Cycle Survey of Design, Training and DeploymentarXivActMem: From Latent Memory Reasoning to Grounded Robotic ActionarXivReference-Free Humanoid Skateboarding via Termination-Shaped Reinforcement LearningarXivAchieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection PipelinesarXivAgentRoboCritic: Understanding the Capability of Frontier Agents on Direct Robot ControlarXivAgent as Policy for Robotic ManipulationarXivMapping the Wind to Find the Source: Online Physics-Informed Gas Source Localization with Mobile RobotsarXivFerrofluid Shape Control with Deep Reinforcement LearningarXivWEVO: World Model-Enabled VLA Optimization for Whole-Body Loco-ManipulationarXivMoRE: Mixture-of-Experts for Multi-Physics Robotic World ModelsarXivDifferentiable Hydrodynamics for Whole-Body MPC of Underwater RobotsarXivWAMotor: Accelerating World Action Models via Speculative Inference under Dual Nonuniform Denoising DynamicsarXivLearning Ankle Exoskeleton Control for Reactive Standing Balance Through Neuromusculoskeletal SimulationarXivTrajectory-Calibrated Merging of Embodied PoliciesarXivGraF-VTA: Neuro-Symbolic Trajectory Generation from Vision and Temporal Logic via Graph-Based FusionarXivCauSyncVLA: Causal Latent World Modeling for Asynchronous Robot ControlarXivHindsight Self-Distillation: Teaching Robots to Act from the PresentarXivECHO: In-Context Behavior foundation model for Humanoid Whole-Body ControlarXivLearning optimal gaits and styles for terrain-adaptive quadruped locomotionarXivDynamic Human-Robot Role Allocation through Entropy-Based Monitoring and LLM ReasoningarXivUniVEP: Unifying Velocity and Endpoint Prediction for Robot ManipulationarXivPhysVAM: Physics-oriented Future Value Action Model for Dynamic Object ManipulationarXivSpatially Conditioned Trajectory DiffusionarXivA Practical Proprioceptive Data Collection Utility for the Unitree GO1arXivOne View, One Action: Spatially Generalizable VLAs through Observation-Aligned Experts and Cross Graph ConsistencyarXivPlanning to Stop: Factored Certification and Terminal Repair for Noncircular RobotsarXivEmbodyAgent: Post-Training Embodied VLM Agents via Distillation, SFT, and RLarXivTeaching Vision-Language-Action Models to Stop SafelyarXivI See You: Initial Multi-Robot LiDAR Registration with Mutual-Observation ChecksarXivLocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Whole-Body ControlarXivReasoning on Call: Efficient Agentic Robot Control for Long-Horizon Robot ManipulationarXivPUPPET: Physical-Unified Platform for Presence, Embodiment, and TeleoperationarXivAlignment Drives Reuse: Learning Generalizable Robot-Use Agents from Heterogeneous ExperiencearXivPhyDEX: A Benchmark for Physical Reasoning in Vision-Language-Action Models via Dynamic Extrinsic DexterityarXivA Tutorial on Complementarity-Based Contact Models for RoboticsarXivMIR-Depth: Multi-Range Refinement for Single-View RGB-D Depth Completion of Transparent ObjectsarXivLoopedWAM: Looped World Action Models for Elastic InferencearXivAn Autonomous Sea Turtle Robot that Follows Marine AnimalsarXivRoboForge: Cross-space Motion Refinement for Physically Executable Humanoid Whole-body TrackingarXiv3D Generation for Embodied AI and Robotic Simulation: A SurveyarXivSixthSense: Proprioception-Only Whole-Body Wrench Estimation for HumanoidsarXivOrchestrating Wheeled Mobile Robots Online without ConflictsarXivFlatness Preserves Instruction Following in Vision-Language-Action ModelsarXivSemantic Role-Structured World Model for Physical Interaction PlanningarXivA Physics-Consistent Benchmark for Contact-Rich Human-Robot Interaction in Assistive CarearXivGLoTouch: Global-to-Local Haptic Perception Using a Parallel Gripper for Object Search, Recognition, and Grasping Without External VisionarXivRAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action ModelsarXivRMRRT: Riemannian Barrier Metric RRT for Inequality-Aware Steering on Equality ManifoldsarXivPILOT: Guiding Long-Horizon World-Model Planning for Robot Manipulation with Imagined Subgoals and Policy PriorsarXiv