#Robotics
Latest news articles tagged with "Robotics". Follow the timeline of events, related topics, and entities.
Articles (30)
-
🇺🇸 CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines
[USA]
arXiv:2602.22452v1 Announce Type: new Abstract: A reliable action feasibility scorer is a critical bottleneck in embodied agent pipelines: before any planning or reasoning occurs, the agent must iden...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation
[USA]
arXiv:2602.20200v1 Announce Type: cross Abstract: Hierarchical Vision-Language-Action (VLA) models have rapidly become a dominant paradigm for robotic manipulation. It typically comprising a Vision-L...
Related: #Artificial Intelligence, #Computer Vision -
🇺🇸 Cooperative-Competitive Team Play of Real-World Craft Robots
[USA]
arXiv:2602.21119v1 Announce Type: cross Abstract: Multi-agent deep Reinforcement Learning (RL) has made significant progress in developing intelligent game-playing agents in recent years. However, th...
Related: #Multi-agent reinforcement learning, #Simulation-to-real transfer -
🇺🇸 Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids
[USA]
arXiv:2602.21174v1 Announce Type: cross Abstract: Hierarchical, multi-resolution volumetric mapping approaches are widely used to represent large and complex environments as they can efficiently capt...
Related: #Path Planning, #Multi-Resolution Mapping -
🇺🇸 Sensory-Motor Control with Large Language Models via Iterative Policy Refinement
[USA]
arXiv:2506.04867v4 Announce Type: replace Abstract: We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly m...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Learning Physical Principles from Interaction: Self-Evolving Planning via Test-Time Memory
[USA]
arXiv:2602.20323v1 Announce Type: cross Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planne...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
[USA]
arXiv:2602.21198v1 Announce Type: cross Abstract: Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of i...
Related: #Machine Learning, #Artificial Intelligence -
🇺🇸 What Matters for Simulation to Online Reinforcement Learning on Real Robots
[USA]
arXiv:2602.20220v1 Announce Type: cross Abstract: We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world training r...
Related: #Reinforcement Learning, #Machine Learning -
🇺🇸 "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation
[USA]
arXiv:2506.04500v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematical, an...
Related: #Artificial Intelligence, #Natural Language Processing -
🇺🇸 SIT-LMPC: Safe Information-Theoretic Learning Model Predictive Control for Iterative Tasks
[USA]
arXiv:2602.16187v1 Announce Type: cross Abstract: Robots executing iterative tasks in complex, uncertain environments require control strategies that balance robustness, safety, and high performance....
Related: #Learning‑Based Control, #Model Predictive Control, #Information Theory, #Safety in Automation -
🇺🇸 RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation
[USA]
arXiv:2602.16444v1 Announce Type: cross Abstract: The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike data collection from ...
Related: #Data collection and curation, #Machine learning / pre‑training, #Agentic systems, #Task generation -
🇺🇸 Test-Time Adaptation for Tactile-Vision-Language Models
[USA]
arXiv:2602.15873v1 Announce Type: cross Abstract: Tactile-vision-language (TVL) models are increasingly deployed in real-world robotic and multimodal perception tasks, where test-time distribution sh...
Related: #Multimodal artificial intelligence, #Test‑time adaptation, #Sensor reliability, #Distribution shifts -
🇺🇸 Amazon halts Blue Jay robotics project after less than six months
[USA]
Amazon said Blue Jay's core tech will be used for other robotics projects and the employees who worked on it were moved to other projects.
Related: #Technology, #Corporate Strategy -
🇺🇸 Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance
[USA]
arXiv:2602.12288v1 Announce Type: cross Abstract: With the growth of intelligent civil infrastructure and smart cities, operation and maintenance (O&M) increasingly requires safe, efficient, and ener...
Related: #Infrastructure, #Energy Efficiency, #AI Applications -
🇺🇸 ForeAct: Steering Your VLA with Efficient Visual Foresight Planning
[USA]
arXiv:2602.12322v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Learning Native Continuation for Action Chunking Flow Policies
[USA]
arXiv:2602.12978v1 Announce Type: cross Abstract: Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk ...
Related: #Artificial Intelligence, #Computer Vision -
🇺🇸 Monocular Reconstruction of Neural Tactile Fields
[USA]
arXiv:2602.12508v1 Announce Type: cross Abstract: Robots operating in the real world must plan through environments that deform, yield, and reconfigure under contact, requiring interaction-aware 3D r...
Related: #3D Reconstruction, #Artificial Intelligence -
🇺🇸 PMG: Parameterized Motion Generator for Human-like Locomotion Control
[USA]
arXiv:2602.12656v1 Announce Type: cross Abstract: Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical cha...
Related: #Locomotion Control, #Machine Learning -
🇺🇸 ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
[USA]
arXiv:2602.12691v1 Announce Type: cross Abstract: We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Cent...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Upside Robotics is reducing fertilizer use and waste in corn crops
[USA]
Upside Robotics builds autonomous solar-powered robots that can help farmers reduce their fertilizer use by 70%.
Related: #Agriculture, #Sustainability -
🇺🇸 Humanoid robot startup Apptronik has now raised $935M at a $5B+ valuation
[USA]
Apptronik has sold another $520 million in a Series A extension to existing and new investors like Google and Mercedes-Benz.
Related: #Venture Capital, #Artificial Intelligence -
🇺🇸 Boston Dynamics CEO Robert Playter steps down after 30 years at the company
[USA]
Robert Playter announcd he is leaving Boston Dynamics after 30 years at the company in various roles, including six years as CEO.
Related: #Technology, #Business Leadership -
🇺🇸 Extended to Reality: Prompt Injection in 3D Environments
[USA]
arXiv:2602.07104v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse a...
Related: #Cybersecurity, #Artificial Intelligence -
🇺🇸 MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation
[USA]
arXiv:2602.07082v1 Announce Type: cross Abstract: When embodied AI is expanding from traditional object detection and recognition to more advanced tasks of robot manipulation and actuation planning, ...
Related: #Artificial Intelligence, #Computer Vision -
🇺🇸 Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
[USA]
arXiv:2602.07055v1 Announce Type: new Abstract: Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at pa...
Related: #Artificial Intelligence, #Spatial Reasoning -
🇺🇸 Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
[USA]
arXiv:2602.08373v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise as planners for embodied AI, but their stochastic nature lacks formal reasoning, preventing strict safety gua...
Related: #Artificial Intelligence, #Safety -
🇺🇸 VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
[USA]
arXiv:2602.07399v1 Announce Type: new Abstract: Vision--Language--Action (VLA) models bridge multimodal reasoning with physical control, but adapting them to new tasks with scarce demonstrations rema...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning
[USA]
arXiv:2602.08734v1 Announce Type: new Abstract: Solving partially observable Markov decision processes (POMDPs) requires computing policies under imperfect state information. Despite recent advances,...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Leveraging Adaptive Group Negotiation for Heterogeneous Multi-Robot Collaboration with Large Language Models
[USA]
arXiv:2602.06967v1 Announce Type: cross Abstract: Multi-robot collaboration tasks often require heterogeneous robots to work together over long horizons under spatial constraints and environmental un...
Related: #Artificial Intelligence, #Automation -
🇺🇸 Realistic Synthetic Household Data Generation at Scale
[USA]
arXiv:2602.07243v1 Announce Type: cross Abstract: Advancements in foundation models have catalyzed research in Embodied AI to develop interactive agents capable of environmental reasoning and interac...
Related: #Artificial Intelligence, #Data Science