Origin (Artila）
"Physical AI For The Built World"
San Francisco startup whose OG1 tool-changing mobile robot does autonomous drywall finishing and painting, with four units live on US interior fit-out sites.
Origin is an early-stage American construction robotics company that builds OG1, a mobile robot for autonomous interior wall finishing. It trades as Origin on origin.tech and is incorporated as Artila Robotics Inc. with its head office in San Francisco. The company was started in December 2024 by founder and chief executive Yogesh Ghaturle; an Indian engineering entity, Artila Robotics Private Limited, was registered in Bangalore on 25 November 2024 under CIN U62099KA2024PTC195239, with Yogesh Vilasrao Ghaturle, Tushar Makkar and Ashish Daga as directors. Accel and Better Capital are named as investors; neither the round size nor the total raised has been published.
OG1 is presented as a general-purpose construction robot whose first trades are drywall finishing and painting. It is a mobile platform with a modular tool system, so the same machine changes end tooling to take on additional trades, and the company states it is narrow enough to pass through the smallest doorways on a site and able to work across varying surfaces, angles and heights. Control policies are trained in high-fidelity simulation before deployment, and the robot carries onboard perception for real-time jobsite awareness and obstacle navigation. Target buildings are multi-family housing, offices, hotels and warehouses - interior fit-out work where the same wall detail repeats at scale.
The deployment record is short and the company publishes it as a timeline rather than as case studies. A first prototype was working in March 2025, first autonomy on a test site followed in May, the first customer jobsite deployment in July, a customer-ready product in September, and a first New York deployment in November 2025, carried out with general and trade contractors. As of the company's own public figures, four robots are in active service. Other performance claims on the site - multiples of time saved, margin expansion percentages, cost reduction per project, square footage and hours delivered - are self-reported and carry no third-party verification, so they are recorded here as marketing positioning rather than as facts.
Origin sits in a crowded interior-finishing niche: comparable robots include Okibo of Israel, ConBotics of Germany, Finish Robotics of the United States and Baubot of Austria, while Crunchbase lists Hadrian, Built Robotics and Dusty Robotics as competitors. What distinguishes Origin at this stage is the combination of a general-purpose, tool-changing platform rather than a single-trade machine, a US-India engineering structure, and backing from Accel less than a year after incorporation."
Primary type & automation activities this supplier delivers:
Contact Origin (Artila）
WEBSITE
https://origin.tech/HEADQUARTERS
India
Company Facts
Founded
2024
Primary Role
Manufacturer
Company Size
-
Primary Region
-
Annual Sales
-
Funding Stage
-
Funding Total
-
Humanoid Robot Demonstrates Agility on Monkey Bars in Latest Video Showcase
In the latest edition of Video Friday, a humanoid robot showcases its ability to traverse monkey bars, demonstrating advanced agility and perception of complex 3D structures. This task requires the robot to jump onto the structure, navigate through sparse bar interactions, and land safely, highlighting its whole-body motion capabilities. The significance of this demonstration lies in its implications for humanoid robotics, particularly in environments where navigating thin and overhanging geometries is essential. As humanoid robots become more adept at traversing challenging obstacles, the potential applications in search and rescue, disaster response, and other critical fields continue to expand. Looking ahead, the upcoming Humanoids Summit in Seoul and other robotics events scheduled for late 2026 will likely feature further advancements in humanoid robotics. No further timeline was disclosed at the time of publication.
Humanoid-robots Video-friday Drones Robot-videos Center-for-robot-assisted-search Quadruped-robots
ACE Robotics and NTU S-Lab Release Open-Source Puffin-World Multimodal Model
ACE Robotics and NTU S-Lab have announced the open-source release of Puffin-World, a multimodal world model that integrates physics, geometry, and appearance. This model utilizes the Puffin-16M dataset and achieves state-of-the-art camera absolute pose errors, reporting sub-degree accuracy across four public benchmarks. The significance of this release lies in its potential to enhance various applications in robotics and computer vision by providing a unified framework for understanding complex environments. By achieving such high accuracy in pose estimation, Puffin-World could facilitate advancements in autonomous navigation and scene understanding. Looking ahead, the impact of Puffin-World on the robotics community will be closely monitored, particularly in how it influences future research and development in multimodal models. No further timeline was disclosed at the time of publication.
Northrop Grumman's Lumberjack Drone Successfully Tests Quantum Navigation Technology
Sandbox AQ has successfully tested its quantum sensor-based Magnetic Navigation (MagNav) on Northrop Grumman’s Lumberjack drone, marking a significant milestone in unmanned aircraft systems. This test is the first of its kind for an attritable drone, showcasing the potential of quantum navigation in GPS-denied environments, which is increasingly relevant given current military operations. The successful integration of MagNav with Lumberjack's visual navigation system is crucial as the U.S. military seeks alternatives to GPS for navigation and targeting. The ongoing conflicts in Ukraine and West Asia highlight the need for resilient navigation systems that can operate effectively even when GPS signals are jammed or spoofed. This advancement could enhance operational capabilities in contested domains. Looking ahead, the deployment of Sandbox AQ’s AQNav technology in various aircraft platforms could revolutionize military navigation. The ease of integration into existing systems, as demonstrated by the rapid installation on Lumberjack, suggests a promising future for quantum navigation solutions in defense applications. No further timeline was disclosed at the time of publication.
Military
Tactile Sensing Technology Sees Significant Growth in Robotics Sector
Tactile sensing technology is gaining prominence in the robotics industry as humanoid robots transition from exhibition spaces to factory floors. Since 2026, funding in the tactile sensing sector has exceeded 7 billion yuan, with the penetration rate of tactile sensors in commercial humanoid dexterous hands rising from 20% to over 60% this year. This rapid growth is notable within the robotics components sector, highlighting a shift in robotic applications. While visual-language-action models have enhanced robots' environmental understanding and task planning, precision assembly and flexible grasping require tactile feedback for effective force control and slip detection. According to Qianjue Robotics founder Ma Daolin, tactile sensing is essential for high-precision industrial operations. The evolution of technology supports this need, as Qianjue Robotics' VTLA model integrates tactile modalities into traditional frameworks, enabling real-time perception of deformation, texture, and force distribution during contact. Their comprehensive tactile solution expands sensing from fingertips to palms, achieving a sensor density of 125 points per square centimeter and a force accuracy of 0.03 Newtons. As hardware costs decrease and data accumulation accelerates, tactile sensing is becoming a necessary capability in real-world operational scenarios.
Tactile Sensors Humanoid Robots Robotics Technology Industrial Automation
Vention Showcases Unified Platform Integrating Physical AI and Agentic AI at IMTS 2026
Vention is set to demonstrate its unified industrial automation platform at IMTS 2026, featuring both Physical AI and Agentic AI. The platform combines these two layers of intelligence to enhance robotics and machine operations, showcasing innovations such as the MachineAgent agentic cell. The significance of this development lies in its potential to streamline manufacturing processes through an interactive, end-to-end automated workflow. Attendees can witness live demonstrations of Physical AI capabilities, including Rapid Operator AI for deep bin picking and goal-driven collision-free path planning, which utilize advanced autonomous perception and robotic motion. Looking ahead, industry professionals should monitor how Vention's integration of these AI technologies influences manufacturing efficiency and automation trends. No further timeline was disclosed at the time of publication.
Ouster Partners with Flyability and GeoCue to Enhance Drone Mapping with Lidar Technology
Ouster has announced two significant partnerships aimed at expanding the use of lidar technology in commercial drone operations. The collaboration with Flyability focuses on integrating Ouster's lidar into the Elios 3 drone, which is designed for inspections in confined spaces like mine shafts and wastewater tunnels. Meanwhile, the partnership with GeoCue will see Ouster's Rev8 OS1 Max lidar integrated into TrueView drone mapping systems for utility surveying. These partnerships highlight the growing importance of lidar in enhancing drone capabilities, particularly in challenging environments where traditional GPS and cameras may fail. The Elios 3 drone, equipped with Ouster's compact OS0 lidar, enables real-time localization and collision avoidance, making it suitable for hazardous inspections. Ouster's CEO, Angus Pacala, emphasized the operational value of digital lidar in environments that conventional systems cannot easily access. Looking ahead, Flyability is evaluating Ouster's Rev8 lidar technology for future applications, which promises improved range, resolution, and color data. The companies plan to showcase their advancements at INTERGEO 2026 in Munich, Germany, from September 15-17, demonstrating how lidar is transforming the documentation of complex industrial environments.
Applications Drone News Drone News Feeds Inspection LiDAR News
Unitree Technology Unveils G1 Autonomous Robot's Real-Time Combat Capabilities
On September 7, Unitree released a 38-second video showcasing its G1 humanoid robot engaging in real-time combat against a human opponent. This marks a significant milestone as it is the first instance of a fully autonomous humanoid robot fighting without human remote control, demonstrating advanced decision-making capabilities. The importance of this development lies in the robot's ability to autonomously predict, evade, and counterattack in real-time, a feat that has previously required human intervention. The G1 robot adjusts its stance and actions based on the opponent's movements, showcasing a complete feedback loop from perception to execution, which is crucial for effective combat. Looking ahead, the G1 is set to compete in the CMG World Robot Competition in May 2025, where it will further demonstrate its capabilities. The video highlights the challenges of real-time decision-making in combat scenarios, emphasizing the need for rapid response and adaptation in unpredictable environments. No further timeline was disclosed at the time of publication.
Humanoid Robots Autonomous Systems Robotics Research Artificial Intelligence
Over 30 Companies Participate in the 9th China Robotics Summit in Hangzhou
The 9th China Robotics Summit took place on September 17-18 in Hangzhou, featuring over 30 companies and institutions. The event highlighted advancements in robotics, including humanoid, quadruped, industrial, service, and special robots, showcasing the industry's shift from basic functionalities to real-world applications. This summit is significant as it reflects the evolving landscape of robotics, where competition now hinges on comprehensive industrial collaboration rather than isolated components or algorithms. The focus has shifted towards the integration of AI, cloud computing, and advanced sensors, which enhance robots' capabilities in understanding environments and executing tasks. Looking ahead, the industry is expected to continue evolving, with an emphasis on how robots perceive their surroundings, understand tasks, and make decisions. The integration of key components such as dexterous hands, sensors, and precision manufacturing systems will play a crucial role in enhancing product performance and production efficiency.
Robotics AI System Integration Industrial Automation Supply Chain
ZhiYuan Unveils AGILE 2.0: Transforming Robotic Vision and Motion Capabilities
ZhiYuan has launched the AGILE 2.0 model, known as the AGIBOT Generative Intelligent Locomotion Engine, enabling robots to perceive, plan, and move with human-like agility. The innovative short film 'Acrobat BOT' showcases the robot's ability to perform complex tasks, such as jumping through fire hoops and balancing on a ball, demonstrating the advanced capabilities of AGILE 2.0. This development is significant as it addresses the challenges of synchronizing visual perception and motor control in robotics. While previous models struggled with dynamic coordination, AGILE 2.0 integrates environmental observation, terrain understanding, and full-body motion control into a cohesive system, allowing for real-time planning and execution. Looking ahead, AGILE 2.0's advancements in visual perception and dynamic interaction mark a pivotal shift in humanoid robotics, enabling operations in unstructured environments. No further timeline was disclosed at the time of publication.
Robotic Vision Intelligent Locomotion AI Robotics Dynamic Motion Control
Examining the Origins of Haptic Sensing Technology and Its Development Challenges
In the field of robotic haptic sensing, significant breakthroughs have emerged from years of technical accumulation and engineering capabilities. Leading haptic sensor companies have focused on multi-dimensional tactile perception, high-precision torque calculation, and heterogeneous array calibration, establishing a comprehensive intellectual property system. Their efforts have demonstrated that there are no shortcuts in haptic sensing; each aspect must be meticulously developed to create truly usable products. The emergence of new companies in 2026, which quickly introduce concepts like 'magnetized flexible materials' and 'exclusive replaceable electronic skin,' raises concerns. While their product images appear polished and their technical jargon comprehensive, comparisons with open-source projects like ReSkin and AnySkin reveal significant similarities in magnetic circuits, PCB designs, and algorithms. This suggests that some newcomers are attempting to simplify the complex development process into mere replication of existing technologies. To understand the implications of 'open-source rebranding,' it is essential to clarify the technological lineage of ReSkin, AnySkin, and eFlesh. The foundational work by Waseda University's Sugano Laboratory laid the groundwork for magnetic tactile skin technology, influencing subsequent developments by Meta AI and NYU. As these technologies evolve, the focus on low-cost, modular manufacturing continues to shape the future of haptic sensing applications.
Haptic Sensors Open Source Technology Robotics Innovation Technology Transparency
China’s Dexterous Hand Industry, 2026 Part 3 — The Players
Five vendor archetypes, MIR’s composite top ten, eight company profiles and six field deployments — every firm linked to the RobotToday supplier directory.
Teradyne’s IP Offensive and the Next Phase of Cobot Competition
Teradyne Robotics filed two European IP actions against Chinese cobot makers Elite Robots and JAKA within six months of 2026. This briefing maps the timeline, the differences between the cases, each side’s position, and what it signals about collaborative robot market competition.
Software, Compute and Interaction at WRC 2026
47 WRC 2026 exhibitors supply robot software, compute or interaction — but only 19 call themselves software companies. Five open artefacts, licence-checked.
WAIC Review 1/4: Embodied AI's Industrialization Wave: Financing Data, Unit Economics, and a Widening Split
China's embodied AI sector raised $12.5B in H1 2026, but WAIC 2026 speakers detailed ROI demands, power bottlenecks, and the mass-production-to-sales gap.
Introduction to Robotics J. J. Craig — RSF Top 10 Robot Education Textbooks · No. 6
Six of ten benchmark universities teach kinematics from Craig. Frames, transforms and D-H parameters: the language vendor manuals already speak.
FCC Robot Ban Takes Effect, Unitree Launches $620M IPO
The FCC's Covered List robot ban and a House-passed NDAA provision land within days of each other, while Unitree launches its $620M STAR Market IPO. A supply-chain and market-access update.
Pittsburgh Regional Alliance Convenes Nine CMU-Rooted Robotics Firms at Automate 2026
At Automate 2026, the Pittsburgh Regional Alliance convened nine robotics firms — most spun out of Carnegie Mellon — spanning materials, perception and AMRs.
Digital Twin, Physical AI & Robot OEM Readiness 2026: Platforms, VLA Models, LLM Programming
A balanced analysis of the robot intelligence revolution: multi-vendor digital twin platforms (NVIDIA, Siemens, Dassault, ABB, Rockwell, Hexagon), Physical AI VLA models (RT-2, pi0, GR00T N1, AgiBot), current Physical AI limitations, LLM robot programming, and the OEM readiness matrix across US, European, and Chinese manufacturers.
AI Space Data Centers: Power the Next Generation of Robotics
From Starcloud's $170M Series A to Google's Project Suncatcher and China's operational LEO constellations, AI space data centers are moving from concept to infrastructure. Here's what the robotics industry needs to know.
CONSTRUCTION ROBOTICS | Surface Finishing & Painting
Surface finishing robots are construction's hottest automation segment. Okibo, Canvas, Dusty Robotics, Pictobot, and Brightrobot are rewriting the economics of painting, drywall, and tile-setting. Key stat: Okibo's EG7+ cuts finishing labor costs 50% and operates 10x faster than manual crews.
