Config
"General-purpose bimanipulation, built on real-world data."
Builds data infrastructure and foundation models for general-purpose bimanual robotic manipulation.
Config (Config Intelligence Inc.) is a robotics software and AI company building the data infrastructure and technology that enable general-purpose bimanual manipulation. The company develops a platform, Loop, that turns real-world human and robot demonstrations into deployable, task-specific robot policies through six composable modules spanning data collection to evaluation, powered by two GPU-based engines. Alongside the platform it develops CFG-1, a first-generation robot foundation model for bimanual manipulation trained on in-house human and robot data and adaptable to a customer task within hours; the company reports more than 10,000 training hours and sub-50-millisecond inference for the model. Config's approach centers on closing the loop between data and deployment, validating data by training models and testing them on physical robots, and working directly with customers to convert demonstration data into real-world robot deployments. Its published research and engineering work covers long-horizon memory for vision-language-action models, two-handed task execution across diverse real-world settings, and robots operating safely in environments where people are present. The team comprises AI and robotics engineers and scientists with backgrounds at organizations including Google, Meta, Waymo, NAVER, UC Berkeley, Harvard, KAIST and the University of Washington.
The company operates offices in San Jose, California in the United States, in Seoul, South Korea, and in Hanoi, Vietnam. Config positions its products around physical AI for manipulation, providing data pipelines, foundation models and deployment support for partners building bimanual robotic systems.
Primary type & automation activities this supplier delivers:
Contact Config
WEBSITE
https://config.inc/HEADQUARTERS
United States
Company Facts
Founded
-
Primary Role
Software/Algorithm
Company Size
-
Primary Region
North America
Annual Sales
-
Funding Stage
-
Funding Total
-
Keywords
- Config
- robotics (verify)
- bimanual manipulation
- robot foundation model
- physical AI
- robot learning
- vision-language-action
- robotics data infrastructure
- manipulation policies
- Software/Algorithm
- Control & Software
- Manufacturing
Shenzhen's Qiaojie Robotics Aims to Redefine Robotics with New Operating System
Qiaojie Robotics has emerged as a leader in motion control for bipedal robots, claiming to have the highest number of configurations globally, according to founder Shang Yangxing. At the 2026 World Robotics Conference, the company showcased its RoboCraft AI and discussed advancements in embodied intelligence technology with industry partners. The significance of Qiaojie's approach lies in addressing a major pain point in the robotics industry: the need for teams to relearn basic functions with each new robot. Shang Yangxing emphasized that their goal is to create a universal operating system that encapsulates the underlying capabilities of robotic hardware, making it accessible for users unfamiliar with robotics. Looking ahead, Qiaojie Robotics is focused on developing a three-layer operating system, with the Motion layer as its foundation. This approach differentiates it from traditional systems like ROS, which do not encapsulate motion capabilities effectively. No further timeline was disclosed at the time of publication.
Robotic Operating Systems Motion Control Humanoid Robots AI Robotics Innovation
Pudu Robotics Introduces MP2000 Autonomous Forklift for Efficient Material Transport
Pudu Robotics has launched the MP2000, an AI-powered autonomous forklift designed for efficient floor-to-floor material transport in warehouses and factories. This new model features pallet pickup cycles as quick as 20 seconds, enhancing the company's portfolio of autonomous mobile robots (AMRs) for high-frequency, heavy-payload transport in busy logistics environments. The MP2000 is equipped with advanced 3D lidar and depth cameras, allowing it to identify pallet locations and adjust its approach in real time. This capability ensures safe navigation through facilities, avoiding obstacles while validating pallet sizes and configurations. The MP2000 supports various pallet formats and adapts to non-standard load carriers, making it versatile for different operational needs. As part of a distributed fleet, the MP2000 can coordinate with other Pudu Robotics AMRs, enhancing overall efficiency. It also features a manual operator override for use as a powered manual forklift. The vehicle's ability to communicate with peripheral equipment like doors and elevators further streamlines access to controlled areas within facilities. No further timeline was disclosed at the time of publication.
Automated Warehouse Autonomous Mobile Robots (AMRs) Logistics Manufacturing News Pudu Robotics
Rodriguez Unveils Movotrak Cobot Transfer Unit to Enhance Automation Flexibility
Rodriguez has launched the Movotrak Cobot Transfer Unit (CTU), a collaborative linear transfer system that enables a cobot to operate across multiple workstations with an impressive range of up to 10 metres. This innovative system is designed to enhance robot utilization by allowing a single cobot to perform tasks at various positions along a production line, rather than being confined to one location. The introduction of the Movotrak CTU is significant for manufacturers as it reduces the need for repositioning or reconfiguring automation equipment when production demands shift. A standout feature of this system is its integrated collision detection, which is claimed to be the only one of its kind on the market. This capability allows the system to detect collisions while in motion, enhancing safety in environments where humans and automated systems work closely together. Looking ahead, the Movotrak CTU's modular design and compatibility with various standard cobots present opportunities for manufacturers to optimize their production setups. The system's ability to be installed in multiple orientations and its Freedrive function for manual guidance further simplify the integration process. No further timeline was disclosed at the time of publication.
Industrial robots News Robotics cobots collaborative robots industrial automation
World Humanoid Robot Games to Feature 666 Teams and 2,056 Robots This August
The second World Humanoid Robot Games is set to open on August 22 at the Ice Ribbon, featuring 666 teams and 2,056 robots. This marks a significant increase of 138% in team participation and a quadrupling of the number of robots compared to previous events. This year's games highlight the growing interest in humanoid robotics, with industry figures noting a convergence in machine configurations and a rise in core parts capacity and orders. However, challenges remain, as scenarios are still unsettled and hardware has not yet reached industrial-grade quality. As the event approaches, attention will be on the evolving landscape of humanoid robotics, particularly the increasing data demand, which has surged from thousands of hours to tens of millions. No further timeline was disclosed at the time of publication.
Robots Start Adapting Their Forms to Environments at WRC 2023
At this year's WRC, an intriguing trend emerged: robots are beginning to adapt their physical forms to better suit their environments. While discussions in the past focused on advanced models and capabilities, the practical need for adaptability became evident when robots faced real-world challenges, such as navigating through doorways or adjusting to varying heights of workspaces. This shift in focus is significant as it highlights the importance of deploying robots in environments where they can operate effectively. Companies are now reconsidering robot designs to enhance their adaptability, with many opting for the Marvin humanoid arm from Tianji to improve flexibility. This arm allows robots to adjust their physical configurations, enabling them to perform tasks in diverse settings. Looking ahead, the industry must continue to explore how robots can integrate into existing human environments. The ability of robots to navigate and operate in spaces designed for humans is crucial for their long-term functionality. No further timeline was disclosed at the time of publication.
Robotics Adaptive Technology Industrial Automation AI Mobility Solutions
U.S. Army to Evaluate BLADE's Hunter WOLF Robotic Vehicle with 82nd Airborne Division
The U.S. Army is set to conduct field evaluations of BLADE's Hunter WOLF robotic vehicle with the 82nd Airborne Division on August 20 at Fort Polk, Louisiana. This unmanned ground vehicle is designed to assist in support tasks during military operations, boasting a payload capacity of 2,800 pounds to facilitate the movement of equipment and supplies. The significance of this evaluation lies in its potential to enhance operational efficiency for soldiers by reducing their physical burden during demanding missions. Hunter WOLF's capabilities, including casualty evacuation and mobile power support, allow troops to focus more on combat tasks rather than logistics, addressing the needs of light infantry units. Looking ahead, the evaluation will provide 82nd Airborne soldiers with hands-on experience, assessing the vehicle's adaptability in various mission scenarios. BLADE plans to configure Hunter WOLF for roles such as tactical communications and equipment transport, with the aim of validating its flexibility and effectiveness in real-world operations. No further timeline was disclosed at the time of publication.
AI and Robotics Military
Apellix B2 Leads Commercial Cleaning Drone Market with Superior Specs in 2026
As of August 6, 2026, the Apellix B2 stands out among purpose-built commercial cleaning drones, boasting a working height of 195 feet and a maximum flight time of 32 minutes. The growing trend of using drones for exterior cleaning is reshaping the industry, as it reduces the need for traditional scaffolding and keeps crews safely on the ground. The significance of this shift is underscored by recent contracts, such as a Jacksonville building bid that specifically sought drone cleaning services, resulting in an Apellix operator winning the contract. This competitive landscape has prompted traditional window-washing companies to adopt drone technology to remain viable in the market. Looking ahead, the Apellix Power Wash Drone continues to dominate the commercial cleaning sector, with deployments in 21 countries. Buyers are encouraged to evaluate specific configurations and performance metrics before making a purchase, as the market for cleaning drones is rapidly evolving and diversifying.
Applications Drone News Drone News Feeds Sponsored Content
Dai Weijin Discusses Collaborative Efficiency as Key to Robot Chip Development
Dai Weijin, Chief Strategy Officer of Chipone Technology, highlighted the critical issue of collaborative efficiency in robot chip development. While the industry focuses on TOPS performance metrics, he emphasized that the real challenge lies in ensuring system efficiency aligns with computational power. He pointed out that while automotive chips may have excess computational capacity, robots require low-latency perception capabilities that are currently insufficient. Dai noted that reusing automotive chips was a necessary early choice for the industry, but the fundamental logic differs between automotive and robotics. Robots demand precise interactions in complex environments, which cannot be achieved by simply repurposing automotive technology. He explained that robot chips typically utilize a layered computing architecture, where the 'brain' handles decision-making and planning, while the 'small brain' manages perception and real-time control. Looking ahead, Dai believes that industrial applications, particularly in logistics and material handling, will lead the way in adopting these technologies. Chipone's strategy focuses on scalable architecture and providing clients with the most suitable configurations to quickly develop their products, emphasizing that collaborative efficiency is the true competitive advantage in the market.
Robot Chips Collaborative Efficiency Layered Computing Industrial Automation
PI's X-365 Gantry System Delivers Configurable Motion for Precision Applications
PI has introduced the X-365 gantry system, which features extensive travel ranges and high precision, making it ideal for semiconductor handling and advanced manufacturing applications. The significance of the X-365 lies in its ability to provide configurable and affordable motion solutions, catering to the needs of high-throughput and high-accuracy tasks in various industrial sectors. Looking ahead, industry professionals should monitor the adoption of the X-365 system in semiconductor and advanced manufacturing processes, as it may set new standards for efficiency and precision in these fields. No further timeline was disclosed at the time of publication.
PI Launches Modular Precision Linear Stage Family for High-Precision Positioning Systems
PI (Physik Instrumente) has unveiled its Modular Precision Linear (MPL) stage family, which offers a configurable platform for high-precision linear positioning systems. This new product aims to streamline the specification and integration process for users in various applications. The introduction of the MPL stage family is significant as it provides thousands of possible configurations, allowing for tailored solutions to meet specific precision motion control needs. This flexibility is crucial for industries requiring high accuracy and reliability in their positioning systems. Looking ahead, industry professionals should monitor the adoption of the MPL stage family in various sectors, as its modular design could influence future developments in precision motion control technology. No further timeline was disclosed at the time of publication.
Your Three-Shift Robot Is on a One-Shift Maintenance Plan: Phase 3 and the PM System
A three-shift robot on a one-shift maintenance plan ages at triple speed. RSF Phase 3: three PM tiers, three trigger models, environmental corrections.
Planning Algorithms Steven M. LaValle — RSF Specialist Shelf · Book S4 of 6
The reference that treats planning as a subject in its own right: configuration space, sampling-based methods, RRT. Free online, dual difficulty 4/5-2/5.
Handbook of Marine Craft Hydrodynamics and Motion Control Thor I. Fossen — RSF Specialist Shelf · Book S1 of 6
Added mass, wave loading, DVL navigation: the marine GNC reference for USV, ROV and AUV service engineers. The hardest book on the RSF list, 5/5.
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.
Modern Robotics K. M. Lynch & F. C. Park — RSF Top 10 Robot Education Textbooks · No. 8
The book the field agreed to make free: full preprint PDF, video lectures and open code from the authors. Screw theory and kinematics, taught rigorously.
Springer Handbook of Robotics B. Siciliano & O. Khatib (eds.) — RSF Top 10 Robot Education Textbooks · No. 10
Eighty-plus chapters, 2,300 pages, nobody reads it cover to cover. It ranks for one reason: when a fault crosses domains, this is the reference of record.
Autonomous Mobile Robots Siegwart, Nourbakhsh & Scaramuzza — RSF Top 10 Robot Education Textbooks · No. 3
AMR and AGV fleets are the biggest robot service market. Siegwart decodes the vendor manual: odometry, localization, cost maps.
Robot Initial Parameter Record: Why Day One Data Matters
The Initial Parameter Record captures your robot's baseline on installation day — data that can never be recreated. Inside RSF Phase 1: RACI, IPR, load inertia.
Inside RSF Domain 1: The Five-Phase Robot Service Lifecycle
RSF Whitepaper v1.0 defines the first five-phase service lifecycle for industrial robots. How Domain 1 relates to ISO 55001, ANSI/A3, Japan's law & GB standards.
The Most Important AI at WAIC Wasn't a Robot
At WAIC 2026, AI-native platforms quietly replaced interpreter hardware — what invisible AI infrastructure means for robotics and embodied AI.
