Bear Robotics Achieves 8x Processing Speed Improvement for KR1 Humanoid Robot Using NVIDIA Technology
- Published
- Source
- InterestingEngineering.com
Bear Robotics has successfully reduced the processing time for its KR1 humanoid robot's model inference from 500 milliseconds to 60 milliseconds, achieving an eightfold improvement through NVIDIA software. This enhancement is facilitated by KINO-2, a new robot-learning platform that allows the KR1 to learn tasks from human demonstrations rather than requiring manual programming for each movement.
This significant reduction in processing time is crucial for improving the robot's responsiveness in identifying and handling objects, which is essential for its deployment in commercial operations. Bear Robotics has already deployed over 16,000 robots across more than 5,000 customer locations, primarily in service roles, indicating a strong market presence and the potential for further advancements in humanoid robotics.
Looking ahead, Bear Robotics is demonstrating the KR1's capabilities at NVIDIA GTC Berlin, showcasing its ability to perform complex warehouse workflows. However, no further timeline was disclosed at the time of publication regarding additional enhancements or deployment plans for the KR1 humanoid robot.
Original report
Humanoid robot cuts model processing delay 8x with NVIDIA tech in internal tests
InterestingEngineering.com · Neetika WalterThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Bear Robotics
United States
US company making autonomous service robots for restaurants and hospitality venues; majority-owned by LG Electronics since January 2025.
NVIDIA Robotics
United States
NVIDIA robotics division delivering Isaac simulation and training tools, Jetson edge compute modules, and Omniverse digital twin frameworks for physical AI.
Deci AI (Acquired by NVIDIA)
Israel
Israeli deep learning optimization startup acquired by NVIDIA in May 2024 for ~$300M; known for AutoNAC neural architecture search technology.
Kinisi Robotics
United States
US wheeled humanoid robot maker; KR1 stands 162 cm, reaches 14.4 km/h, handles 10 kg payloads for warehouse pick-and-place tasks.
Kassow Robots ApS
Denmark
Danish 7-axis collaborative robot maker for industrial manufacturing, majority-owned by Bosch Rexroth since 2022.
Shenzhen Moqi Intelligent Technology Co., Ltd. 深圳墨奇智能技术有限公司
China
Shenzhen embodied-intelligence startup building home-service robots, backed by a 2026 angel round led by Alibaba and Tencent.
Seoul Dynamics Inc.
Korea, Republic of (South)
Korean maker of heavy-duty physical-AI mobile robots: the RAPTOR LIFT 1.5-2 t riderless autonomous forklift and the 10-15 t TYRANNO platform for yards/sites.
Dexmate
United States
Santa Clara maker, founded 2024, of Vega, a foldable wheeled bimanual humanoid on Jetson Thor listed from USD 83,000, plus grippers and a teleop exoskeleton.
Ubicept
United States
Boston computer-vision startup founded 2021 by MIT and UW-Madison researchers; Photon Fusion software gives SPAD cameras up to 140 dB dynamic range.
QING
Netherlands
Arnhem, Netherlands food automation firm founded 2013; builds vision-AI inspection, robotic sorting and processing systems on its STAQ platform.
Chengdu Humanoid Robot Innovation Center Co., Ltd. 成都人形机器人创新中心有限公司
China
Chengdu-registered humanoid robot R&D company behind the Gongga-1 humanoid, the open-source RW-02OP wheeled-biped platform and Raydiculous-1 planning software
Hubei Humanoid Robot Innovation Center 湖北人形机器人创新中心
China
Wuhan public platform opened in June 2025 to train humanoid robots and collect embodied-AI data in 23 simulated scenes; led by a Hubei state tech investor.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
