Gemini Robotics 2.5 Enhances Apollo 2's Performance on Mercedes-Benz Production Lines
- Published
- Source
- HumanoidsDaily
Google DeepMind has launched Gemini Robotics 2.5, an upgrade to its vision-language-action model, tested on over 200 tasks with improved dexterity and reliability. The model's rapid development was facilitated by Gemini 4 Argon, which allowed extensive virtual training and error correction. Apollo 2 robots, equipped with Sharpa's advanced hands, successfully performed automotive kitting tasks at Mercedes-Benz plants in Hungary and Germany, achieving a 96% success rate.
The significance of this advancement lies in the integration of advanced robotics into real-world industrial applications, demonstrating the potential for humanoid robots to work alongside humans in manufacturing settings. The collaboration between DeepMind and Apptronik highlights the effectiveness of combining cutting-edge AI models with practical robotics, paving the way for enhanced productivity in automotive production.
DeepMind's Gemini Robotics 2.5 is expected to continue evolving, with future developments likely to focus on expanding its capabilities and applications in various industrial environments. No further timeline was disclosed at the time of publication.
Original report
Gemini Robotics 2.5 Puts Apollo 2 on Mercedes-Benz Lines as Argon Speeds Up Training
HumanoidsDaily · [email protected] (Humanoids Daily Staff)This 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
Google DeepMind
United Kingdom
Alphabet's London-based AI lab, developer of the Gemini Robotics vision-language-action models and the open-source MuJoCo physics simulator.
Apptronik
United States
Austin, Texas humanoid robotics company; builds the Apollo robot and runs pilots with Mercedes-Benz, GXO Logistics, and Jabil.
TRON K.K.
Japan
Tokyo humanoid integrator (est. 2024) bringing physical-AI robots, simulation training and Prevu3D factory digital twins to Japanese manufacturers.
VLM Robotics
France
VLM Robotics, near Bordeaux, builds CNC-controlled robotic cells (GEMINI, SOLO, COMPAQT, CALYPSO) for WAAM, cold spray, milling and NDT of large parts.
Sharpa
Singapore
Singapore-headquartered AI robotics company developing dexterous robotic hands and humanoid robots for general-purpose manipulation tasks.
Embodied AI
Switzerland
Lausanne start-up building soft, compliant robots that learn factory tasks on site by imitation; first round led by Faber VC in September 2026.
Walden Robotics
United States
Walden Robotics launched from stealth in July 2026 with a $300M seed co-led by Toyota, deploying general-purpose factory robots at a Toyota plant.
Seed Robotics Team, ByteDance Seed 字节跳动Seed机器人团队
China
ByteDance Seed's robotics research team, developer of the GR-3 vision-language-action model and the ByteMini bimanual mobile robot.
Contactile
Australia
Australian developer of optical multimodal tactile sensors and smart grippers giving robots a human sense of touch for dexterous manipulation.
Tangent Robotics
United States
New York City spin-out of Columbia Engineering building tactile multi-finger robot hands and learned dexterity policies; raised a 4.5M pre-seed round in 2026.
Beijing Simulation World Engine Co., Ltd. (SimWE) 北京云道智能科技股份有限公司
China
Beijing CAE developer (est. 2014) of the Simdroid multiphysics platform and Sim-PI, a GPU physics-simulation platform for training embodied robot models.
Songying Technology 松应科技
China
Songying Technology (ORCA3D) is a Shanghai physics-AI simulation software maker for embodied-AI robot training, backed by early-stage VC investors.
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.
