UC Berkeley and NVIDIA Introduce Agentic Robotics to Tackle Data Challenges in Robotics
- Published
- Source
- IEEESpectrumRobotics
UC Berkeley and NVIDIA have announced a new approach called agentic robotics, aimed at addressing the data scaling problem in robotics. This method seeks to program robots for practical tasks without relying heavily on vast amounts of training data, which has proven to be a challenge in achieving reliability in industrial applications.
The significance of agentic robotics lies in its potential to shift the paradigm from data dependency to coding solutions, leveraging advances in AI coding tools. This approach could enhance the flexibility and reliability of robots, which are essential for commercial deployments. The traditional reliance on imitation learning has shown limitations, particularly in industrial settings where performance consistency is critical.
Ken Goldberg, a professor at UC Berkeley, emphasizes the need for a reliable solution as the industry faces challenges with data-driven methods. No specific timeline for widespread adoption of agentic robotics was disclosed at the time of publication, but its development marks a pivotal moment in the evolution of robotics programming.
Original report
Can Agentic Robotics Solve Robotics’ Data Scaling Problem?
IEEESpectrumRobotics · Evan AckermanThis 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
RobotToday Weekly November 2 – 6, 2026 RobotToday · 2 days ago
- 11
- 12
Related Suppliers
Hybrid Robotics Lab, UC Berkeley
United States
UC Berkeley lab led by Prof. Koushil Sreenath researching nonlinear control of legged and aerial robots; creator of the open-source Berkeley Humanoid Lite.
UC Berkeley Robotics and Intelligent Machines / BAIR Lab
United States
UC Berkeley's AI and robotics research lab with 50+ faculty; known for robot learning, manipulation, and reinforcement learning research by Abbeel.
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.
Ambi Robotics
United States
Ambi Robotics is a US AI robotics company providing autonomous parcel sorting and palletizing systems for e-commerce and logistics operations.
Deccan AI
United States
Enterprise data company providing expert-curated SFT, RLHF datasets, RL environments and evaluations for training LLMs and AI agents.
Synphony Robotics
United States
Y Combinator-backed San Francisco startup founded in 2025 building strawberry-picking robots and bed-level analytics software for California farms.
Intelligence Factory
United States
New York startup founded 2026 (YC P26) training robot manipulation foundation models on human demonstration data recorded with custom sensing gloves.
Robotriks Ltd
United Kingdom
Cornwall robotics R&D firm founded in 2018 that builds the RTU, a low-cost tracked electric autonomous farm platform with adjustable scaffold-pipe frame.
amiSter sp. z o.o. sp.k.
Poland
Polish system integrator programming ABB, FANUC, KUKA, and Yaskawa robots and Siemens PLCs for automotive OEMs.
Asamaka Industries Ltd
Canada
Windsor, ON engineering firm; electrical design, PLC controls, robot programming, AI/ML integration, and XR digital twins for manufacturers.
Beijing Surgerii Robotics 北京术锐机器人股份有限公司
China
Chinese medical robotics company developing the SHURUI single-port surgical robot with flexible snake-like instruments for minimally invasive surgery.
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.
