Fudan Researchers Develop RoboSkill for Reusable Text-and-Code Skills in Robots
- Published
- Source
- PanDaily.com
Researchers at Fudan University have developed RoboSkill, a system that enables robot agents to convert learned methods into reusable text-and-code skills. This innovation incorporates touch sensing technology, significantly reducing task completion time both in simulations and on actual robots.
The introduction of RoboSkill is significant as it enhances the efficiency of robotic operations by allowing robots to retain and reuse learned skills. This advancement could lead to improved productivity in various applications, making robots more adaptable and effective in their tasks.
Fudan's RoboSkill aims to optimize robotic learning processes, with no further timeline disclosed at the time of publication regarding its commercial deployment or additional features.
Original report
Fudan's RoboSkill Lets Robot Agents Save What They Learn as Reusable Text-and-Code Skills
PanDaily.com · [email protected] (Pandaily)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
Botfellows GmbH
Germany
Chemnitz-based Fraunhofer IWU spin-off selling Dynamic Safety fenceless robot-cell monitoring, Safety Twin planning and RobCraft no-code teaching software.
FANUC Corporation
Japan
Japanese factory-automation group behind FANUC CNCs, industrial and CRX collaborative robots; its one-millionth robot shipped in August 2023.
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.
Robot Hosting
United States
Menlo Park AI software company developing cognitive software for mechanical robots and simulated web-based androids, deployed in education and retail.
RoboMatter
United States
Pittsburgh-based company producing ROBOTC programming tools and Robot Virtual Worlds 3D simulation for VEX and LEGO educational robots.
Deccan AI
United States
Enterprise data company providing expert-curated SFT, RLHF datasets, RL environments and evaluations for training LLMs and AI agents.
ACCESS
Japan
ACCESS Co., Ltd. is a Tokyo-listed (TSE:4813) Japanese software firm known for the NetFront browser, now testing VLA-model remote robot control over IOWN APN.
Portable Intelligence Inc.
Canada
Markham-based developer of RF Plus and TED warehouse management software giving manufacturers barcode-driven, real-time inventory and task tracking.
Extend Robotics
United Kingdom
Reading, UK firm founded 2019 whose AMAS VR teleoperation platform drives robots and collects training data; raised GBP 2.6m pre-Series A in 2026.
LabyrinthAI
United States
Boston startup building AI foundation models and data collection tools for robot training, serving e-commerce and manufacturing clients.
Haptica Inc.
United States
San Francisco start-up founded by Stanford alumni building tactile sensing hardware and tactile data for robot learning; piloting with select partners.
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.
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.
