Eka Robotics raises $150M to scale its vision-force-action model for robots
RoboticsMechanical Engineering
THE AI ANGLE
Learning dexterous manipulation through simulated reinforcement learningEka Robotics raised $150 million to scale a vision-force-action model for dexterous manipulation. The system trains robots in simulation with reinforcement learning instead of copying human demonstration data. This approach offers roboticists a method to achieve high-speed handling of unfamiliar objects.
THE TEACHING ANGLE
Students can debate whether simulated physical learning can replace human demonstration data for contact-rich assembly tasks.Read the original at therobotreport.com Generate teaching or study materials
More in Robotics
- Sterling Anderson doesn’t think humanoid robots should be building carsThe Verge · October 27, 2026
- ANYbotics begins delivering ANYmal X legged robot for explosive atmospheresThe Robot Report · October 27, 2026
- Artificial skin helps robots grasp pencil lead and pull away from needlesPhys.org — Technology · October 27, 2026
- AI-powered robotic laboratory paves the way for discovering next-generation heat-resistant coatingsPhys.org — Chemistry · October 27, 2026
- Xpanner launches autonomous pile driver for solar farm contructionThe Robot Report · October 27, 2026