Teleoperation

Assembly Line

ARMADA: Augmented Reality for Robot Manipulation and Robot-Free Data Acquisition

📅 Date:

✍️ Authors: Nataliya Nechyporenko, Ryan Hoque, Christopher Webb, Mouli Sivapurapu, Jian Zhang

🔖 Topics: Industrial Robot, Imitation Learning, Teleoperation

🏢 Organizations: University of Colorado, Apple


Teleoperation for robot imitation learning is bottlenecked by hardware availability. Can high-quality robot data be collected without a physical robot? We present a system for augmenting Apple Vision Pro with real-time virtual robot feedback. By providing users with an intuitive understanding of how their actions translate to robot motions, we enable the collection of natural barehanded human data that is compatible with the limitations of physical robot hardware. We conducted a user study with 15 participants demonstrating 3 different tasks each under 3 different feedback conditions and directly replayed the collected trajectories on physical robot hardware. Results suggest live robot feedback dramatically improves the quality of the collected data, suggesting a new avenue for scalable human data collection without access to robot hardware.

Read more at arXiv

TRUMPF Introduces Remote Operations Support for Automated Laser Cutting in the U.S.

📅 Date:

🔖 Topics: Teleoperation

🏢 Organizations: TRUMPF


TRUMPF has introduced Remote Operations Support, a new service for automated laser cutting machine customers in the United States. The service connects experts in Germany with U.S.-based customers operating TruLaser Center machinery. Designed for autonomous production, TRUMPF’s TruLaser Center is a full-service laser machine that automates the entire laser cutting process from loading of sheet metal to laser cutting and then part removal and sorting. The Remote Operations Support service was created to assist customers with this automated laser cutting technology.

The average processing time to remotely resolve a TruLaser Center machine standstill is estimated at less than fifteen minutes. In addition, the experts at TRUMPF have found that more than fifty percent of machine downtimes can be resolved remotely.

Read more at TRUMPF Newswroom