The recent collaboration between ABB Robotics and PSYONIC demonstrates how human-generated data is helping advance robot learning. As part of this workflow, MANUS gloves were used to capture natural hand movements that contribute to human demonstration data for robot training. Haply,as another part of the workflow, supports the wrist tracking and force feedback.
For robotics teams developing imitation learning and teleoperation systems, collecting human demonstrations is becoming increasingly common. The fidelity of captured human motion can influence the usefulness of the resulting training data.
MANUS data gloves support this process, enabling researchers and engineers to capture natural hand movements and integrate them into teleoperation, motion retargeting, and robot learning workflows.
Human demonstrations have become an important source of data for imitation learning and related approaches. Whether demonstrations are collected directly on a robot or through teleoperation, the captured hand motion forms the basis of the resulting dataset.
Capturing natural finger movement preserves how people grasp and manipulate objects during real tasks. These demonstrations can then be reused to train, validate, and refine manipulation policies across projects.
As more organizations invest in humanoid robotics and Physical AI, collecting repeatable human demonstration data is becoming an increasingly common practice.
MANUS gloves enable robotics teams to capture natural hand movements for teleoperation, motion retargeting, and robot learning. Beyond controlling robotic hands in real time, the recorded demonstrations can be integrated into existing data collection workflows for future training and evaluation.
Researchers can capture expert demonstrations, retarget human hand motion to different robotic platforms, and build reusable datasets that support dexterous manipulation research, humanoid development, and embodied AI applications.
Because MANUS integrates with a wide range of robotic hands and software environments, teams can incorporate hand motion capture into existing workflows without changing their established development pipeline.
The collaboration between ABB Robotics and PSYONIC highlights the growing role of human-generated data in advancing robot learning. As robotics teams continue to develop more capable manipulation systems, collecting consistent, high-quality human demonstrations will remain an important part of training robots for real-world tasks.
MANUS supports this effort by providing hand motion capture technology that enables researchers and developers to transform natural human movements into reusable training data for teleoperation, motion retargeting, and robot learning.
