Environment-aware Retargeting
A method for retargeting human motion trajectories to a robot that incorporates scene geometry into the optimization, generating joint targets and base targets simultaneously to ensure the retargeted whole-body motion is physically feasible in the environment and avoids collisions.
Timeline (last 90 days)
Environment-Aware Retargeting (EAR) combines the reconstructed scene geometry information with the head and gripper trajectories in the demonstration to determine the robot pose and generate collision-aware joint targets and base targets.
Environment-aware retargeting converts trajectories into executable action sequences through delay-calibrated action allocation.
Environment-aware retargeting incorporates scene geometry information into the optimization objective and generates joint targets and base targets simultaneously, ensuring that the retargeted whole-body motions are physically feasible in the environment.
All Facts (3)
Environment-Aware Retargeting (EAR) combines the reconstructed scene geometry information with the head and gripper trajectories in the demonstration to determine the robot pose and generate collision-aware joint targets and base targets.
50%UnverifiedEnvironment-aware retargeting converts trajectories into executable action sequences through delay-calibrated action allocation.
50%UnverifiedEnvironment-aware retargeting incorporates scene geometry information into the optimization objective and generates joint targets and base targets simultaneously, ensuring that the retargeted whole-body motions are physically feasible in the environment.
50%