18806621. SYSTEMS AND METHODS FOR ROBOTIC TELEOPERATION INTENTION ESTIMATION (HONDA MOTOR CO., LTD.)
SYSTEMS AND METHODS FOR ROBOTIC TELEOPERATION INTENTION ESTIMATION
Organization Name
Inventor(s)
Lijing Kuang of La Jolla CA US
Soshi Iba of Mountain View CA US
SYSTEMS AND METHODS FOR ROBOTIC TELEOPERATION INTENTION ESTIMATION
This abstract first appeared for US patent application 18806621 titled 'SYSTEMS AND METHODS FOR ROBOTIC TELEOPERATION INTENTION ESTIMATION
Original Abstract Submitted
Systems and methods for robotic teleoperation are provided. The system receives motion input and gaze data of a human operator performing a robotic teleoperation task, and a plurality of features are extracted from the received data. A recurrent neural network determines latent actions from the extracted features and generates temporally associated action inferences. A model determines inferred intention from a sequenced pair of action inferences, an intention hierarchy, and a probabilistic uncertainty function. A teleoperated robotic element performs a task associated with the inferred intention without a corresponding control signal from the human operator. The recurrent neural network is trained using extracted features and contrastive learning. The intention hierarchy is generated from action inferences. The probabilistic uncertainty function is generated using Bayesian hierarchical modeling. The system and method improves robotic teleoperation by estimating the intention of the human operator.
