Safety shared control system based on performance of teleoperator

A safety shared control system based on performance of teleoperator, comprising a master teleoperation system, a slave robotic manipulator system and a communication module;

• the master teleoperation system comprises EEG signal measurement device of a teleoperator, hand controller operation input, and upper computer software, wherein the upper computer software comprises a graphical user interface (GUI), safety simulation for protecting the safety of a robot, and a performance of teleoprator (PoT) model;
• the slave robotic manipulator system comprises a robotic manipulator, a vision camera and lower computer software, wherein the lower computer software comprises a target recognition algorithm, an autonomous controller for generating an autonomous instruction of the robot, and a shared controller for dynamically allocating human-robot control weights;
• and
• the communication module is configured to implement communication between the master teleoperation system and the slave robotic manipulator system,
• wherein the EEG signal measurement device of the teleoperator in the master teleoperation system aims to obtain original EEG signals by acquiring EEG signals using an Emotiv EPOC 14-channel EEG headset;
• the hand controller operation input involves a process of performing operation input to obtain an operation instruction Uh of the teleoperator using a Geomagic Touch X hand controller;
• the graphical user interface comprises information feedback output, and a robot state, as well as interactive operations, selecting a manual/shared/autonomous mode, and ending a task;
• and
• the safety simulation is used for identifying a safety control coefficient Ks of the teleoperator before actual operation of the teleoperator, with specific steps as follows:
• (a) constructing a safety simulation environment, comprising a robotic manipulator having an end fixture, a target object, and a target position;
• (b) executing a grabbing task, wherein the teleoperator uses the hand controller to manipulate the robotic manipulator in the safety simulation environment to grasp the target object to the target position;
• (c) calculating the performance of teleopreator (PoT) in the safety simulation (PoTSIM), with a calculation formula as follows:
• PoT
• SIM
• =
• ∑
• W
• i
• ⁢
• P
• i
• ,
• in the formula, i=1, 2, 3, Pi represents an ith normalized operational performance indicator, and Wi represents a weighting coefficient corresponding to the ith operational performance indicator;
• and
• (d) outputting a safety control coefficient Ks=PoTSIM, Ks∈[0,1];
• the PoT model uses the EEG signals to indirectly acquire the performance of teleoperator (PoTBP) for a prolonged operation through a backpropagation (BP) neural network model, wherein the BP neural network comprises an input layer, a hidden layer and an output layer, an 14-channel EEG signal of the teleopreator is used as input, and the model outputs PoTBP;
• and during the model training, data of the grabbing task in the safety simulation are adopted.