Remote control system
A remote control system, in which an operator remotely operates a robot having an end effector that is capable of gripping and manipulating an object, includes an acquisition part acquiring information on a state of the operator operating the robot; an end effector capable of performing multiple types of gripping methods; a gripping method table in which the gripping methods are stored; and a gripping method selector selecting the gripping method from the gripping method table based on a joint flexion angle of the operator obtained from operator information of the acquisition part.
1 . A remote control system in which an operator remotely operates a robot having an end effector that is capable of gripping and manipulating a target object, the remote control system comprising:
an end effector capable of performing multiple types of gripping methods;
a controller, to operate the end effector, the controller comprising a sensor;
a data base, comprising a memory storing a gripping method table;
a processor configured to function as:
an acquisition part acquiring information on a state of the operator operating the robot;
a gripping method selector selecting the gripping method from the gripping method table based on a joint flexion angle of the operator obtained from operator information of the acquisition part;
a drive command generation part generating a drive command based on the selected gripping method;
an intention estimation part estimating an intention of the operator by comparing a distance between a fingertip of a thumb and a fingertip of another finger of the operator with a size of the target object, wherein the intention estimation part determines that the target object is not an intended object that the operator is trying to grasp when the distance between the fingers is narrower than the size of the target object, and the intention estimation part determines that the target object is the intended object that the operator is trying to grasp when the distance between the fingers is wider than the size of the target object;
wherein the end effector is driven according to the drive command,
wherein the gripping methods of the gripping method table are classified by a plurality of classes of taxonomy,
wherein learning data obtained by learning a feature amount of the joint flexion angle of the operator is stored for each of the gripping methods stored in the gripping method table,
wherein the processor is further configured to function as a gripping method determination part that performs a cross check by using the data base in which information related to gripping and the target object is stored,
in the cross check, a shape of a hand of the operator is estimated by using sensor values detected by the sensor included in the controller, and an estimated shape of the hand is compared with the gripping method table classified by the plurality of classes of taxonomy, so as to evaluate whether the selected gripping method is appropriate.
2 . A remote control system in which an operator remotely operates a robot having an end effector that is capable of gripping and manipulating an object, the remote control system comprising:
an end effector capable of performing multiple types of gripping methods;
an environment sensor, detecting a size of a target object;
a memory, storing a gripping method table;
a processor configured to function as:
an acquisition part acquiring information on a state of the operator operating the robot;
an intention estimation part estimating an intention of the operator by comparing a distance between a fingertip of a thumb and a fingertip of another finger of the operator with a size of the target object, wherein the intention estimation part determines that the target object is not an intended object that the operator is trying to grasp when the distance between the fingers is narrower than the size of the target object, and the intention estimation part determines that the target object is the intended object that the operator is trying to grasp when the distance between the fingers is wider than the size of the target object; and
a gripping method selector selecting the gripping method from the gripping method table based on the intention of the operator estimated;
a drive command generation part generating a drive command based on the selected gripping method;
wherein the end effector is driven according to the drive command.