Robot Control Device, Robot Control Method, and Robot Control Program

A robot control method of controlling a robot that operates an operation object to be operated to transition from a state in which the operation object is away from an object of interest located in an environment to a completion state in which the operation object is in contact with the object of interest in a specific manner, the robot control method causing a computer to execute processing comprising:

• setting an intermediate target state or the completion state as a target state of current movement, the intermediate target state being a target state in a middle of movement of the operation object until reaching the completion state;
• acquiring an observation result by a sensor regarding a position and a posture of the operation object and presence or absence of contact between the operation object and the object of interest;
• setting a set of particles representing uncertainty of the position and the posture of the operation object, each of the particles included in the set of particles representing one of possible positions and postures of the operation object;
• increasing a weight of a particle for a particle representing a position and a posture closer to a position and a posture of the operation object indicated by the observation result among the particles, and increasing a weight of a corresponding particle for a particle closer to a state in which the object of interest and the operation object arranged in a position and a posture represented by each of the particles are in contact with each other in a virtual space where shapes and a relative positional relationship of the object of interest and the operation object are expressed in a case in which the observation result indicates that the contact has occurred;
• calculating an estimated state that is a position and a posture of the operation object estimated based on the set of particles in which a weight of each of the particles is adjusted;
• planning an action for moving the operation object from the estimated state to the target state of the current movement;
• commanding the robot to execute the planned action;
• and
• repeating setting of the target state, acquisition of the observation result, setting of the set of particles, adjustment of the set of particles, calculation of the estimated state, planning of the action, and execution of the action until the estimated state coincides with the completion state within a predetermined error.

A non-transitory storage medium storing a robot control program for controlling a robot that operates an operation object to be operated, to transition from a state in which the operation object is away from an object of interest located in an environment to a completion state in which the operation object is in contact with the object of interest in a specific manner, the robot control program being executable by a computer to perform processing comprising:

• setting an intermediate target state or the completion state as a target state of current movement, the intermediate target state being a target state in a middle of movement of the operation object until reaching the completion state;
• acquiring an observation result by a sensor regarding a position and a posture of the operation object and presence or absence of contact between the operation object and the object of interest;
• setting a set of particles representing uncertainty of the position and the posture of the operation object, each of the particles included in the set of particles representing one of possible positions and postures of the operation object;
• increasing a weight of a particle for a particle representing a position and a posture closer to a position and a posture of the operation object indicated by the observation result among the particles, and increasing a weight of a corresponding particle for a particle closer to a state in which the object of interest and the operation object arranged in a position and a posture represented by each of the particles are in contact with each other in a virtual space where shapes and a relative positional relationship of the object of interest and the operation object are expressed in a case in which the observation result indicates that the contact has occurred;
• calculating an estimated state that is a position and a posture of the operation object estimated based on the set of particles in which a weight of each of the particles is adjusted;
• planning an action for moving the operation object from the estimated state to the target state of the current movement;
• commanding the robot to execute the planned action;
• and
• repeating setting of the target state, acquisition of the observation result, setting of the set of particles, adjustment of the set of particles, calculation of the estimated state, planning of the action, and execution of the action until the estimated state coincides with the completion state within a predetermined error.