Information processing apparatus and storage medium

A method for controlling a robot arm, the method comprising:

• acquiring state information indicating a state of at least one of the robot arm and an environment obtained from at least one sensor and acquiring a plan sequence that is a time series of control plans with respect to the robot arm;
• generating, by inputting the state information and the plan sequence into a first learned model, a state sequence that is a time series of pieces of state information each indicating a predicted future state;
• calculating, using the state sequence, a success probability of the plan sequence, the calculating including computing an average vector of state vectors included in the state sequence and inputting the average vector into a second learned model to output the success probability;
• and
• based on the success probability and the plan sequence, generating control information including input values to robot joints and outputting the control information via a communication section to cause the robot arm to execute at least a portion of the plan sequence.

A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause a computer to perform a method comprising:

• acquiring state information indicating a state of at least one of a robot arm and an environment obtained from at least one sensor and acquiring a plan sequence that is a time series of control plans with respect to the robot arm;
• generating, by inputting the state information and the plan sequence into a first learned model, a state sequence that is a time series of pieces of state information each indicating a predicted future state;
• calculating, using the state sequence, a success probability of the plan sequence, the calculating including computing an average vector of state vectors included in the state sequence and inputting the average vector into a second learned model to output the success probability;
• and
• based on the success probability and the plan sequence, generating control information including input values to robot joints and outputting the control information via a communication section to cause the robot arm to execute at least a portion of the plan sequence.