Abstract: A control method for a mobile object automatically moving includes: causing the mobile object to move along a first path; causing a sensor of the mobile object to detect a position and an attitude of a target object while the mobile object is moving along the first path; setting a second path up to a target position at which predetermined position and attitude with respect to the target object are achieved based on the position and the attitude of the target object; switching the first path to the second path to move the mobile object along the second path; executing optimization calculation based on an evaluation function, to set a third path; and switching the second path to the third path to move the mobile object along the third path.

Abstract: A control device determines an operation scheme of an apparatus on a rule base on the basis of state information indicating the state of the apparatus or the state of an environment in which the apparatus operates, calculates a parameter for determining the content of an operation in the determined operation scheme on the basis of the state information and a learning model constructed on the basis of the operation of the apparatus based on the state information and evaluation of the operation, and commands the apparatus to execute the operation.

Abstract: A signal processing device includes: a data receiver configured to transmit a transmission wave a position of which changes in a first direction and which spreads in a second direction orthogonal to the first direction, and generate a matrix of acquired observation data in the first and second directions, as a reception signal matrix, with a value of a position in the reception signal depending on a signal strength; a range processor configured to specify a range in the second direction in an imaging matrix, and set a sparse vector including a component in the first direction of the specified range; a reconstruction processor configured to perform reconstruction processing using the reception signal matrix and the sparse vector to calculate a component of the sparse vector; and a synthesis processor configured to synthesize the resulting sparse vector while moving the range, to generate an imaging matrix.

Abstract: A movement control method for a multi-vehicle system for moving multiple vehicles to target positions individually set for the vehicles includes: acquiring first positions of the vehicles; determining control input for moving the vehicles from the first positions to second positions away from the target positions by a first distance or more while the vehicles satisfy a predetermined condition; and updating the first distance to be a shorter distance when a distance between the second position and the target position of each of the vehicles becomes equal to or more than the first distance and within an updating distance.

Abstract: A method of controlling movement of multi-vehicle includes acquiring a constraint condition under which vehicles move and a calculation cycle for calculating movement routes of the vehicles; acquiring a position of each vehicle; specifying a target position for each vehicle; calculating, based on the position of each vehicle, the target position, and the constraint condition, a movement route for prediction steps of each vehicle; determining, based on the movement routes of the vehicles, a driving condition of each vehicle from a current time to a unit time; and controlling movement of each vehicle. Calculating the movement route including performing optimization calculation based on an evaluation function, evaluation of which becomes higher as a deviation between the vehicle and the target position for each prediction step becomes smaller, and the constraint condition, to calculate the movement route.

Abstract: A control method for a mobile object automatically moving includes: causing the mobile object to move along a first path; causing a sensor of the mobile object to detect a position and an attitude of a target object while the mobile object is moving along the first path; setting a second path up to a target position at which predetermined position and attitude with respect to the target object are achieved based on the position and the attitude of the target object; switching the first path to the second path to move the mobile object along the second path; executing optimization calculation based on an evaluation function, to set a third path; and switching the second path to the third path to move the mobile object along the third path.

Abstract: A signal processing device includes: a data receiver configured to transmit a transmission wave a position of which changes in a first direction and which spreads in a second direction orthogonal to the first direction, and generate a matrix of acquired observation data in the first and second directions, as a reception signal matrix, with a value of a position in the reception signal depending on a signal strength; a range processor configured to specify a range in the second direction in an imaging matrix, and set a sparse vector including a component in the first direction of the specified range; a reconstruction processor configured to perform reconstruction processing using the reception signal matrix and the sparse vector to calculate a component of the sparse vector; and a synthesis processor configured to synthesize the resulting sparse vector while moving the range, to generate an imaging matrix.

Abstract: A path generation method includes: acquiring information about a position of a vehicle; acquiring information about a target position of the vehicle; acquiring information about a position of an obstacle; setting a constraint condition that the vehicle at each of predicted steps does not interfere with the obstacle, based on the position of the vehicle, a size of the vehicle and the position of the obstacle; and calculating a moving path of the vehicle by optimization calculation based on the constraint condition and an evaluation function in which a score becomes higher as a deviation between the position of the vehicle at each of the predicted steps and the target position becomes smaller.

Abstract: A forklift apparatus includes: an error prediction unit configured to predict a first positional error which is a positional error after picking-up between a standard position of a fork and a central position of a pallet on the fork after the pallet is picked up and a first angle error which is an angle error after picking-up with respect to the fork in the pallet; a travel route correction unit configured to correct a travel route from a picking-up position of the pallet to a stacking position of the pallet to offset the first positional error and the first angle error when the pallet is stacked; and a conveyance travel control unit configured to perform travel control such that the pallet is conveyed along the corrected travel route.

Abstract: [Problem] Provided is a vehicle control system that can, without needing to specify a self-position based on external reference data, cause a vehicle to arrive at an object with satisfying required conditions for the position and orientation of a vehicle when the vehicle arrives at the object corresponding to the position and orientation of the object. [Solution] The vehicle control system includes a detection device that detects a positional relationship between two reference points of the vehicle and two feature points of the object and a control device that determines a movement route of the vehicle on the basis of only information indicative of the positional relationship between the two reference points and the two feature points detected by the detection device.

Abstract: A movement control method for multi-vehicle for moving multiple vehicles to target positions individually set for the vehicles includes the steps of: acquiring positions of the vehicles; determining control input for moving the vehicles from the acquired positions to positions away from the target positions by a first distance or more while the vehicles satisfy a predetermined condition; and updating the first distance to a shorter distance when a distance between the position and the target position of each of the vehicles becomes equal to or more than the first distance and within an updating distance.

Abstract: A method of controlling movement of multi-vehicle includes acquiring a constraint condition under which vehicles move and a calculation cycle for calculating movement routes of the vehicles; acquiring a position of each vehicle; specifying a target position for each vehicle; calculating, based on the position of each vehicle, the target position, and the constraint condition, a movement route for prediction steps of each vehicle; determining, based on the movement routes of the vehicles, a driving condition of each vehicle from a current time to a unit time; and controlling movement of each vehicle. Calculating the movement route including performing optimization calculation based on an evaluation function, evaluation of which becomes higher as a deviation between the vehicle and the target position for each prediction step becomes smaller, and the constraint condition, to calculate the movement route.

Abstract: A decision-making device (2) comprising: an action selection unit (200) for selecting one of a plurality of actions that can be taken in a first state so that an environment performs the selected action; a state acquisition unit (201) for acquiring a second state indicating the state that follows the execution of the action; a reward acquisition unit (202) for acquiring a reward serving as an indicator for indicating whether or not the second state is desirable; and a storage processing unit (203) whereby experience data in which the first state, the action, the second state, and the reward are associated is stored in a storage unit (21) associated with the action, the storage unit (21) being one of a plurality of storage units.

Abstract: An automated driving control device includes a registration unit configured to generate automated driving information used for driving a vehicle automatically based on a first image obtained by capturing an environment around the vehicle in a mode of driver driving; and a control unit configured to automatically drive the vehicle based on the automated driving information and a second image obtained by capturing the environment around the vehicle in a mode of automated driving. The registration unit includes an extraction unit configured to extract candidate feature points existing in the environment around the vehicle based on the first image; and a generation unit configured to select the candidate feature points that are determined to be structures fixed around a target position of the vehicle based on the first images captured while the vehicle moves, as feature points.

Abstract: A control device determines an operation scheme of an apparatus on a rule base on the basis of state information indicating the state of the apparatus or the state of an environment in which the apparatus operates, calculates a parameter for determining the content of an operation in the determined operation scheme on the basis of the state information and a learning model constructed on the basis of the operation of the apparatus based on the state information and evaluation of the operation, and commands the apparatus to execute the operation.

Abstract: A parking support system includes a parking path planning unit that plans a trajectory of each unit path when moving a vehicle to a target parking position by repeating a movement of the unit path including one forward movement and one backward movement in succession and calculates a vehicle control signal that causes the vehicle to move along the trajectory such that a steering angle of the vehicle is substantially 0 degrees at an arrival position of each of the forward movement and the backward movement.

Abstract: A forklift apparatus includes: an error prediction unit configured to predict a first positional error which is a positional error after picking-up between a standard position of a fork and a central position of a pallet on the fork after the pallet is picked up and a first angle error which is an angle error after picking-up with respect to the fork in the pallet; a travel route correction unit configured to correct a travel route from a picking-up position of the pallet to a stacking position of the pallet to offset the first positional error and the first angle error when the pallet is stacked; and a conveyance travel control unit configured to perform travel control such that the pallet is conveyed along the corrected travel route.

Abstract: A mobile robot 1 having a plurality of kinds of moving forms includes a body unit 11 having a front face and a back face, four limb units 12 having a plurality of limb-side drive shafts, and front end tools 13 provided on a front end side of the limb units 12. A base end side of the limb unit 12 is connected to the body unit 11. The four limb units 12 are the same units. The body unit 11 and the four limb units 12 are movable by switching a front face side and a back face side so that a moving operation of the front face side and a moving operation of the back face side are symmetrical across the center of a thickness direction of the body unit 11.

Abstract: An automated driving control device includes a registration unit configured to generate automated driving information used for driving a vehicle automatically based on a first image obtained by capturing an environment around the vehicle in a mode of driver driving; and a control unit configured to automatically drive the vehicle based on the automated driving information and a second image obtained by capturing the environment around the vehicle in a mode of automated driving. The registration unit includes an extraction unit configured to extract candidate feature points existing in the environment around the vehicle based on the first image; and a generation unit configured to select the candidate feature points that are determined to be structures fixed around a target position of the vehicle based on the first images captured while the vehicle moves, as feature points.

Abstract: A parking support system includes a parking path planning unit that plans a trajectory of each unit path when moving a vehicle to a target parking position by repeating a movement of the unit path including one forward movement and one backward movement in succession and calculates a vehicle control signal that causes the vehicle to move along the trajectory such that a steering angle of the vehicle is substantially 0 degrees at an arrival position of each of the forward movement and the backward movement.