A computer-implemented method for controlling a vehicle includes receiving, via a processor, from two or more IX control devices disposed at a two or more stationary positions having known latitudes longitudes and orientations, first sensory data identifying the position and dimensions of a feature in a mapped region. The processor generates a plurality of IX nodes based on the first sensory data received from the IX control devices, and receives LiDAR point cloud that includes LiDAR and other vehicle sensory device data such as Inertial Measurement Unit (IMU) data received from a Vehicle (AV) driving in the mapped region. The LiDAR point cloud includes a simultaneous localization and mapping (SLAM) map having second dimension information and second position information associated with the feature in the mapped region. The processor generates, without GPS and/or real-time kinematics information, an optimized High-Definition (HD) map having Absolute accuracy using batch optimization and map smoothing.

Spin controller that can enable an autonomous vehicle (AV) to spin in place. A model predictive controller (MPC) can trigger the spin controller any time the MPC determines that a spin in place is required. In some configurations, the spin controller can move the AV to within 5 of the destination point. Spin controller can determine spin method based on the configuration of the AV, calculate an optimum turning path based at least on device mode and obstacles, and can enable the AV to spin in place.

Spin controller that can enable an autonomous vehicle (AV) to spin in place. A model predictive controller (MPC) can trigger the spin controller any time the MPC determines that a spin in place is required. In some configurations, the spin controller can move the AV to within 5 of the destination point. Spin controller can determine spin method based on the configuration of the AV, calculate an optimum turning path based at least on device mode and obstacles, and can enable the AV to spin in place.

A method for controlling a patrolling robot is provided. The method includes the steps of: acquiring, as first situation information on the patrolling robot, at least one of weight information on a support coupled to the patrolling robot and image information on the support and information on a location of the patrolling robot in a patrolling place; and determining a task and a travel route of the patrolling robot on the basis of the first situation information.

A conveyance system according to the present disclosure includes a conveyance vehicle configured to travel along a guide line laid on a traveling road. The conveyance vehicle includes: a guide line detection unit configured to detect the guide line; an object position detection unit configured to detect information on a position of an object around the conveyance vehicle; and a stop position determination unit configured to determine a stop position of the conveyance vehicle based on a result of detection by the object position detection unit.

A robot control system is a robot control system that controls a plurality of mobile robots, in which: each of the mobile robots includes right and left wheels, and a sensor that detects actions of the right and left wheels; and the control system calculates abrasion degrees of right and left components for the right and left wheels, depending on a detection result of the sensor, and manages traveling of the plurality of mobile robots, depending on the abrasion degrees.

A robot control system is a robot control system that controls a plurality of mobile robots, in which: each of the mobile robots includes right and left wheels, and a sensor that detects actions of the right and left wheels; and the control system calculates abrasion degrees of right and left components for the right and left wheels, depending on a detection result of the sensor, and manages traveling of the plurality of mobile robots, depending on the abrasion degrees.

Techniques to use a trained model to determine a yaw of an object are described. For example, a system may implement various techniques to generate multiple representations for an object in an environment. Each representation vary based on the technique and data used. An estimation component may estimate a representation from the multiple representations. The model may be implemented to output a yaw for the object using the multiple representations, the estimated representation, and/or additional information. The output yaw may be used to track an object, generate a trajectory, or otherwise control a vehicle.

Techniques to use a trained model to determine a yaw of an object are described. For example, a system may implement various techniques to generate multiple representations for an object in an environment. Each representation vary based on the technique and data used. An estimation component may estimate a representation from the multiple representations. The model may be implemented to output a yaw for the object using the multiple representations, the estimated representation, and/or additional information. The output yaw may be used to track an object, generate a trajectory, or otherwise control a vehicle.

A conveyance system according to the present disclosure includes a host vehicle position estimation unit that detects at least one of a traveled distance of a conveyance vehicle and a position of the host vehicle, and a control switching unit that switches, when the traveled distance or the position of the host vehicle detected by the host vehicle position estimation unit falls within a preset range while the conveyance vehicle is being controlled by an autonomous traveling control unit, a control mode from traveling control by the autonomous traveling control unit to traveling control by a guided traveling control unit.