Abstract: A motor controlling ECU 202 includes an automatic steering controller 42 that sets an automatic steering control amount, an assist controller 41 that sets an assist control amount, an integrated control amount calculating portion 43 that calculates an integrated control amount by adding the automatic steering control amount and the assist control amount, and an actual automatic steering angle calculating portion 46 that calculates, based on at least one of either of a steering torque and the assist control amount, an actual automatic steering angle that is a steering angle due to automatic steering control and included in an actual steering angle. The automatic steering controller 42 uses a target automatic steering angle and the actual automatic steering angle to set the automatic steering control amount.

Abstract: An oil condition estimation apparatus to be applied to a vehicle in which oil is agitated by a rotator includes a storage device and an execution device. The storage device stores mapping data for defining mapping. The mapping includes, as input variables, a speed variable indicating a rotation speed of the rotator, and a pressure variable indicating a pressure of the oil, and includes, as an output variable, an air bubble variable related to air bubbles contained in the oil. The execution device executes an acquisition process for acquiring values of the input variables, and a calculation process for calculating a value of the output variable by inputting, to the mapping, the values of the input variables acquired through the acquisition process.

Abstract: A computer architecture includes an application program interface (API). The API does not include a user interface. The computer architecture asynchronously receives into the API data relating to mission plan domains from clients. The data include an identification of vehicles, goals of the vehicles, and threats to the vehicles. The mission plan domains include an air domain, a sea or ocean domain, and a land domain. The computer architecture uses a parallel processing scheme to process the mission plan domains from the clients for determining goal priorities for each of the plurality of vehicles, processing the data using a genetic algorithm and physics models associated with the plurality of vehicles, and transmitting to the vehicles path commands based on the processing of the genetic algorithm.

Abstract: A processing path generating device including an intuitive path teaching device and a controller is provided. The intuitive path teaching device is provided for gripping and moving with respect to a workpiece to create a moving path. The intuitive path teaching device has a detecting portion for detecting a surface feature of the workpiece. The controller is connected to the intuitive path teaching device. The controller generates a processing path according to the moving path of the intuitive path teaching device and the surface feature of the workpiece.

Abstract: A method for controlling wheel slip of a vehicle includes: observing and estimating equivalent inertia information of a driving system in real time based on operation information of the driving system by receiving the operation information of the driving system for driving the vehicle; calculating the compensated amount for compensating a torque command of a driving device from the equivalent inertia information of the driving system observed and estimated by a controller; compensating the torque command of the driving device by using the calculated compensated amount; and performing a control of a torque applied to a driving wheel according to the compensated torque command.

Abstract: A computing device performs computation for controlling operations of a mobile manipulator configured to hold a plurality of target objects with a manipulator and move the target objects to predetermined positions. The computing device includes a storage and a calculator. The storage stores a trained machine learning model trained by inputting a plurality of training data sets, which are combinations of state variables and pieces of determination data associated with the state variables. The training data sets are acquired in advance. The calculator outputs a movement-target object to be moved to a predetermined position at current time by inputting the state variable to the trained machine learning model read from the storage. The state variable contains relative positions of the target objects to a specific portion of the mobile manipulator. The determination data associated with the state variable represents the movement-target object.

Abstract: A vehicle control device includes a memory configured to store a first target speed applied under a specific traveling situation and a second target speed that is equal to or less than the first target speed and applied to a traveling situation other than the specific traveling situation, and a processor configured to determine whether or not a traveling situation of the vehicle corresponds to the specific traveling situation, control a traveling speed of the vehicle in accordance with the first target speed when a traveling situation of the vehicle corresponds to the specific traveling situation, and control a traveling speed of the vehicle in accordance with the second target speed when a traveling situation of the vehicle differs from the specific traveling situation.

Abstract: There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.

Abstract: An embodiment of the present invention provides an artificial intelligence (AI) robot for determining a cleaning route using sensor data, comprising: a sensor unit including at least one of an image sensor, a depth sensor or a shock sensor; a cleaning unit including at least one of a suction unit or a mopping unit; a driving unit configured to drive the AI robot; and a processor configured to: acquire the sensor data from the sensor unit, determine a complex area using the acquired sensor data, create a virtual wall for blocking an entry into the determined complex area, determine the cleaning route in consideration of the created virtual wall, and control the cleaning unit and the driving unit based on the determined cleaning route.

Abstract: A vehicle, system and method for operating the vehicle is disclose. The system includes a radar system and a processor. The radar system locates a gap between targets in a second lane adjoining a first lane, with the host vehicle residing in the first lane. The processor is configured to determine a viability value of the gap for a lane change, select the gap based on the viability value, align the host vehicle with the selected gap, and merge the host vehicle from the first lane into the selected gap in the second lane.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for scheduling resource-constrained actions. In some implementations, data indicating a set of tasks to be performed by a group of multiple robots is received. A set of candidate plan elements is determined for each task in the set of tasks. A constraint profile for each of the candidate plan elements is generated, where each of the constraint profiles indicates a constraint to be satisfied in order to carry out the corresponding candidate plan element. Plan elements configured to perform each of the tasks in the set of tasks are selected based on the constraint profiles, and assembled into a schedule according to optimization criteria. This schedule can be used to perform tasks, and the schedule may account for variability in timing without failure.

Abstract: A control apparatus for a vehicle includes a skill level acquiring unit and an inter-vehicle distance controller. The skill level acquiring unit is configured to acquire a driving skill level of a driver of a first vehicle other than a second vehicle. The second vehicle is an own vehicle. The inter-vehicle distance controller is configured to control an inter-vehicle distance from the first vehicle to the second vehicle on the basis of the driving skill level acquired by the skill level acquiring unit.

Abstract: The present disclosure relates to a method for displaying lane information of an electronic device. The method for displaying lane information according to the present disclosure includes: acquiring an image photographed while a vehicle is driving; dividing the acquired image according to a distance from the vehicle; detecting lane display lines in the divided areas; curve-fitting the detected lane display lines to a continuous curve; and displaying the curve-fitted curve on a predetermined user interface. According to the present disclosure, it is possible to improve the route visibility to the driver by recognizing the far-distance lane by determining whether the vehicle is in the driving lane. In addition, it is possible to more accurately provide the route guidance information by using the real-time lane recognition results for the display of the route guidance.

Abstract: A method for calculating an arm angle range of a robot arm includes: determining a pose at an tail end position of the robot arm; judging whether an angle of an elbow joint is within a limit thereof when an arm angle is 180 degrees; if yes, constructing a first position matrix characterizing the elbow joint by using the pose and the arm angle; constructing a second position matrix of the elbow joint by using DH parameters of other joints of the robot arm; calculating, according to the first position matrix and the second position matrix, a first arm angle feasible region satisfying a limit of a position joint; judging whether the robot arm has a secondary position joint; and intersecting with the calculated first arm angle feasible region to obtain an arm angle range if no secondary position joint is present at the robot arm.

Abstract: Systems and methods are provided for creating more organic lane change models for autonomous or semi-autonomous operation of a vehicle. A plurality of data associated with a plurality of driver-performed lane change maneuvers is collected from a plurality of different vehicle. Driver-performed lane change maneuvers are discarded when determined to fall outside a threshold of safety. A generic model is generated from the non-discarded data for average lane change maneuvers. Specific models can be generated for different drivers, vehicle types, and other metrics by comparison with the generic model.

Abstract: A mobile robot is configured for operation in a commercial or industrial setting, such as an office building or retail store. The robot can patrol one or more routes within a building, and can detect violations of security policies by objects, building infrastructure and security systems, or individuals. In response to the detected violations, the robot can perform one or more security operations. The robot can include a removable fabric panel, enabling sensors within the robot body to capture signals that propagate through the fabric. In addition, the robot can scan RFID tags of objects within an area, for instance coupled to store inventory. Likewise, the robot can generate or update one or more semantic maps for use by the robot in navigating an area and for measuring compliance with security policies.

Abstract: Steering a vehicle in an electronic steering mode of operation that includes a front axle steering system, a rear axle steering system, one or more vehicle environment sensors, and a controller operatively coupled with the front axle steering system, the rear axle steering system, and the vehicle environment sensors. Commanding the vehicle to operate at a desired vehicle speed, detecting a lateral force acting on the vehicle in response to input from the vehicle environment sensors, and determining an actual lateral acceleration of the vehicle and a predicted lateral acceleration of the vehicle from the desired vehicle speed. Determining a lateral acceleration error by comparing the predicted lateral acceleration to the actual lateral acceleration, and determining if the lateral acceleration error exceeds a lateral acceleration limit, then turning both of the front axle steering system and the rear axle steering system to a crab steering correction angle.

Abstract: According to a non-limiting example embodiment, a remote control device includes a display configured to display a risk map; an input interface configured to input a travel route for an object to move along; a computing device, including at least one processor, the computing device configured to: receive obstacle information detected as the object moves along an actual travel route based on the travel route, and receive route information of the actual travel route of the object; and reset the travel route inputted by the input interface to a reset travel route in real time based on a mission given to the object or a risk level in each of a safe area and a dangerous area displayed on the risk map.

Abstract: A front blind spot detection and warning system for vehicle comprising: a monitoring element mounted to a front portion of a host vehicle for monitoring the condition of a current lane and a neighboring lane in front of the host vehicle, the monitoring element defining a detectable blind spot zone in a front area of the neighboring lane; and a controller connected with the monitoring element for receiving detected information from the monitoring element; wherein the controller is configured to obtain the running state of the host vehicle and the detected information of the monitoring element and to determine there is a blind spot risk.

Abstract: A method for generating guidance information is disclosed, which uses one or more machine learning algorithms to continually adapt and update a version of a model used to generate guidance instructions based on feedback data received from one or more users, such that the instructions generated by the model better fit the expectations or behaviour of the user or users. The method can be performed on a mobile navigation device, such that the model is adjusted to suit the needs of a single user. Alternatively, the method can be performed on a server based on feedback data from a plurality of users, and the updated model, once generated, transmitted to a plurality of mobile navigation devices to replace the existing model.