Abstract: A control device for a vehicle controls a subject vehicle configured to switch between manual driving by a driver and automated driving. The control device includes a processor and a memory device. The processor is configured to execute learning control that learns vehicle-to-vehicle information being vehicle-to-vehicle time or vehicle-to-vehicle distance of the subject vehicle with respect to a preceding vehicle during traveling with the manual driving, and to reflect a learning result of the vehicle-to-vehicle information by the learning control in a control of the vehicle-to-vehicle information during the automated driving. The memory device is configured to store the vehicle-to-vehicle information as learning data during the manual driving. In the learning control, the processor determines, based on a type of the preceding vehicle, whether or not the vehicle-to-vehicle information for the preceding vehicle is caused to be stored in the memory device as the learning data.

Abstract: Systems and methods for managing a battery charge of a work machine are described herein. The battery charge is maintained using a source of power (or other source) while the work machine also uses the source of power to power the work machine and the systems associated with the work machine. In instances in which the source of power may be removed for use by the work machine, a modification request may be used to change the battery from primary mode of operation, where the battery charge is maintained at a lower level to maintain the life of the battery, to a secondary mode of operation where the battery is charged to a high charge. The higher charge can be used to accommodate work machine operations while the battery is removed from the source of power. The battery can thereafter be returned to the primary mode of operation.

Abstract: A method and an apparatus for using a multi-boundary region to provide an Internet of Things (IoT) service according to an entrance and an exit of a preset boundary region based on a location of a vehicle, and an apparatus therefor. A method of controlling a location-based service includes determining a current location of a vehicle, and controlling reception of a notification information service. The notification information services is generated by at least one IoT device corresponding to a preset point in a plurality of states based on an ignition state and a relationship of the current location with respect to a first geo-fence set based on a distance from the preset point and a second geo-fence set based on an expected arrival time from the point. The second geo-fence may be set inside the first geo-fence.

Abstract: A drift control apparatus and method of controlling the same, include a sensor, a processor and a driving device. The sensor may obtain driving state information of a vehicle. The processor is configured to determine a drift state of the vehicle according to the driving state information, generate a control signal corresponding to detecting the drift state, determine a vertical load deviation between an internal wheel and an external wheel of the vehicle in the drift state, and determine a control amount in proportion to the vertical load deviation. The driving device may control driving forces of wheels based on the control amount in response to the control signal.

Abstract: Embodiments of the present invention provide a control system (100). The control system (100) is for a host vehicle (10) operable in an autonomous mode and a non-autonomous mode. The control system (100) comprises one or more controllers (110). The control system (100) is configured to receive, when operating in a non-autonomous mode, a mode signal and environment data. The mode signal is indicative of the host vehicle (10) operating in a training mode. The environment data is indicative of a sensed environment of the host vehicle (10) during a first manoeuvre by the host vehicle (10) from a first location to a first navigation goal. In the training mode, the one or more controllers (110) identify a navigable area and output vehicle control data. The navigable area is in a vicinity of the first manoeuvre and is suitable to contain a plurality of possible navigation paths for subsequent navigation of the host vehicle (10), operating in an autonomous mode, to a second navigation goal within the navigable area.

Abstract: Techniques and architectures for controlling movement of a system along a desired path in an efficient manner are discussed herein. For example, an autonomous lawn mower can be configured to determine a target state for the autonomous lawn mower indicating a target position, orientation, linear velocity, rotational velocity, etc. The autonomous lawn mower can determine a difference between a current state of the autonomous lawn mower and the target state. Based on the difference, the autonomous lawn mower can determine an amount of force/torque and control the autonomous lawn mower to move based on the amount of force/torque, which can cause the autonomous lawn mower to realign with a target state.

Abstract: Methods for reversing determination for a vehicle asset are provided. The methods include capturing by a telematics device coupled to the vehicle acceleration data from a three-axis accelerometer, determining by an edge reversing-determination machine learning mode, a machine-learning-determined reversing indication for the vehicle asset. The edge reversing-determination machine-learning model being updated based on a centralized reversing-determination machine-learning model trained using a vehicle-provided reversing indication.

Abstract: Systems and methods for online augmentation for learned grasping are provided. In one embodiment, a method is provided that includes identifying an action from a discrete action space. The method includes identifying a second set of grasps of the agent utilizing a transition model based on the action and at least one contact parameter. The at least one contact parameter defines allowed states of contact for the agent. The method includes applying a reward function to evaluate each grasp of the second set of grasps based on a set of contact forces within a friction cone that minimizes a difference between an actual net wrench on the object and a predetermined net wrench. The reward function is optimized online using a lookahead tree. The method includes selecting a next grasp from the second set. The method includes causing the agent to execute the next grasp.

Abstract: A mobile robot includes: a chassis supporting a locomotive assembly; a sensor; a processor configured, in a guided travel mode, to: detect an external force applied to the chassis in a first direction; control the sensor to capture sensor data corresponding to a physical environment of the mobile robot; detect, based on the sensor data, an operational constraint in the physical environment; determine, based on the detected operational constraint, a feedback force in a second direction opposite the first direction; and controlling the locomotive assembly according to the feedback force.

Abstract: Disclosed is a high-definition (HD) map-based local path planning method and apparatus for dynamic and static object avoidance. An HD map-based local path planning method for dynamic and static object avoidance performed by a computer device includes verifying a position on a global path by parameterizing the global path using an arc length; generating a path candidate group based on the global path; and selecting an optimal path as a path having a smallest cost function related to a global path following from the path candidate group. The cost function includes a global-path-following cost for selecting a path candidate group having a smallest lateral offset from the global path.

Abstract: A control device for a robot includes: an external force acquisition section configured to acquire external force applied to a movable element during operation of the robot; a first condition determination section configured to determine whether or not a first condition that the external force exceeding a predetermined first threshold is applied to the movable element is satisfied; a second condition determination section configured to determine whether or not a second condition that the movable element is moving is satisfied; and an operation control section configured to stop the operation of the robot when both the first condition and the second condition are satisfied, while continuing the operation of the robot when at least one of the first condition and the second condition is not satisfied.

Abstract: A method of adjusting an action parameter includes a positional posture determination step of making a robot execute a task a plurality of times in a plurality of positional postures different in positional posture of an object when starting the task to obtain evaluation values of the respective tasks, comparing the evaluation values of the tasks out of the evaluation values of the respective tasks with a reference evaluation value, and determining an evaluation positional posture from the positional postures in the tasks in which the evaluation value is no higher than the reference evaluation value, an updating step of making the robot operate with a tentative action parameter using the evaluation positional posture as a starting positional posture in the task to measure a time taken for the task or a vibration of the robot, and updating the tentative action parameter based on a measurement result, and a determination step of repeatedly performing the updating step until the time taken for the task or the vi

Abstract: An adaptive speed control system and method for adapting control of an electric motor under a changing load condition. A load torque observer determines a load torque value when the motor is operating at a constant speed, and the load torque value is used to adapt a torque. An inertia observer determines an inertia load value when the motor is operating at a changing speed, and the inertia load value is used to adapt a controller gain. An active disturbance input decoupler provides disturbance rejection when the motor is operating at a constant speed. An adaptive control switch switches the load torque observer between driving the inertia observer and driving the active disturbance input decoupler. The system may be configured for a multi-axis system in which multiple motors are each associated with a different axis of motion, and multiple adaptive speed control systems are each associated with a different motor.

Abstract: An example operation includes one or more of determining, by a server, an event associated with a transport, receiving, by the server, atypical data related to the transport from a plurality of devices over various times prior to the event, analyzing, by the server, the atypical data, forming, by the server, a consensus based on the analyzed atypical data to determine a severity of the event, and determining, by the server, an action to take based on the severity.

Abstract: A dual mounted end-effector system mounted on a motive robot arm for preparing an object surface is described. The system includes a first tool configured to contact and prepare the object surface and a second tool configured to contact and prepare the object surface. The system also includes a force control. The force control is configured to align, in a first state, with the first tool in position to contact and prepare the object surface and, in a second state, with the second tool in a position to contact and prepare the object surface.

Abstract: A method of generating a control program, wherein the method includes: executing an application by the first robot manipulator, at the same time, determining trajectory data and/or wrench data, determining robot commands from a stored time series, the robot commands being principal elements of the control program for the robot manipulator without relation to design conditions of a first robot manipulator, and generating the control program for a second robot manipulator based on the stored robot commands and based on the design conditions of the second robot manipulator.

Abstract: Techniques for providing remote guidance to a vehicle operating in an environment, by an operator located in the environment, are described herein. The operator can include a safety observer configured to observe one or more vehicles operating in the environment and may identify a scenario that requires a modification to a vehicle operation (e.g., stop forward movement, change direction of travel, modify a maximum speed, etc.). The operator may access a graphical user interface (GUI) via an operator computing device, and may input a constraint to modify the vehicle operation. The vehicle computing system may receive a control signal including the constraint, and may modify a vehicle trajectory based on the constraint. The vehicle computing system may later determine that a condition associated with the constraint is satisfied, and may continue vehicular operation in absence of the constraint.

Abstract: Provided is an autonomous mobile body, an information processing method, and an information processing device that enable a user to experience discipline for the autonomous mobile body. The autonomous mobile body includes a recognition unit that recognizes an instruction given, an action planning unit that plans an action on the basis of the instruction recognized, and an operation control unit that controls execution of the action planned, in which the action planning unit changes a detail of a predetermined action as an action instruction that is an instruction for the predetermined action is repeated. The present technology can be applied to a robot, for example.

Abstract: The present invention relates to methods and systems that utilize the production vehicles to develop new perception features related to new sensor hardware as well as new algorithms for existing sensors by using federated learning. To achieve this, the production vehicle's own worldview is post-processed and used as a reference, towards which the output of the software (SW) or hardware (HW) under development is compared. Through this comparison, a cost function can be calculated and an update of the SW parameters can be locally updated according to this cost function.

Abstract: An autonomous travel system is provided with a location acquisition unit, an inertia measuring device, a travel control unit, an initialization control unit, and a condition setting unit. The location acquisition unit acquires a location of a work vehicle by using a satellite positioning system. The inertia measuring device detects an orientation of the work vehicle. The travel control unit causes the work vehicle to travel autonomously along a preset travel route. The initialization control unit carries out an initialization process for the inertia measuring device by obtaining the orientation of the work vehicle on the basis of a value acquired by the location acquisition unit during initialization travel in which the work vehicle travels straight in a predetermined direction.