Abstract: A control method is implemented in a vehicle comprising an internal-combustion engine providing a first torque and coupled to a gearbox by a coupling device comprising a hydraulic circuit and delivering a second torque from the first torque in a coupling position, and an electric motor installed between the coupling device and gearbox and producing, from the second torque, a third torque having a negative value opposite to that of the first torque to charge a battery. This method comprises a step (10-20) in which, in the event of a transition between neutral and parking positions during a charging phase, a nullification of the third torque produced is triggered to nullify the first torque before a sudden placement of the coupling device in a decoupling position.

Abstract: A vehicle including a transceiver, a memory and a processor is disclosed. The transceiver may be configured to receive a first trigger signal and a second trigger signal. The processor may be configured to determine pre-automation operational states associated with a plurality of vehicle components and optimal operational states associated with a set of vehicle components associated with an automation mode, responsive to obtaining the first trigger signal. The processor may further store an information associated with the pre-automation operational states in the memory, and cause the set of vehicle components to operate based on the optimal operational states. The processor may further restore operational states associated with the set of vehicle components back to their respective pre-automation operational states based on the information associated with the pre-automation operational states, responsive to obtaining the second trigger signal.

Abstract: An autonomous and adaptable AI-powered robotic workstation system is designed for diverse real-world applications. This includes a configurable workstation seamlessly integrating a dynamic robotic hand, endowed with real-time decision-making capabilities. The workstation features an automatic calibration and self-configuration mechanism utilizing six-axis motion for task execution, ensuring alignment and auto-positioning via cameras. A dynamic and no-code onboarding process with auto-calibration captures and stores product onboarding, optimization of object categorization and prioritizing captures using vision AI. The system also includes a vision-based operations module with AI-driven functionality, integrated hardware, scalable design, calibration capabilities, and unification of specified operations within the same workstation system.

Abstract: Disclosed herein is a method for performing a robot skill based on skill uncertainty using a large language model. The method includes generating a subtask list using a large language model by receiving a target task and environment information, mapping a subtask in the subtask list into a skill embedding space through an abstract skill policy network, and performing the subtask by decoding the mapped subtask through a manipulation skill policy network.

Abstract: A walking control method of an embodiment includes decomposing a mobile device with legs into a plurality of mass points, decomposing the plurality of decomposed mass points into a first interest mass point and mass points other than the first interest mass point, making a length between the first interest mass point and a contact point on a walking plane constant, making the mass points other than the first interest mass point constrained to an affine-transformed position of the first interest mass point, and generating a constraint trajectory of the mass points other than the first interest mass point in accordance with the constraint when the first interest mass point is moved.

Abstract: A motion plan device 10X mainly includes a condition setting means 90X and a motion plan means 100X. The condition setting means 90X sets a first condition in which a robot performing a pick-and-place for one or more transport objects and the one or more transport objects are located inside movable region being a region where no collision with a collision avoidance necessary target occurs, and a second condition in which, while the robot is grasping and carrying the transport object, the movable region around the collision avoidance necessary target of the robot and the movable region around the collision avoidance necessary target of the transport object being carried match with each other. Next, the motion plan means 100X calculates a motion plan of the robot based on the first condition and the second condition.

Abstract: A system and method for managing a series hybrid powertrain in an electric vehicle platform includes a battery, at least one traction electric motor, an internal combustion engine/motor generator combination and a vehicle supervisory controller. The battery is configured to supply power to the electric motor, and the electric motor is configured to drive the wheels of the electric vehicle. The internal combustion engine/motor generator is configured to generate electricity to recharge the battery pack and optionally provide additional power to the electric motor when necessary. The vehicle supervisory controller is configured to manage the operation of the series hybrid powertrain. The controller is programmed with a set of algorithms that determine the optimal use of the battery, electric motor, and internal combustion engine/motor generator based on various factors, including but not limited to the current state of the battery pack charge, driving conditions, and electric motor power requirements.

Abstract: Systems and methods of using a common control scheme to autonomously control a vehicle during semi-autonomous and fully autonomous driving modes are provided. In particular, embodiments of the presently disclosed technology incorporate reference tracking for driving input and vehicle state into this common control scheme. In some embodiments, this common control scheme may be implemented using Model Predictive Control (“MPC”).

Abstract: A substrate conveying robot includes a controller configured or programmed to acquire a conveyance gap based on an image captured by an imager, and control at least one of carrying a substrate out of a storage or carrying the substrate into the storage based on a size of an acquired conveyance gap.

Abstract: An autonomous system attaches corrugated metal decking to roof structural members such as purlins, trusses or joists using a motorized wheeled carriage that traverses deck corrugations and drives threaded fasteners with closed-loop control. A fastener management module holds structural and sidelap screws in separate hoppers, orients them via screw sorters, and distributes them by a linearly translatable gantry to multiple drill units. Each unit includes a PWM-controlled drill, a linear actuator for plunge, and a spring-biased jaw release cooperating with a magnetized nut driver. A sensor assembly within a corrugation detects structural members, guides lateral alignment, and senses pre-existing fasteners; metal deck edge range sensors and a fail-safe brake preventing the system from running off the roof deck. Controllers networked over CAN coordinate motion, torque, patterns, speed, plunge of the fastening system, verify seating by motor/force feedback, and generate audit records of as-installed locations.

Abstract: A method for providing customized information to a user, that includes receiving at a backend portion historical information, regarding multiple features, from a first user and one or more other users, categorizing the information and users as a function of a similarity of certain features of the historical information, receiving at the backend portion current information from the first user, determining a predicted future use as a function of at least some of the historical information and at least some of the current information, and providing a customized recommendation from the backend portion to the first user.

Abstract: An apparatus can include an actuator configured to move a wire along a longitudinal direction, a tractor that is connected to the wire and is configured to move the wire along the longitudinal direction, a driving unit, a first arm connected to the driving unit that drives the first arm to the longitudinal direction, a board connected to the first arm, a second arm connected to the wire, a plurality of sensors that can include at least a first sensor and a second sensor arranged at a different position from each other along a direction perpendicular to the longitudinal direction, at least one positional sensor configured to detect light from the board, a support member configured to support at least one positional sensor, and a breakaway mechanism that can include a breakaway connector configured to connect and disconnect the first arm and the second arm.

Abstract: A custom drift control method includes: determining whether to enter a drift mode based on a drift mode activation condition; when the drift mode activation condition is satisfied, entering the drift mode; based on the entering the drift mode, receiving input information including at least one of an accelerator reaction speed level, an attitude control assist level, and road surface information from a user; and based on the input information, performing custom drift control.

Abstract: A method including the receipt of a set of data associated with a surface condition of a vehicle, a determination of an extent of an instance of one or more imperfections upon a surface of the vehicle made by an artificial intelligence system, and an update to a pathway followed by one or more robots based on the determination of the extent of the instance of the one or more imperfections. The determination of the extent of the instance of the one or more imperfections causes the one or more robots to initiate a remediation action to a targeted portion of the surface of the vehicle to resolve the instance of the one or more imperfections.

Abstract: The present disclosure relates to methods, systems, a vehicle and a computer-readable storage medium and a computer program product. The method includes obtaining a baseline risk model generated based on one or more risk-associated parameters. The method further includes obtaining sensor data from a sensor system of a vehicle. The method further includes estimating one or more risk values associated with the one or more risk-associated parameters based on the obtained sensor data and generating, based on the one or more estimated risk values, an adopted risk model. Further, the method includes provisioning the generated adopted risk model for determining an acceptable risk model for forming a driving policy of an ADS.

Abstract: A gripper which has a friction estimation module configured to estimate static and/or dynamic friction forces acting on gripping jaws is provided. The static friction force is calculated on the basis of constraining reactions whereto the gripping jaws are subjected, the constraining reactions being calculated at least as a function of an actuation force exerted on the gripping jaws, a coefficient of friction of gripper materials and/or lubricant used being known. The dynamic friction force is calculated on the basis of speed of the gripping jaws, width of sliding surfaces and distance between the sliding surfaces of the gripping jaws, the viscosity of the lubricant used being known.

Abstract: The invention relates to a robot arm comprising a plurality of robot joints mechanically connecting a robot base to a robot tool flange wherein a robot controller is configured for controlling movement of said plurality of robot joints and thereby movement of said robot tool flange. The robot controller is connected to an interface device comprising an input device via which a user is able to communicate with said robot controller and thereby change mode of operation of the robot arm. The input device is a mechanical multifunctional input device and in response to a first predetermined sequence of activation applied to the input device, the robot controller is arranged to change mode of operation to a stop mode, and in response to a second predetermined sequence of activation applied to the input device, the robot controller is arranged to change mode of operation to a second mode of operation.

Abstract: Disclosed herein are systems, devices, and methods for real-time motion and path planning. The real-time motion and path planner may generate occupancy information about an environment around a robot. The occupancy information represents defined volumes of space of the environment, and each defined volume of space is associated with a corresponding occupancy probability. The motion/path planner also determines a sequence of robot configurations between a starting and a target configuration based on the occupancy information, wherein the sequence of robot configurations defines poses of the robot that occupy selected ones of the defined volumes of space. The motion/path planner also generates an instruction for the robot based on the sequence of robot configurations, wherein the instruction includes trajectory information to control the robot to move from the starting configuration to the target configuration through the sequence of robot configurations.

Abstract: A system and method for robotic teleoperation enable a teleoperated robotic element to perform a sequence of actions based on intention estimation, eliminating the need for continuous human control. The system includes a robotic teleoperation input that receives motion inputs and gaze data from a human operator performing a robotic teleoperation task. A robotic teleoperation feature extractor analyzes and processes the motion inputs and the gaze data into sequential input data. A multi-window model assigns hierarchical prediction windows to the input data, generating windowed sequential data. A hierarchical neural network processes the windowed sequential data to determine low-level action intentions and high-level task intentions, and generates an intention estimation based on the low-level action intentions and the high-level task intentions. A hierarchical dependency model incorporates hierarchical dependent loss to refine the intention estimation.

Abstract: An operation control device that controls an operation of a robot having a plurality of arms and end effectors connected to each of the arms includes an acquisition unit configured to acquire an operation instruction including a target position of the end effector from an operator, a relative relationship maintenance instruction unit configured to issue an instruction to keep a relative relationship between the end effectors constant, a control command generation unit configured to correct a target position of the end effector to maintain a relative relationship between the end effectors in response to the operation instruction acquired according to an instruction from the relative relationship maintenance instruction unit, and to calculate a joint angle target of the arm based on the corrected target position of the end effector.