A vehicle steering device includes a reaction force device, a drive device, a first ECU configured to control the reaction force device, a second ECU configured to control the drive device, a first rudder angle sensor and a second rudder angle sensor each configured to detect a steering angle of a wheel and output the detected steering angle to the second ECU, and a communication line that transmits at least one of steering angles of the wheel as detected values of the first rudder angle sensor and the second rudder angle sensor from the second ECU to the first ECU.

A multidirectional wheel system, apparatus, and method to control one or more multidirectional wheels to provide multidirectional motion or movement for a movable apparatus, such as a skateboard, roller blades, a car, a motorcycle, a cleaning robot, to which the one or more multidirectional wheels are attached. The multidirectional wheel system includes a braking system to slow and/or stop the movement of the multidirectional wheel(s). At least one of the multidirectional wheels is an omnidirectional wheel, with a plurality of multidirectional wheels acting thereon to control movement thereof. The multidirectional wheel system includes a drone, wherein the omnidirectional wheel operates based on instructions from the drone.

Provided are an assistant system and assistant method for a backward driving of a vehicle, wherein the assistant system includes an input unit configured to receive a backward driving assistant command, a position tracking unit configured to track real-time positions of the vehicle, an obstacle sensing unit configured to generate an obstacle sensing signal, a steering device manipulation unit configured to adjust a steering angle of a steering device of the vehicle, a primary backward path generation unit configured to generate a primary backward path, a secondary backward path generation unit configured to generate a secondary backward path for the vehicle to drive backward, and a control unit configured to match the real-time positions of the vehicle to the secondary backward path, and at the time of a backward driving, to control the steering device manipulation unit.

A mobile robot triangle chassis assembly is disclosed, which includes a housing, a top plate, an isolation plat, a bottom plate, a power package, multiple support beams and three sets of gear trains. The three sets of gear trains are equilaterally triangularly distributed, each of which includes a motor, a speed reducer, a support frame and an omnidirectional wheel. The mobile robot triangle chassis assembly has a double-layer structure, the three sets of gear trains are located at a lower layer of the double-layer structure, and the power package is located at an upper layer of the double-layer structure, so as to reduce an occupied area of the mobile robot triangle chassis assembly. In the mobile robot triangle chassis assembly, only the bottom of the omnidirectional wheel is located outside the bottom plate, so that components within the mobile robot triangle chassis assembly are protected.

A mobile robot triangle chassis assembly is disclosed, which includes a housing, a top plate, an isolation plat, a bottom plate, a power package, multiple support beams and three sets of gear trains. The three sets of gear trains are equilaterally triangularly distributed, each of which includes a motor, a speed reducer, a support frame and an omnidirectional wheel. The mobile robot triangle chassis assembly has a double-layer structure, the three sets of gear trains are located at a lower layer of the double-layer structure, and the power package is located at an upper layer of the double-layer structure, so as to reduce an occupied area of the mobile robot triangle chassis assembly. In the mobile robot triangle chassis assembly, only the bottom of the omnidirectional wheel is located outside the bottom plate, so that components within the mobile robot triangle chassis assembly are protected.

The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance travelled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance travelled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

A control device includes a lane departure detection unit that detects lane departure of a vehicle, a rear vehicle determination unit that determines whether a rear vehicle is present on a rear side, a lane change start detection unit that detects start of a lane change, a lane change end detection unit that detects end of the lane change, a steering assistance control unit that applies an assistive steering torque to a steering wheel, and an assistive steering torque cancellation unit that, in a case where the start of the lane change is detected and no rear vehicle is present, cancels application of the assistive steering torque, and in a case where the end of the lane change is detected and a rear vehicle is present, cancel the application of the assistive steering torque.

System, methods, and other embodiments described herein relate to implementing and calibrating a learning model for inferring operator intent by estimating grip intensity. In one embodiment, a method includes estimating, using a learning model during a driving scenario, first grip intensity on a steering device for a vehicle according to initial image data depicting a hand of an operator gripping outside set areas that have pressure sensors. The method also includes calibrating the learning model for the operator and the steering device using grip measurements and additional image data acquired from gripping inside the set areas. The method also includes computing, using the learning model during the driving scenario, second grip intensity outside the set areas on the steering device according to hand images acquired about the operator. The method also includes adapting a vehicle parameter of the vehicle according to the second grip intensity.

System, methods, and other embodiments described herein relate to implementing and calibrating a learning model for inferring operator intent by estimating grip intensity. In one embodiment, a method includes estimating, using a learning model during a driving scenario, first grip intensity on a steering device for a vehicle according to initial image data depicting a hand of an operator gripping outside set areas that have pressure sensors. The method also includes calibrating the learning model for the operator and the steering device using grip measurements and additional image data acquired from gripping inside the set areas. The method also includes computing, using the learning model during the driving scenario, second grip intensity outside the set areas on the steering device according to hand images acquired about the operator. The method also includes adapting a vehicle parameter of the vehicle according to the second grip intensity.