Abstract: In some examples, a dynamic system, including a vehicle, may be represented using a graph-based representation. One or more nodes in the graph-based representation may correspond to one or more agents in the dynamic system, and one or more edges between the nodes in the graph-based representation may correspond to one or more interactions between the agents in the dynamic system. The interactions may be defined based on human domain knowledge of the dynamic system. The dynamic system may be modeled using a respective machine learning model that includes a reward decoder that operates on the graph-based representation and evaluates one or more reward functions for the dynamic system. The one or more reward functions may be defined based on the human domain knowledge of the dynamic system. Autonomous operation of the vehicle may be controlled based on the modeling of the dynamic system.

Abstract: A battery includes a housing, a plurality of cells disposed inside the housing, and a set of strap structures. Each cell comprises a plurality of positive electrode plates and a plurality of negative electrode plates, and each respective electrode plate has a respective tip. The set of strap structures includes one or more of a first strap structure, which includes a positive strap line, a negative strap line, and at least two bridging lines disposed between and connected with the positive strap line and the negative strap line. The negative strap line is connected with respective tips of a plurality of negative electrode plates in a cell. The positive strap line is connected with respective tips of a plurality of positive electrode plates in a different cell. The first strap structure, the set of strap structure, and a method of making the battery are also provided.

Abstract: A method and system for controlling a device includes training a low-level policy to form a trained low-level policy and a low-level value function to form a trained goal conditioned value function, wherein training is performed using a static data set using goal conditioned episodes, training a high-level goal planner having high level goals having high-level sub-goals corresponding to a plurality of future time steps using the low-level value function to maximize a cumulative reward over the sub-goals for the plurality of future time steps so that the sub-goals are reachable by the low-level policy, obtaining an observation of a device, and generating an executable action using the low-level policy and the high-level goal planner and operating the device with the executable action.

Abstract: An electrode-modified heavy metal ion microfluidic detection chip, comprising a microfluidic module (1) and a three-electrode sensor (2), wherein the microfluidic module (1) is integrally molded by 3D printing, and the interior thereof has a microchannel (10) and a sensor slot (11); and the three-electrode sensor (2) comprises three electrodes (21, 22, 23) printed on a card-shaped bottom plate (20), among which the working electrode (21) is a porous nano-NiMn2O4 modified bare carbon electrode, and the three-electrode sensor (2) is inserted into the sensor slot (11) that matches same to form the microfluidic detection chip.

Abstract: Systems and methods for pessimistic offline reinforcement learning are described herein. In one example, a method for performing offline reinforcement learning determines when sampled states are out of distribution, assigns high probability weights to the sampled states that are out of distribution, generates a fitted Q-function by solving an optimization problem with a minimization term and a maximization term, estimates a Q-value using the fitted Q-function by estimating the overall expected reward assuming the agent is in the present state and performs a present action, and updates the policy according to an existing reinforcement learning algorithm. The minimization term penalizes an overall expected reward when a present state is out of distribution. The maximization term cancels the minimization term when the present state is an in-distribution state.

Abstract: An electrode-modified heavy metal ion microfluidic detection chip, comprising a microfluidic module (1) and a three-electrode sensor (2), wherein the microfluidic module (1) is integrally molded by 3D printing, and the interior thereof has a microchannel (10) and a sensor slot (11); and the three-electrode sensor (2) comprises three electrodes (21, 22, 23) printed on a card-shaped bottom plate (20), among which the working electrode (21) is a porous nano-NiMn2O4 modified bare carbon electrode, and the three-electrode sensor (2) is inserted into the sensor slot (11) that matches same to form the microfluidic detection chip.

Abstract: A device for rapidly detecting energy efficiency of a permanent magnet synchronous motor includes a test platform, an energy circulation device, and a data synchronous acquisition module, the test platform being fixedly connected to support legs via threads, an upper end surface of the test platform being provided with baffles to define a motor mounting tank, a bolt hole being provided in a surface of an outer baffle of the motor mounting tank, the energy circulation device being mounted on a fixed baffle on one end of the motor mounting tank, a second intelligent power analyzer, a first intelligent power analyzer, and a temperature inspection instrument being sequentially mounted on an upper surface of a tail end on a right side of the test platform, and the data synchronous acquisition module being provided on one end of an inner wall of the motor mounting tank.

Abstract: The present disclosure discloses a method and device for detecting a state of holding a steering wheel, wherein the method includes: a detection result is obtained by detecting a video stream collected from a target vehicle; an associated state of the first ROI information and the second ROI information in the two-dimensional plane carried in the detection result is obtained, wherein the first ROI information is ROI information about the steering wheel of the target vehicle, and the second ROI information is ROI information about the driver's hand of the target vehicle; a current state between the hand of the driver and the steering wheel of the target vehicle is determined according to the associated state. Then, the disclosure solves the technical problem in the related art that it is impossible to detect the grasping state of the steering wheel by the driver while driving.

Abstract: A device for rapidly detecting energy efficiency of a permanent magnet synchronous motor includes a test platform, an energy circulation device, and a data synchronous acquisition module, the test platform being fixedly connected to support legs via threads, an upper end surface of the test platform being provided with baffles to define a motor mounting tank, a bolt hole being provided in a surface of an outer baffle of the motor mounting tank, the energy circulation device being mounted on a fixed baffle on one end of the motor mounting tank, a second intelligent power analyzer, a first intelligent power analyzer, and a temperature inspection instrument being sequentially mounted on an upper surface of a tail end on a right side of the test platform, and the data synchronous acquisition module being provided on one end of an inner wall of the motor mounting tank.

Abstract: The present disclosure relates to a liquid crystal panel and a repairing method thereof, and a display device. The liquid crystal panel includes an array substrate and a filter substrate, and the repairing method includes: irradiating a pixel which is a bright spot of the liquid crystal panel with laser from one side of the array substrate away from the filter substrate, so that a portion of the array substrate located in the pixel is converted from a light transmitting area into a light shielding area.

Abstract: The present disclosure discloses a method and device for detecting a state of holding a steering wheel, wherein the method includes: a detection result is obtained by detecting a video stream collected from a target vehicle; an associated state of the first ROI information and the second ROI information in the two-dimensional plane carried in the detection result is obtained, wherein the first ROI information is ROI information about the steering wheel of the target vehicle, and the second ROI information is ROI information about the driver's hand of the target vehicle; a current state between the hand of the driver and the steering wheel of the target vehicle is determined according to the associated state. Then, the disclosure solves the technical problem in the related art that it is impossible to detect the grasping state of the steering wheel by the driver while driving.

Abstract: In some examples, a dynamic system, including a vehicle, may be represented using a graph-based representation. One or more nodes in the graph-based representation may correspond to one or more agents in the dynamic system, and one or more edges between the nodes in the graph-based representation may correspond to one or more interactions between the agents in the dynamic system. The interactions may be defined based on human domain knowledge of the dynamic system. The dynamic system may be modeled using a respective machine learning model that includes a reward decoder that operates on the graph-based representation and evaluates one or more reward functions for the dynamic system. The one or more reward functions may be defined based on the human domain knowledge of the dynamic system. Autonomous operation of the vehicle may be controlled based on the modeling of the dynamic system.

Abstract: The present disclosure relates to a liquid crystal panel and a repairing method thereof, and a display device. The liquid crystal panel includes an array substrate and a filter substrate, and the repairing method includes: irradiating a pixel which is a bright spot of the liquid crystal panel with laser from one side of the array substrate away from the filter substrate, so that a portion of the array substrate located in the pixel is converted from a light transmitting area into a light shielding area.

Abstract: A method and device for use in hand gesture recognition is applicable to image processing. The method includes: acquiring a depth map of a hand in a current image; estimating first positions of joints of the hand according to the depth map of the hand; creating a 3D point cloud of the hand according to the depth map of the hand; matching the first position of the joints of the hand and a stored 3D hand model to the 3D point cloud of the hand to obtain second positions of the joints and first degree of freedom parameters of the joints; and recognizing the hand's gestures according to the second positions of the joints and the first degree of freedom parameters of the joints. The method achieves a practical hand gesture recognition technique and recognizes hand gestures accurately.

Abstract: A multi-card user equipment and a method for processing its service are provided. The method includes, when receiving service request corresponding to a first subscriber identity card, implementing data transmission channel between user equipments and a network which is corresponding to the first subscriber identity card to process the service request; the data transmission channel corresponding to at least two of the subscriber identity cards shares a common wireless connection. With the method, providing services for multiple cards at the same time can be available, meanwhile hardware cost and complexity is decreased, and wireless transmission resources is saved.

Abstract: A method and device for use in hand gesture recognition is applicable to image processing. The method includes: acquiring a depth map of a hand in a current image; estimating first positions of joints of the hand according to the depth map of the hand; creating a 3D point cloud of the hand according to the depth map of the hand; matching the first position of the joints of the hand and a stored 3D hand model to the 3D point cloud of the hand to obtain second positions of the joints and first degree of freedom parameters of the joints; and recognizing the hand's gestures according to the second positions of the joints and the first degree of freedom parameters of the joints. The method achieves a practical hand gesture recognition technique and recognizes hand gestures accurately.

Abstract: Embodiments of the invention relate to a composite film and a fabrication method thereof, a photoelectric element and a photoelectric apparatus. The fabrication method of the composite film includes: preparing a polyfluorene-based compound solution, wherein the polyfluorene-based compound solution includes polyfluorene or polyfluorene derivatives; preparing a quantum dot solution; mixing the polyfluorene-based compound solution and the quantum dot solution together to prepare a mixed solution; removing a solvent in the mixed solution to prepare the composite film.

Abstract: A multi-card user equipment, and service processing method and device thereof are provided. The method includes, when receiving a service request, detecting whether a data transmission channel has been established with a network, wherein a number of the established data transmission channels is less than a number of the subscriber identity cards in the multi-card user equipment; and processing a service corresponding to the service request by using the established data transmission channel. With the method, multiple cards can be provided service at the same time, while hardware cost and complexity is decreased and wireless transmission resources is saved.

Abstract: The invention refers to quantum dots (QDs) composite particles and their preparation method, photoelectric elements and photoelectric equipment. The preparation method of QDs composite particles comprises: coating the surface of metal nanoparticles (MNPs) with silica; modifying the silica coated MNPs through amination to make the surface of the silica have amino functional groups; and combining the carboxyl-functionalized QDs with amino-functionalized silica coated MNPs, thereby preparing the QDs composite particles. The preparation method can enhance the fluorescent efficiency of QDs.