21945results about "Control devices" patented technology

An example may receive at least one input via at least one device. An example may use the at least one input to determine an entity identity. An example may use the entity identity to create an automated agent and load context data associated with the entity identity into at least one layer of a multi-layer memory of the automated agent. An example may cause the automated agent to machine-learn a supervision level via the context data. The machine-learned supervision level may indicate a level of supervision of the automated agent by an entity associated with the entity identity. An example may configure the automated agent to execute a task on behalf of the entity and in accordance with the machine-learned supervision level.

The invention relates to the technical field of new energy automobile thermal management, in particular to a direct cooling and heating management system and method in an automobile power battery. The method comprises the following steps: acquiring vehicle real-time operation condition data and battery pack state monitoring data; working condition mode recognition processing is conducted according to the vehicle real-time operation working condition data, and vehicle working condition mode feature data are generated; performing thermal load demand analysis on the battery pack state monitoring data based on the vehicle working condition mode characteristic data to obtain dynamic thermal load demand data of the battery pack; and according to the dynamic thermal load demand data of the battery pack, refrigerant demand quantity calculation and analysis are carried out, the refrigerant supply capacity of the current direct cooling system is evaluated, and refrigerant supply and demand matching feature data are obtained. The specific requirements of three heat sources of the battery, the motor and the cockpit for the refrigerant flow are quantified, and a refrigerant distribution strategy is formed according to the proportional relation, so that the safety of the battery is improved, and the driving comfort and the working stability of the electric driving system are also guaranteed.

An apparatus and method relate to analyzing metrics relating to EV charging points and facilitating selection of an EV charge point based on metrics associated with the EV charge points. Methods may include: determining locations of one or more electric vehicle charging stations; determining a total power available at the one or more electric vehicle charging stations; determining, for the one or more electric vehicle charging stations, if dynamic load balancing is used; determining occupancy of charge points at each of the one or more electric vehicle charging stations; calculating an available power at a charge point of the one or more electric vehicle charging stations based on the total power available and the occupancy of charge points for the one or more electric vehicle charging stations; and calculating an estimated time to charge a vehicle at the one or more electric vehicle charging stations based on the available power.

The invention provides an end-to-end automatic driving decision control method and system, and belongs to the technical field of automatic driving. The invention relates to an end-to-end automatic driving decision control method based on multi-modal perception and hierarchical trajectory optimization, and the method comprises the steps: constructing an end-to-end decision closed loop through combining the zero sample migration capability of a vision-language-action (VLA) model with a hierarchical optimization architecture: analyzing multi-modal input (vision, language and point cloud) by using a pre-trained VLA model to generate path points; the vehicle pose is dynamically adjusted through upper-layer optimization to expand a feasible solution space, a smooth track meeting dynamics and collision avoidance constraints is solved in real time through lower-layer optimization, and finally a vehicle control instruction is output. According to the method, a multi-modal sensing and hierarchical trajectory optimization mechanism is fused, and the sensing generalization ability, the path planning feasibility and the control execution robustness of the system in a complex traffic environment are effectively improved.

A system and method generate a trip plan for a trip of a vehicle system along a route. The usage of an engine during the trip is determined based on engine operational parameters, energy storage device operational parameters, and one or more objectives of the trip desired to be achieved. The usage of the energy storage device during the trip is also determined based on the engine operational parameters, the energy storage device operational parameters, and the one or more objective, including when to charge or discharge the energy storage device during the trip.

The invention discloses an end-to-end automatic driving method based on dynamic multi-modal fusion in a complex scene, and belongs to the technical field of automatic driving. In order to solve the problems of sensor perception deficiency, cross-modal feature mismatching, unstable trajectory planning and the like easily occurring in night, low-illumination and complex dynamic environments in the existing end-to-end automatic driving method, texture details of a camera mode and geometric structure features of a laser radar mode are respectively enhanced through a double-flow feature refining mechanism; the characteristic difference between different modes is relieved; an information-driven dynamic fusion strategy is designed, the fusion weight is adaptively adjusted according to scene factors such as environment illumination and obstacle density, and the scene sensitivity and discrimination ability of the model are improved; asymmetric convolution and a low-rank-sparse decoupling technology are introduced, multi-order reconstruction of key channels is carried out on the multi-modal features, and the path change modeling capability is enhanced; and in combination with time sequence dependence of waypoints, outputting a future trajectory through an autoregression decoder to realize high-precision trajectory prediction and stable decision control.

The invention belongs to the technical field of radars, and discloses a vehicle-mounted multi-source radar converged communication system based on a FlexRay bus and a synchronization method of the vehicle-mounted multi-source radar converged communication system based on the FlexRay bus. The FlexRay communication bus supports a static and dynamic dual-channel structure and has a deterministic communication capability, and the maximum bandwidth can reach 10Mbps; the distributed radar controller is connected with each radar node and used for collecting local radar data, packaging timestamps and uploading the data through FlexRay; the time synchronization controller is used for realizing nanosecond synchronization through a FlexRay global clock mechanism and broadcasting clock signals to all radar nodes; the fusion processing unit is used for intensively receiving all radar data and carrying out target detection and data fusion based on a unified time sequence; and the main control coordination module is used for upwards communicating with the automatic driving domain controller and downwards uniformly coordinating the behaviors of the subsystems. The system has the capabilities of accurate time sequence, multi-source data fusion, fault-tolerant control and the like, and is a high-reliability communication platform supporting intelligent driving decision making.

The invention discloses a battery thermal management method, device and system and a vehicle, and relates to the technical field of battery management. A specific embodiment of the method comprises the following steps: acquiring battery data of a battery, acquiring a maximum battery cell temperature from the battery data, and extracting battery characteristics; determining the thermal runaway probability of the battery according to the battery data and the battery characteristics; selecting a target early warning strategy matched with the maximum cell temperature and the thermal runaway probability from a preset multi-level early warning strategy and a preset hidden state early warning strategy; according to the environment information of the environment where the battery is located and the battery characteristics, rule parameters in the target early warning strategy are adjusted, and regulation and heat dissipation are conducted on the battery through the adjusted target early warning strategy. According to the embodiment, the rule parameters of the early warning strategy are adaptively adjusted according to the actual state of the battery, a fixed threshold value judgment mode is replaced, advanced recognition of potential hazards and dynamic optimization of the early warning strategy are achieved, and therefore early warning accuracy and flexibility are greatly improved.

The invention relates to the technical field of intelligent driving, and discloses an obstacle avoidance analysis system for intelligent driving. The system comprises a data acquisition module, a road feature extraction module, a lane type judgment module, a virtual marking generation module, an obstacle detection and trajectory prediction module, a dynamic obstacle avoidance decision module and a system verification and optimization module. The method comprises the following steps: acquiring data through a laser radar, a camera and the like; fusing point cloud and an image to extract the width and curvature of a road; judging the type of a lane according to the width; generating a virtual marking line on a marking-free road, fitting by using a B-spline curve when the curvature is large, fusing the point cloud and the image to detect an obstacle, and predicting a track by using Kalman filtering or a social force model. In combination with virtual marking and risk assessment, a safe trajectory is generated through an OccupanyGrid map, an A * algorithm and MPC, and a simulation and real road test optimization system is adopted, so that the problem of marking-free road trajectory planning deviation is solved, and the obstacle avoidance precision and the road condition adaptability are improved.

The invention discloses a vehicle, a driving track generation method, electronic equipment, a storage medium and a product, and relates to the technical field of intelligent driving. The method comprises the following steps: inputting bird's-eye view angle characteristics of an all-round view image of a vehicle into a computer vision model to obtain a plurality of candidate initial driving tracks; and selecting a target visual language model according to the driving instruction, generating a trajectory correction cue word according to each candidate initial driving trajectory, the look-around image, the driving state information and the driving instruction, and performing trajectory correction on each candidate initial driving trajectory by using the target visual language model. And calculating the driving cost of each candidate driving track based on different types of driving cost weight coefficients determined by the look-around image, and finally outputting the candidate driving track with the lowest driving cost as the driving track of the vehicle at the next moment. According to the invention, the problem that the track generation quality cannot meet the real demand of a user in related technologies can be solved, and the track prediction accuracy and reliability are effectively improved.

The invention relates to the technical field of electric forklifts and energy storage, and discloses an intelligent battery management system and prediction method based on optical fiber sensing, the system comprises a distributed optical fiber sensing network, a data acquisition and processing module, an intelligent analysis decision module, a battery management control module and a cloud platform interaction module; the method comprises the following steps: collecting a battery signal through a snakelike-spiral optical fiber network, reconstructing a temperature / strain field through noise reduction and filtering, extracting multi-modal features, inputting the multi-modal features into an LSTM model to predict thermal runaway, generating a risk level in combination with an improved equation, dynamically adjusting charging, discharging and heat dissipation strategies, and realizing three-dimensional visual monitoring through a cloud platform. According to the invention, high-precision distributed monitoring of the temperature / strain field of the battery pack is realized through the BOTDR optical fiber sensing network, the LSTM prediction model is constructed by fusing multi-physical field characteristics, and thermal runaway is warned in advance. The improved algorithm reduces the false alarm rate, charging and discharging parameters are dynamically adjusted to prolong the service life of the battery, and a three-dimensional visual platform improves the operation and maintenance efficiency.

The invention discloses a world model driven decision model training method, system, device and product, and relates to the technical field of artificial intelligence. According to the scheme, the initial world model is generated through the target video data and the diffusion generation model, and the initial world model is finely adjusted by using three different loss functions, namely the diffusion loss function, the dynamic loss function and the structure maintenance loss function based on the third-order motion prior; physical consistency and high-frequency detail fidelity of short-term and long-range prediction are realized; furthermore, a reward function is automatically generated by using the uncertainty of world model prediction, so that the training efficiency is improved; according to target video data and a world model closed-loop training decision model, collaborative optimization of environment cognition and strategy evolution is realized; and finally, the trained world model and the decision model can be integrated to the target server, closed-loop control of perception-decision-motion execution is realized, the method has low delay, high robustness and expansibility, and the safety of the automatic driving system is improved.

A method of controlling drift of a vehicle in which the vehicle more easily enters, maintains, releases, and transitions drift behavior, includes determining, by a controller, whether a current driving situation of the vehicle is a drift entry situation or a release situation based on vehicle driving information, and generating a drift index configured to indicate a current degree of drift from a determination result, determining, by the controller, a target yaw moment for left and right speed control depending on a driving situation or a braking situation of the vehicle and target yaw moments for drift assistance control depending on a driver input and a vehicle state in the drift entry situation, based on the vehicle driving information, and generating and outputting, by the controller, a target torque of a motor configured to drive each wheel of the vehicle based on the determined target yaw moments.

A blood pump system includes a catheter, a pump housing disposed distal of a distal end of the catheter, a rotor positioned at least partially in the pump housing, a controller, and an electrode coupled a distal region of the blood pump. The electrode can be used to sense electrocardiogram (EKG) signals and transmit the signals to a controller of the blood pump. The operation of the blood pump can be adjusted based on the EKG signal and on cardiac parameters derived from the EKG signal. Further, the controller can determine a need for defibrillation or pacing of the patient's heart based on the signal and can administer treatment with electrical shocks to the heart via the electrode coupled to the blood pump. The use of an electrode with a blood pump already in place in the heart allows for more efficient and safer treatment of serious cardiac conditions.

Apparatus and methods are described including delivering a left-ventricular assist device to a subject's aorta. The device including a distal-tip element that defines a straight proximal portion, and a curved distal portion, the curved distal portion defining first and second curves with an elongated straight portion between the first and second curves. The distal-tip element is centered with respect to the aortic valve using the curved distal portion of the distal-tip element, to thereby guide the device through the subject's aortic valve atraumatically. A pump pumps blood through from the subject's left ventricle to the subject's aorta. Other applications are also described.

Systems and methods for controlling an implantable pump are provided. For example, the exemplary controller for controlling the implantable pump may only rely on the actuator's current measurement. The controller is robust to pressure and flow changes inside the pump head, and allows fast change of pump's operation point. For example, the controller includes, a two stage, nonlinear position observer module based on a reduced order model of the electromagnetic actuator. The controller includes an algorithm that estimates the position of the moving component of the implantable pump based on the actuator's current measurement and adjusts operation of the pump accordingly. Alternatively, the controller may rely on position measurements and / or velocity estimations.

The invention discloses a forward collision early warning device and method based on risk assessment, electronic equipment and a storage medium, and relates to the field of driving prediction, and the device comprises a sensing unit which is used for obtaining the relative position data of a detected object, and carrying out the modeling according to the relative position data of the recognized detected object; detecting a driving state of a driver; detecting the motion state of the vehicle in real time; the processing unit is used for processing the data of the sensing unit in real time, performing target classification, running a dynamic risk assessment algorithm and outputting an early warning level; the prompt unit is used for displaying prompt information on the instrument panel display module and the vehicle-mounted terminal; by means of the scheme, the problems that when a static vehicle or a low-speed obstacle is detected by an existing system, due to the conservative property of TTC calculation, the time window for triggering early warning is later, collision is difficult to avoid when the vehicle is close to the static vehicle, and potential safety hazards exist are solved.

Apparatus and methods are described including delivering a left-ventricular assist device to a subject's left ventricle. A tube is positioned such that a proximal portion of the tube traverses an aortic valve of the subject, and a distal portion of the tube is disposed within a left ventricle of the subject. A pump pumps blood through the tube from the subject's left ventricle to the subject's aorta such as to cause the proximal portion of the tube to be maintained in an open state, and to cause at least a portion of the tube to become curved. Other applications are also described.

The invention provides an automatic driving vehicle track prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring scene information and initial noise of a target vehicle; the scene information comprises surrounding vehicle information, road information, static object information and navigation information; predicting a future trajectory of the target vehicle according to the scene information and the initial noise based on a pre-trained automatic driving trajectory prediction model; the automatic driving track prediction model comprises an adaptive layer normalization sub-module and a scale adaptive self-attention sub-module; the automatic driving track prediction model is obtained by training according to a scene information sample and a real self-vehicle track sample added with noise, and the automatic driving track prediction model can predict a conditional velocity field and an unconditional velocity field at the same time during training. According to the method, efficient space-time fusion of multi-source input information is realized, and a multi-vehicle game / interaction behavior in a high-interaction scene is effectively simulated.

The invention provides a vehicle anti-skid control method, device and system and a vehicle. According to at least one driving wheel of the vehicle, the chassis wheel speed, the actual wheel speed, the wheel end actual torque, the adhesion coefficient, the total wheel load, the target slip rate, the wheel radius and the vehicle speed are obtained; a feedforward control torque is determined according to an attachment coefficient, a total wheel load and a wheel radius, a wheel speed deviation is determined according to a target slip rate, a chassis wheel speed and an actual wheel speed, a torque deviation is adjusted through a vehicle speed, the attachment coefficient and the wheel speed deviation to obtain a feedback control torque, and the feedback control torque and the attachment coefficient are superposed to serve as an output torque for vehicle anti-skid control. Dynamic wheel load changes and wheel load changes caused by the vehicle on the ramp road surface are considered, the total wheel load is estimated in real time, feed-forward control is introduced to obtain the feed-forward control torque, feedback control is compensated, and the stability and accuracy of anti-skid control are enhanced when the ramp road surface and the loads change.

Apparatus and methods are described including a ventricular assist device that includes an impeller configured to be placed inside a left ventricle of a subject. A driving magnet is coupled to a motor and is rotated by the motor. A driven magnet is magnetically coupled to the driving magnet and is rotated by the driving magnet. A drive cable extends from the driven magnet and imparts rotational motion from the driven magnet to the impeller. A set of sensors is configured to detect a magnetic phase difference between the driven magnet and the driving magnet. A computer processor receives the detected magnetic phase difference and determines a physiological parameter of the subject, at least partially in response thereto. Other applications are also described.

The invention relates to the technical field of charging control, in particular to a new energy automobile charging safety regulation and control method and system, and the method comprises the steps: collecting a multi-dimensional feature parameter set; acquiring battery health state and charge state information, and collecting multi-point temperature information on the surface of the battery; constructing the multi-dimensional feature parameter set into a multi-dimensional time sequence, performing statistical analysis on the multi-dimensional time sequence, and extracting dynamic feature indexes; performing structured fusion on the dynamic characteristic indexes, thermal field gradient parameters calculated according to multi-point temperature information and a multi-dimensional characteristic parameter set, and projecting the dynamic characteristic indexes, thermal field gradient parameters and the multi-dimensional characteristic parameter set to a key characteristic subspace through principal component analysis to obtain a charging response vector; generating a multi-dimensional security hyperplane through the dynamic security boundary model; continuously comparing the charging response vector with the multi-dimensional safety hyperplane, and calculating a safety margin scalar in real time; and inputting the safety margin scalar into the self-adaptive regulation and control model, and adjusting the charging current output. According to the invention, active predictive charging safety regulation and control are realized through multi-dimensional perception.

A modular electric power take-off (E-PTO) system for a refuse vehicle includes a modular housing. The modular E-PTO also includes a motor, an inverter, a battery, and a hydraulic pump positioned within the modular housing. The modular housing is removably coupled with a front of a waste receptacle or a hopper of the waste receptacle of a refuse vehicle.

The invention belongs to the field of driver state detection, and particularly discloses a multi-dimensional data-based driver state detection method and system, and the method comprises the steps: collecting binocular image data of a driver region through a binocular vision camera, and constructing a multi-dimensional data collection system in combination with pressure and angle sensors at positions such as a seat and a steering wheel. A binocular vision image analysis algorithm is used for establishing a driver body posture visual space model, sensor data are converted into physical parameters through a multi-dimensional data body posture calculation model, a complete body posture representation model is constructed through fusion matching, and real-time states such as fatigue and distraction of a driver are detected in combination with preset rules. The system comprises six units including a binocular image acquisition and sensing unit and a multi-dimensional data acquisition and sensing unit, and all the units work cooperatively. According to the invention, accurate and real-time detection of the driver state is realized by using multi-source data and an innovative model.

A thermal management system includes a compressor, a water-cooled condenser, a battery chiller, a valve body assembly, a first water pump, a second water pump, and a third water pump that are disposed in a centralized manner. The thermal management system can separately form a passenger compartment cooling loop, a passenger compartment heating loop, a battery cooling loop, a battery heating loop, and an electrical driver cooling loop, and any one or more of the passenger compartment, the battery, and the electrical driver can be cooled or heated.

The invention discloses a cloud control self-driving automobile control method considering automobile cloud communication time delay. By constructing a time delay prediction model based on historical communication delay data, the back-and-forth communication time delay at the current moment is accurately predicted, and forward compensation is carried out on the vehicle state by adopting an iterative prediction formula in combination with a vehicle transverse dynamic model. According to the method, a process disturbance correction item is introduced, system modeling errors caused by environment disturbance are effectively corrected, and the state prediction precision is improved. And deducing a future vehicle state through the predicted time delay step number in combination with a historical vehicle state and control input so as to realize dynamic compensation of the time delay influence. The method effectively solves the problems of control lag and state information lag caused by communication delay in vehicle-cloud cooperative control, improves the control real-time performance and precision of a cloud control automatic driving system, enhances the robustness and safety of the system in a complex environment, and is suitable for automatic driving scenes with high dynamic and high safety requirements.

A catheter includes a catheter body, a pump assembly and a cannula. The pump assembly can be disposed at a distal end of the catheter body and has a distal portion. The cannula can be coupled to the distal end portion of the pump assembly and can include a proximal cannula portion and a distal cannula portion. The distal cannula portion has an approximately helical shape which can allow the cannula to be inserted into a patient's right heart and pump blood therethrough. In certain implementations, the distal tip of the helical shape has a slight bias relative to the main helix to further facilitate delivery of the device. In certain applications this bias is toward the central axis of the helix.

The invention discloses a hybrid electric vehicle predictive energy management system based on multi-layer cooperative control, and aims to improve the vehicle performance and energy efficiency. According to the method, a hierarchical cooperative control architecture is adopted, and the reinforcement learning, vehicle speed multi-step prediction and model prediction control technologies are combined, so that joint optimization control over vehicle acceleration and power distribution is achieved. The system obtains the vehicle running state and the surrounding environment information in real time through the state sensing module, and determines the expected acceleration by using a strategy network trained by a PPO algorithm. In addition, the future vehicle speed is predicted in combination with an XGBoost multi-step regression model, the optimization module is designed through an MPC strategy, oil consumption, the battery state and driving smoothness are comprehensively considered, and therefore efficient management of the power system is achieved. According to the scheme, the obvious energy-saving advantage is achieved, the driving smoothness and comfort are improved, the good self-adaptive capacity and a real-time feedback mechanism are achieved, and the method is suitable for the complex urban road traffic environment.

The battery pack includes an enclosure including interconnected walls, one or more battery cells contained within the enclosure, and a heat-conducting plate defining one or more of the interconnected walls and being structurally load-bearing. The heat-conducting plate has a first section, the one or more battery cells in heat exchange relationship with the first section, and a second section in heat exchange relationship with the first section. The second section is in heat exchange relationship with an environment outside the enclosure for providing heat exchange between the one or more battery cells and the environment.