Abstract: Methods and systems for decision making in an autonomous vehicle (AV) are described. A vehicle control system may include a control unit, a perception unit, and a behavioral planning unit. The behavioral planning unit may include an intent estimator that receives a first set of perception information from the perception unit. The behavioral planning unit may include a motion predictor that receives the first set of perception information from the perception unit. The behavioral planning unit may include a function approximator that receives a second set of perception information from the perception unit. The second set of perception information is smaller than the first set of perception information. The function approximator determines a prediction, and the control unit uses the prediction to control an operation of the AV.

Abstract: A method for controlling lane changing of a vehicle, including: receiving a lane changing instruction (step 101); acquiring a speed parameter of the vehicle (step 102); according to the speed parameter, determining a controlling coefficient of a predetermined controller (step 103); acquiring a position-deviation parameter and a heading-angle parameter of the vehicle; if the position-deviation parameter is greater than or equal to a first threshold, or, if the heading-angle parameter is greater than or equal to a second threshold, according to the controlling coefficient, the position-deviation parameter and the heading-angle parameter, determining a target steering-wheel steering angle of the vehicle; and according to the target steering-wheel steering angle, controlling the vehicle to perform a lane changing operation, till the position-deviation parameter is less than the first threshold, and the heading-angle parameter is less than the second threshold (step 105).

Abstract: A method for edge identification of a self-shadowing object based on a visual camera and a vehicle includes: collecting image data of an object to be identified, and performing differentiation processing; according to a preset threshold, performing three-value processing to the image that has been differentiation-processed, to acquire a three-value-processed image including positive-direction boundary pixels and negative-direction boundary pixels; according to the positive-direction boundary pixels and the negative-direction boundary pixels, acquiring a positive-direction straight linear segment and a negative-direction straight linear segment that represent boundary trends of the object to be identified; if the straight linear segments do not create a target object that satisfy a predetermined condition, determining the first boundary according to the predetermined condition; according to the first boundary, determining the second boundary; and by using positions of the first boundary and the second boundary

Abstract: A method for controlling gear shifting, including: acquiring a current gear-shifting parameter of the vehicle (101); according to the current gear-shifting parameter and a preset target rotational speed, determining a gear-shifting inputted rotational speed (102); and when a rotational speed of the vehicle reaches the gear-shifting inputted rotational speed, controlling a shifting fork to start up a gear-shifting operation (103). The method for controlling gear shifting presets the target rotational speed of the gears, and, according to the current gear-shifting parameter of the vehicle that is acquired in real time and the preset target rotational speed, inversely calculates the gear-shifting inputted rotational speed, whereby the gear-shifting inputted rotational speed is an accurate gear-shifting inputted rotational speed that matches with the current condition of the vehicle.

Abstract: A control strategy includes: after an engine is energized, the continuously variable valve lift mechanism self learning to determine a current position; if the self learning is successful, the continuously variable valve lift mechanism being located at a maximum lift position, preparing for starting the engine, and determining a regulating mode based on a starting temperature, wherein at the time of normal temperature start, regulation is performed from the maximum lift position to a minimum lift position, and at the time of low temperature start, regulation is performed from the maximum lift position to a position where the two valves for the same cylinder have a maximum lift difference; if the self learning fails, entering a preliminary start mode; entering a CVVL control mode based on an operation condition of the engine; and powering off the engine.

Abstract: A hydraulic controlling system including: a cooling and lubricating oil line and a main controlling oil line; an oil-liquid storage; a first pump, wherein an inlet of the first pump is connected to the oil-liquid storage and an outlet of the first pump is connected to the main controlling oil line; a second pump, wherein an inlet of the second pump is connected to the oil-liquid storage and an outlet of the second pump selectively communicates with the cooling and lubricating oil line or the main controlling oil line; and a gearbox-gear-shifting oil line including a gear-shifting-pressure regulating valve, a plurality of gear-shifting-flow-rate controlling valves and a plurality of gear-shifting selector valves. The gear-shifting-flow-rate controlling valves are connected to the main controlling oil line via the gear-shifting-pressure regulating valve. At least some of the gear-shifting-flow-rate controlling valves are connected to a gear-shifting executing piston via the gear-shifting selector valves.

Abstract: A flow valve control method, apparatus, and storage medium are provided. The method comprises: conducting a median current value teach-in of a flow valve starting from an initial median current value of the flow valve; and correcting a flow-current curve of the flow valve based on a deviation value obtained by the teach-in. Each teach-in process comprises: controlling current output to a flow valve, so that the flow valve successively goes through: when there is a flow passing through, an output flow enables a shifting mechanism to return to position, and when there is a flow passing through again, an output flow again enables the shifting mechanism to return to position; recording a current value the twice when there is a flow passing through the flow valve as a maximum median current value; and acquiring a deviation value of the maximum median current value from the initial median current value.

Abstract: A method and apparatus for correcting a physical slip and wear coefficient of a clutch comprising obtaining a torque difference according to a positional relation between an engine and the clutch; obtaining a correction weight value corresponding to an engine torque according to the torque difference; and correcting the physical slip and wear coefficient according to the correction weight value and a running-in state of the clutch. The method relates to obtaining a torque difference in real time by means of a positional relation between the engine and the clutch in a manner corresponding to the positional relation, obtaining a correction weight value corresponding to the engine torque according to the torque difference, and further correcting the physical slip and wear coefficient by combining the correction weight value and a running-in state of the clutch.

Abstract: A control strategy includes: after an engine is energized, the continuously variable valve lift mechanism self learning to determine a current position; if the self learning is successful, the continuously variable valve lift mechanism being located at a maximum lift position, preparing for starting the engine, and determining a regulating mode based on a starting temperature, wherein at the time of normal temperature start, regulation is performed from the maximum lift position to a minimum lift position, and at the time of low temperature start, regulation is performed from the maximum lift position to a position where the two valves for the same cylinder have a maximum lift difference; if the self learning fails, entering a preliminary start mode; entering a CVVL control mode based on an operation condition of the engine; and powering off the engine.

Abstract: Disclosed herein are methods and systems for motion planning in an autonomous vehicle (AV) that separate path planning and velocity planning and may use reference lines in combination with motion planners to determine paths. The method may include reference lines to project planning data into a S-L coordinate system. A motion planner algorithm uses the reference lines and previous path planning history to generate a path in the S-L coordinate system. A velocity is determined for the path. An AV controller is updated with the path and the velocity. Motion planning computations use a dynamic vehicle look-up table to determine possible vehicle motions based on an initial state and control input.

Abstract: Methods and systems may be used for obtaining a high-confidence point-cloud. The method includes obtaining three-dimensional sensor data. The three-dimensional sensor data may be raw data. The method includes projecting the raw three-dimensional sensor data to a two-dimensional image space. The method includes obtaining sparse depth data of the two-dimensional image. The method includes obtaining a predicted depth map. The predicted depth map may be based on the sparse depth data. The method includes obtaining a predicted error-map. The predicted error map may be based on the sparse depth data. The method includes outputting a high-confidence point-cloud. The high-confidence point-cloud may be based on the predicted depth map and the predicted error-map.

Abstract: Methods and systems may be used for obtaining a high-confidence point-cloud. The method includes obtaining three-dimensional sensor data. The three-dimensional sensor data may be raw data. The method includes projecting the raw three-dimensional sensor data to a two-dimensional image space. The method includes obtaining sparse depth data of the two-dimensional image. The method includes obtaining a predicted depth map. The predicted depth map may be based on the sparse depth data. The method includes obtaining a predicted error-map. The predicted error map may be based on the sparse depth data. The method includes outputting a high-confidence point-cloud. The high-confidence point-cloud may be based on the predicted depth map and the predicted error-map.

Abstract: Methods and system for compensating for vehicle system errors. A virtual camera is added to vehicle sensor configurations and a coordinate transformation process which attempts to match multiple 3D points associated with a landmark to a detected landmark. The virtual camera is associated with the detected landmark. The 3D world coordinate points may be transformed to a real 3D camera coordinate system and then to a virtual 3D camera coordinate system. The 3D points in real and virtual camera coordinate frames are projected onto the corresponding 2D image pixel coordinates, respectively. Inclusion of the virtual camera in the coordinate transformation process presents a 3D to 2D point corresponding problem which may be resolved using camera pose estimation algorithms. An offset compensation transformation matrix may be determined which accounts for errors contributed by mis-calibrated vehicle sensors or systems and applied to all data prior to use by the vehicle control systems.

Abstract: A method and apparatus for correcting a physical slip and wear coefficient of a clutch comprising obtaining a torque difference according to a positional relation between an engine and the clutch; obtaining a correction weight value corresponding to an engine torque according to the torque difference; and correcting the physical slip and wear coefficient according to the correction weight value and a running-in state of the clutch. The method relates to obtaining a torque difference in real time by means of a positional relation between the engine and the clutch in a manner corresponding to the positional relation, obtaining a correction weight value corresponding to the engine torque according to the torque difference, and further correcting the physical slip and wear coefficient by combining the correction weight value and a running-in state of the clutch.

Abstract: An image-based road cone recognition method, apparatus, storage medium, and vehicle. Said method comprises: acquiring, during vehicle driving, an image of an object to be recognized; performing differential processing of the image, so as to acquire an image on which the differential processing has been performed, and performing, according to a preset threshold, ternary processing of the image on which the differential processing has been performed, so as to acquire a ternary image comprising forward boundary pixels and negative boundary pixels; acquiring, according to the forward boundary pixels and the negative boundary pixels, a forward straight line segment and a negative straight line segment which represent the trend of the boundaries of the object to be recognized; when position information of the forward and negative straight line segments matches boundary position information of a known road cone, determining that the object to be recognized is a road cone.

Abstract: Methods and systems for decision making in an autonomous vehicle (AV) are described. A probabilistic explorer reduces the breadth and depth of the potentially infinite actions being explored allowing for an accurate prediction on a future scene to a defined time horizon and an appropriate selection of a goal state anywhere within that time horizon. The probabilistic explorer uses a neural network (NN) to suggest best (probabilistically speaking) actions for the AV and scene values, and a modified Monte Carlo Tree Search to identify a sequence of actions, where exploration is guided by the NN. The probabilistic explorer processes the suggested actions and driving scene(s) to provide estimated trajectories of all scene actors and an estimated trajectory for the AV at every time step for every action explored. A virtual driving scene is generated, which is iteratively processed to determine a vehicle goal state or vehicle low-level control actions.