Abstract: A safety system includes: a memory; a processor connected to the memory and configured execute a safety program; a first communication unit configured to communicate data with one or more safety components via a first transmission line; and a second communication unit configured to communicate data with one or more safety components via a second transmission line. The second communication unit and the first communication unit independently of each other perform processing involved in communicating data. In the memory, a first data area that holds data communicated by the first communication unit and a second data area that holds data communicated by the second communication unit are arranged independently of each other.

Abstract: A method and system are provided for automatically portioning workpieces, such as food products, by simulating portioning the workpieces in accordance with the one or more desired shapes of the final piece(s) as a directly controlled physical characteristic (parameter/specification) as well as one or more resulting indirectly controlled physical characteristics (parameters/specifications). The desired shape(s) of the final piece(s) are defined by a plurality of manipulatable reference coordinates. A workpiece is scanned to obtain scanning information, then portioning of the workpiece is simulated in accordance with the desired shape(s) of the final piece(s) defined by the directly controlled reference coordinates, thereby to determine the one or more indirectly controlled physical characteristics of the one or more final pieces to be portioned from the workpiece.

Abstract: The invented equivalent-plane cross-coupling control method belongs to high-precision and high-efficiency intelligent multi-axis CNC (Computer Numerical Control) machining filed, featured a three-axis cross-coupling controller based on the equivalent plane which can be used for improvement of the three-dimensional contour-following accuracy. This method first find the foot point from the actual motion position to the desired contour using a tangential back stepping based Newton method. Then, establish an equivalent plane which containing the spatial contouring-error vector by passing through the actual motion position and the tangential line at the foot point. After that, estimate the three-dimensional contouring error in a scalar form, thus controlling the signed error using a PID based two-axis cross-coupling controller.

Abstract: Learning related to a device having a driving unit is performed more easily. An information processing device includes: a storage unit that stores a machining program for operating a motor of a machine tool, a robot, or an industrial machine; and a generation unit that generates a learning program for performing learning based on operating characteristics of the motor by extracting a partial machining program including a characteristic element from the machining program stored in the storage unit.

Abstract: According to some aspects of the invention, auxiliary axis measurement systems for determining three-dimensional coordinates of an object are provided as shown and described herein. According to some aspects of the invention, methods for operating auxiliary axis measurement systems for determining three-dimensional coordinates of an object are provided as shown and described herein.

Abstract: A cutting apparatus includes a chuck table that holds a workpiece, a processing unit that forms a processed groove in the workpiece, an imaging unit that images the workpiece, a display unit that displays a captured image of a processed groove imaged by the imaging unit, and a control unit that executes display control of a display screen of the display unit. The control unit causes a mark that indicates the latest processed groove based on the Y-coordinate of the latest processed groove to be displayed on the display unit while being superimposed on a captured image.

Abstract: A controller that performs, for one or more axes of a machine, position control by taking friction into consideration includes a data acquisition unit acquiring at least a position command and a position feedback and a compensation torque estimation unit estimating coefficients of a friction model used when the position control is performed, on the basis of a position deviation which is a difference between the position command and the position feedback.

Abstract: Embodiments of the invention include devices, systems and methods for operating a pressure wave detector. Embodiments include attaching a plurality of members and a ground plate to a substrate, and coupling the ground plate with the plurality of members attached to the substrate. Embodiments also include measuring a pressure wave by at least one of the plurality of members, converting the pressure wave into an electrical signal representing the pressure wave, and monitoring the pressure wave over a configurable period of time.

Abstract: A numerical control system includes an image processing device that performs image processing on images captured by an imaging device and a numerical controller. The numerical controller includes a program analysis unit and a storage unit that stores operation control information of the machine, the imaging device, and the image processing device in a format that can be read and written by the program analysis unit. The numerical control system includes a conversion unit that converts commands or the operation control information stored in the storage unit to image processing input items which are setting values of a format that can be recognized by the imaging device and the image processing device and converts image processing output items which are the results of the image processing from the image processing device to operation control information of a format that can be recognized by the program analysis unit.

Abstract: A control system includes a controller that controls machining of a workpiece, and a photographing device that photographs an image of the workpiece under machining operation. The controller generates a three-dimensional model of the workpiece under machining operation based on the acquired image, compares the generated three-dimensional model and a three-dimensional model generated by a machining simulation with each other, and determines a presence or absence of a machining defect based on a result of the comparison. When the machining defect is present and re-machining is possible, a setting is modified depending on a cause of the machining defect and additional machining is executed based on the modified setting.

Abstract: In order to realize stable quality control, provided is a quality control device (1) having an input device which receives data such as an operation condition of each device (21) to (26) in a production system (20) for producing a product; a calculation unit which assigns a value of the operation condition to a correlation formula calculated in advance and calculates a value derived from the correlation formula; and a determination unit which performs good or bad determination on a quality of a workpiece in each process, on the basis of a result calculated by the calculation unit. Further, when “bad” is determined as a result of the good or bad determination, the quality control device (1) calculates an appropriate value of the operation condition and sets the value to each device (21) to (26).

Abstract: A machine learning device performs machine learning related to optimization of a compensation value of a compensation generation unit with respect to a servo control device that includes a compensation generation unit configured to generate a compensation value to be added to a control command for controlling a servo motor and a limiting unit configured to limit the compensation value or the control command to which the compensation value is added so as to fall within a setting range. During a machine learning operation, when the compensation value or the control command is outside the setting range and the limiting unit limits the compensation value or the control command so as to fall within the setting range, the machine learning device applies the compensation value to the learning and continues with a new search to optimize the compensation value generated by the compensation generation unit.

Abstract: An object is to more appropriately perform settings in the setting of the control of a machine tool. A setting device includes: a first reception unit which receives the specification of a first setting value for at least one or more parameters on the control of a machine tool; a second reception unit which receives the specification of a second setting value for the parameter after the reception of the first setting value; a third reception unit which receives the specification of a selection condition for determining which one of the first setting value and the second setting value is selected; and a selection unit which selects, based on the selection condition whose specification is received by the third reception unit, any one of the first setting value and the second setting value as a setting value that is applied to the parameter.

Abstract: To provide a parameter determination support device and a program capable of simplifying determination of driving parameters upon driving a motor for which the slip constant is unknown.

Abstract: Some embodiments provide a program that retrieves a set of notifications describing failures that occurred on a set of monitored devices. The program further determines a set of topics based on the set of notifications. The program also determines failure modes associated with the set of topic from a plurality of failure modes defined for the set of monitored devices. The program further determines failure modes associated with the set of notifications based on the set of topics and the failure modes associated with the set of topics. The program also receives a particular notification that includes a particular set of words describing a failure that occurred on a particular monitored device in the set of monitored devices. The program further determines a failure mode associated with the particular notification based on the particular set of words and the determined failure modes associated with the set of notifications.

Abstract: A connection management device for establishing secured communications connections to an industrial automation system, wherein the device provides, in cases of a positive authorization verification outcome, access control information for establishing an encrypted communication connection between a first communication unit of a requesting user and a selected second communication unit, where the connection management device is formed by a server instance running on a firewall system, where data packets transmitted via an encrypted communications connection between the first communication unit of the requesting user and the selected second communication unit are encrypted for verification by the firewall system, based on specified security rules and, in cases of a successful verification, the data packets are forwarded encrypted to the first communication unit of the requesting user or to the selected second communication unit.

Abstract: A flay assembly for separating a workpiece from a manufacturing fixture has a horizontal beam assembly and a pair of vertical beam assemblies. The horizontal beam assembly includes a horizontal beam having a horizontal drive motor. Each vertical beam assembly includes a vertical beam operably engaged to the horizontal drive motor and has a workpiece attachment assembly operably engaged to a vertical drive motor. The workpiece attachment assembly has an attachment mechanism attachable to the workpiece. The horizontal drive motor and the vertical drive motors are operable in a manner to move the vertical beams away from each other along a horizontal drive axis while simultaneously moving each workpiece attachment assembly along a vertical drive axis to cause the attachment mechanisms to pull the workpiece side portions away from the manufacturing fixture while a center support of the horizontal beam maintains a workpiece crown in contact with the manufacturing fixture.

Abstract: Provided is a product manufacturing system including: a manufacture control apparatus configured to hold manufacturing data on a product; a virtual manufacturing apparatus configured to virtually manufacture the product by simulation, based on the manufacturing data on the product in the manufacture control apparatus; a physical manufacturing apparatus configured to physically manufacture the product based on the manufacturing data in the manufacture control apparatus; an abnormality determination unit configured to determine whether there is an abnormality in the virtual manufacture of the product by the virtual manufacturing apparatus. When it is determined there is no abnormality from the virtual manufacture of the product, the physical manufacturing apparatus physically manufactures the product.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for communicating between an operational asset and a backend network that include the actions of receiving first data from an operational asset through a first communication interface that is configured to communicate with an operational asset, and where the first data is formatted according to a first data format that is specific to the operational asset. Processing the first data according to an asset template to generate second data, where the second data includes the first data and being formatted according to a second data format that is specific to the backend network. Causing the second data to be transmitted to the backend network by a second communication interface that is configured to communicate with a backend network.

Abstract: A system and a method for scheduling an automation process controlling a machine. The system including a parser module for parsing calendar data, the calendar data comprising calendar events including clock data and task data. The system further including a clock module for monitoring time instances and triggering the parser module to parse the calendar data to retrieve the task data of a calendar event that is identified by clock data corresponding to a time instance; and a task module for processing the task data of the calendar event to obtain machine control data for execution on a machine.

Abstract: A method is presented for positioning a workpiece in a workstation. The method includes: transporting a workpiece into a workstation using an automatic guided vehicle, where the workpiece is supported by a workpiece fixture and the workpiece fixture is supported by the automatic guided vehicle; measuring spatial position of the workpiece fixture; removing the workpiece fixture from the automatic guided vehicle using one or more adjustable locators mounted on a frame of the workstation; calculating an adjustment to position of the workpiece fixture between the measured spatial position of the workpiece fixture and a nominal work position; moving the workpiece fixture suing the one or more adjustable locators to the nominal work position according to calculated adjustment; performing an operation on the workpiece while the workpiece fixture remains in the nominal work position; and returning the workpiece fixture to the automatic guided vehicle.

Abstract: A method for operating a component of predetermined geometry ? that is cyclically loaded during operation, wherein a probability of failure P is determined for the component taking account of distributions of failure times, which are caused by deviations in material properties, the component is operated depending on the determined probability of failure P, wherein at least one maintenance time is set for the component, in particular depending on the determined probability of failure P.

Abstract: Sensor data is received from a plurality of sensors contained in an electrical submersible pump (ESP) deployed in a well hole. An early indication of an ESP failure that is imminent is determined in real time using a pattern recognition methodology based on the sensor data and a pattern detection model that correlates historical ESP failures with historical sensor readings. A notification of the imminence of the ESP failure is provided.

Abstract: An embodiment includes an apparatus that supports a user to make planning decisions of fuel efficiency of an aircraft versus time of arrival of the aircraft along a flight path. An embodiment of the apparatus accepts input data related to the aircraft. The input data may include (i) flight plan data that includes a flight path of the aircraft, (ii) state of the aircraft along the flight path, (iii) environmental data, and (iv) an aircraft performance model of the aircraft. The apparatus calculates aircraft performance and an objective function for a range of altitudes and speeds as a function of the input data. The apparatus causes a user interface to display aircraft performance contour boundaries and a vertical routing path that meets the objective function to provide graphical representations to support a user's planning decisions.

Abstract: This disclosure relates to a communication control technology field and provides a control method, a device, and a remote control for a VR apparatus. The remote control may establish a communication connection to the VR apparatus, and may determine a virtual control in a mapping association with the function button after receiving a first operation on a function button configured for the remote control by a user, the virtual control being located on a display interface of the VR apparatus. The determined virtual control may be operated according to the first operation. Through the foregoing method, the user may control display of the VR apparatus by operating the remote control, thereby simplifying user operations and improving user experience.

Abstract: In a remote-operation apparatus, a communication circuit receives, from an autonomous vehicle via a network, detection data indicating circumstances of an area around the autonomous vehicle. A display displays an image of the area around the autonomous vehicle generated based on the received detection data. The communication circuit transmits, via the network to the autonomous vehicle that is being remotely operated, a control command including an amount of operation obtained by correcting, based on characteristics of the autonomous vehicle, an amount of operation applied to an operation accepter by a remote operator.

Abstract: An apparatus for providing a safety strategy in a vehicle is provided. The apparatus includes a sensor configured to obtain sensing information about the outside of the vehicle, a memory storing road information, an output device outputting a notification, and a control circuit configured to be electrically connected with the sensor, the memory, and the output device. The control circuit recognizes an event associated with a critical situation of the vehicle based on at least a portion of the sensing information or the road information, while performing autonomous control, maintains the autonomous control, outputs a transition demand using the output device, and controls the vehicle according to a predetermined strategy for the critical situation, when the event is a planned event, and immediately outputs the transition demand and controls the vehicle according to the predetermined strategy, when the event is an unplanned event.

Abstract: An apparatus for providing a safety strategy in a vehicle is provided. The apparatus includes a sensor configured to obtain information about a driver of the vehicle, an output device configured to output a notification to the driver, and a control circuit configured to be electrically connected with the sensor and the output device. The control circuit is configured to recognize a state of the driver based on the information obtained by the sensor, set a route toward a safety zone, when the state of the driver meets a specified condition, and control the vehicle to change a lane where the vehicle is traveling to a lane adjacent to the safety zone.

Abstract: An apparatus for controlling to enable an autonomous system in a vehicle is provided. The apparatus includes a sensor, an input device configured to receive an input from a driver of the vehicle, an output device configured to output a notification in the vehicle, and a control circuit configured to be electrically connected with the sensor, the input device, and the output device. The control circuit is configured to activate an autonomous control in response to an input of the driver to the input device, detect a critical situation of the vehicle using the sensor, output a notification to transfer a control authority using the output device in response to the detected critical situation, and automatically reactivate the autonomous control when the critical situation is solved after temporarily releasing the autonomous control, when the critical situation corresponds to a critical situation of a specified type.

Abstract: An apparatus for managing control authority transition in a vehicle is provided. The apparatus includes a steering device, an acceleration device, a deceleration device, a sensor configured to sense information about a driver of the vehicle, and a control circuit electrically connected with the steering device, the acceleration device, the deceleration device, and the sensor. The control circuit is configured to obtain state information about the driver using the sensor when performing an autonomous control, to receive a control input by the driver to at least one of the steering device, the acceleration device, or the deceleration device, to determine whether to transfer a control authority based on the state information and a reliability of the control input, and to transfer the control authority to the driver when the control authority is determined to transfer.

Abstract: The present application generally relates to a method and apparatus for generating an action policy for controlling an autonomous vehicle. In particular, the method is operative to receive an input indicative of a training event, segmenting the driving episode into a plurality of time steps, generate a parse tree in response to each time step, and generate a most probable parse tree from a combination of the generated parse trees.

Abstract: An autonomous vehicle for transporting an item from a first location to a second location includes a vehicle frame having a first set of three guide wheels and a second set of three guide wheels. A pair of road wheels are rotatably engaged with each of the first and second set of three guide wheels. A pair of electric motors are mounted to the frame and drive the road wheels. A compartment is disposed in the interior of the vehicle. Sensors are mounted on the frame for collecting date for determining an environment in which the vehicle is operating. A control module processes data received by the sensors and controls the electric motors to move the vehicle in the environment according to instructions sent by a remote source. A user interface is in communication with the control module for providing a means to communicate with the vehicle.

Abstract: An autonomous system for transporting an item from a first location to a second location includes an autonomous vehicle and a trailer. The autonomous vehicle includes a compartment, a vehicle sensor, a vehicle drive mechanism, a vehicle power source, and a vehicle control module for controlling the vehicle drive mechanism. The trailer includes a hitch for connecting the trailer to the autonomous vehicle, an electrical system, a trailer sensor in communication with the electrical system, a trailer power source in communication with the electrical system, a storage space, and a mechanism for autonomously transferring the item from the storage space into the compartment of the autonomous vehicle. The autonomous vehicle and trailer are configured to transport the item to the first location, the trailer is configured to transfer the item to the autonomous vehicle, and the autonomous vehicle is configured to transport the item to the second location.

Abstract: Achieving safety and natural automatic driving needs a control platform using intelligence (such as learning function and artificial intelligence), but it is difficult to ensure operations suited for the behavior of a vehicle by the output of intelligence. An automatic driving device according to the present invention includes a control program for inputting outside information and vehicle information, and outputting a target control value for a vehicle. The control program has a first program for generating a first target control amount on the basis of a dynamically changing algorithm (which outputs operations based on learning function or artificial intelligence), and a second program for generating a second target control amount on the basis of a prescribed algorithm (which outputs operations according to traffic rules or driving morals).

Abstract: One embodiment describes a control system in an automation system including a first portion located at a first vehicle, which includes a first autonomous module that autonomously controls operation of the first vehicle to perform operations in a first area based at least in part on a first target operation result while the first portion is in an autonomous mode; and a second portion located at a second vehicle, in which the second portion includes a second autonomous module that autonomously controls operation of the second vehicle to perform operations in a second area based at least in part on a second target operation result while the second portion is in the autonomous mode and a first command module that determines the first target operation result and the second target operation result based at least in part on a global plan that indicates a total target operation result.

Abstract: One embodiment describes a control system in an automation system including a first portion located at a first vehicle, which includes a first autonomous module that autonomously controls operation of the first vehicle to perform operations in a first area based at least in part on a first target operation result while the first portion is in an autonomous mode; and a second portion located at a second vehicle, in which the second portion includes a second autonomous module that autonomously controls operation of the second vehicle to perform operations in a second area based at least in part on a second target operation result while the second portion is in the autonomous mode and a first command module that determines the first target operation result and the second target operation result based at least in part on a global plan that indicates a total target operation result.

Abstract: A method for controlling an unmanned aerial vehicle (“UAV”) includes detecting a first operation on an interactive interface. The method also includes determining a flight mode of the UAV triggered by the first operation, and controlling the UAV to fly in the flight mode.

Abstract: Described herein is a LIDAR device that may include a transmitter, first and second receivers, and a rotating platform. The transmitter may be configured to emit light having a vertical beam width. The first receiver may be configured to detect light at a first resolution while scanning the environment with a first FOV and the second receiver may be configured to detect light at a second resolution while scanning the environment with a second FOV. In this arrangement, the first resolution may be higher than the second resolution, the first FOV may be at least partially different from the second FOV, and the vertical beam width may encompass at least a vertical extent of the first and second FOVs. Further, the rotating platform may be configured to rotate about an axis such that the transmitter and first and second receivers each move based on the rotation.

Abstract: A positional sensor detects a current position and a current bearing of a boat body and outputs position information indicating the current position and the current bearing. A controller receives the position information. The controller determines a first target position of the boat body and a target bearing in the first target position. The controller calculates a bearing difference between the current bearing and the target bearing. The controller determines an offset amount of the first target position in response to the bearing difference or an outside disturbance. The controller determines a position spaced away by the offset amount from the first target position on a side toward the current position as a second target position. The controller generates an instruction signal to control a propulsion device so as to cause the boat body to arrive at the second target position.

Abstract: An ADV may determine whether there is preexisting map data for an environment or geographical area/location where the ADV is located/travelling. If there is no preexisting data, the ADV may generate map data based on sensor data obtained from one or more sensors of the ADV. The ADV may determine a path for the ADV based on the generated map data. If there is preexisting map data, the ADV may determine a path for the ADV based on the preexisting map data.

Abstract: A vehicle control system includes: an inputter that accepts an occupant's operation of a host vehicle; an autonomous driving controller that executes an autonomous driving mode for controlling steering and acceleration/deceleration of the host vehicle in a case where a predetermined operation is accepted by the inputter; and a mode controller that prohibits the autonomous driving mode from being started by the autonomous driving controller in a case where the host vehicle has reached a predetermined section including at least one of a divergence point, a merging point, and a destination.

Abstract: In one embodiment, sensor data are collected from one or more sensors mounted on an autonomous driving vehicle (ADV) while the ADV is moving within a region of interest (ROI) that includes a number of obstacles. The collected sensor data are operated on to obtain obstacle data associated with the obstacles, location data, and a number of timestamps that correspond to the obstacle data and the location data. For each of the timestamps, positions of the obstacles are mapped to some of the obstacle data that correspond to the timestamp based on the location data, thereby generating mapped information of the obstacles. The mapped information is automatically labelled to generate labelled data, where the labelled data is utilized to subsequently train a machine learning algorithm to recognize obstacles during autonomous driving of an ADV.

Abstract: A new cost design is disclosed for evaluating candidate path curves for navigating an autonomous driving vehicle (ADV) through a segment of a route which may include an obstacle. Each point on each candidate path curve has a plurality of attributes having logical values and an associated priority of evaluation, and at least one numeric attribute having an associated priority of evaluation. A cost for each path curve is determined using the attributes and priorities, and a least cost path curve is selected using the attributes and priorities. By comparing attribute values in accordance with priority, and utilizing logical values, the efficiency of determining path curve cost and selecting a least cost path curve is substantially improved.

Abstract: According to some embodiments, a system operates an ADV. In one embodiment, the system perceives a driving environment surrounding the ADV based on sensor data obtained from a plurality of sensors, including perceiving a moving obstacle that is moving relative to the ADV. The system projects the moving obstacle as a figure onto a station-time (ST) coordinate system, wherein the ST coordinate system indicates a distance between the figure and a reference point at different points in time. And the system, for each of a plurality of predetermined processing time intervals, determines two points of the figure in the ST coordinate system to represent a shape of the figure, wherein the shape of the figure is utilized to plan a trajectory to drive the ADV to avoid colliding with the moving obstacle.

Abstract: A method for full-stack verification of autonomous agents includes training a neural network to learn a noise model associated with an object detection module of an autonomous agent system of an autonomous vehicle. The method also includes replacing the object detection module of the autonomous agent system with the neural network and a sensory input of the object detection module with ground truth information to apply a surrogate function to the ground truth information. The method further includes verifying the autonomous agent system including the trained neural network to apply the surrogate function in response to the ground truth information to simulate sensor information data to at least a planner module of the autonomous agent system. The method also includes controlling a behavior of the autonomous vehicle using the verified autonomous agent system including the object detection module.

Abstract: According to one embodiment, an obstacle is predicted to move from a starting point to an end point based on perception data perceiving a driving environment surrounding an ADV that is driving within a lane. A longitudinal movement trajectory from the starting point to the end point is generated in view of a shape of the lane. A lateral movement trajectory from the starting point to the end point is generated, including optimizing a shape of the lateral movement trajectory using a first polynomial function. The longitudinal movement trajectory and the lateral movement trajectory are then combined to form a final predicted trajectory that predicts how the obstacle is to move. A path is generated to control the ADV to move in view of the predicted trajectory of the obstacle, for example, to avoid the collision with the obstacle.

Abstract: In one embodiment, a system generates a plurality of trajectory candidates for an autonomous driving vehicle (ADV) from a starting point to an end point of a particular driving scenario. The system generates a reference trajectory corresponding to the driving scenario based on a current state of the ADV associated with the starting point and an end state of the ADV associated with the end point, where the reference trajectory is associated with an objective. For each of the trajectory candidates, the system compares the trajectory candidate with the reference trajectory to generate an objective cost representing a similarity between the trajectory candidate and the reference trajectory. The system selects one of the trajectory candidates as a target trajectory for driving the ADV based on objective costs of the trajectory candidates.

Abstract: A sensor aggregation framework for autonomous driving vehicles is disclosed. In one embodiment, sensor data is collected from one or more sensors mounted on an autonomous driving vehicle (ADV) while the ADV is moving within a region of interest (ROI) that includes a number of obstacles. The sensor data includes obstacle information of the obstacles and vehicle data of the ADV. Each of the vehicle data is timestamped with a current time at which the vehicle data is captured to generate a number of timestamps that correspond to the vehicle data. The obstacle information, the vehicle data, and the corresponding timestamps are aggregated into training data. The training data is used to train a set of parameters that is subsequently utilized to predict at least in part future obstacle behaviors and vehicle movement of the ADV.

Abstract: There is provided an information processing apparatus and information processing method that enables a user to easily teach an action with regard to action learning. A touchscreen outputs unknown state element information that indicates an unknown state element, and teaching request information that requests teaching of an action corresponding to an ambient state, in a case where the ambient state includes the unknown state element. For example, it is possible to apply the present disclosure to a cleaner robot or the like that controls actions on the basis of an action model for finding a probability P (a|s) that the cleaner robot performs an action a in a state s.

Abstract: In one embodiment, in response to detecting an obstacle based on a driving environment surrounding an autonomous driving vehicle (ADV), a system projects the obstacle onto a station-time (ST) graph, where the ST graph indicates a location of the obstacle relative to a current location of the ADV at different points in time. The system determines a first set of end points that are not overlapped with the obstacle within the ST graph, wherein each of the end points in the first set represents a possible end condition. The system generates a first set of trajectory candidates between a starting point representing the current location of the ADV and the end points of the first set based on the ST graph. The system selects one of the trajectory candidates in the first set using a predetermined trajectory selection algorithm to control the ADV in view of the obstacle.