-
公开(公告)号:US20190243372A1
公开(公告)日:2019-08-08
申请号:US16149006
申请日:2018-10-01
申请人: drive.ai Inc.
发明人: Brody Huval , James Patrick Marion
IPC分类号: G05D1/02 , G06K9/00 , B60W50/04 , B60W30/095 , G08G1/16
CPC分类号: G05D1/0221 , B60W30/0953 , B60W50/045 , B60W2050/0031 , G05D1/0274 , G05D2201/0213 , G06K9/00798 , G08G1/167
摘要: One variation of a method for calculating nominal paths for lanes within a geographic region includes: serving a digital frame of a road segment to an annotation portal; at the annotation portal, receiving insertion of a lane marker label, for a lane marker represented in the digital frame, over the digital frame; calculating a nominal path over the road segment and defining a virtual simulator environment for the road segment based on the lane marker label; during a simulation, traversing the virtual road vehicle along the nominal path within the virtual simulator environment and scanning the virtual simulator environment for collisions between the virtual road vehicle and virtual objects within the virtual simulator environment; and, in response to absence of a collision between the virtual road vehicle and virtual objects in the virtual simulator environment, updating a navigation map for the road segment with the nominal path.
-
公开(公告)号:US20190220016A1
公开(公告)日:2019-07-18
申请号:US16058430
申请日:2018-08-08
发明人: Michael Lee Phillips , Don Burnette , Kalin Vasilev Gochev , Somchaya Liemhetcharat , Harishma Dayanidhi , Eric Michael Perko , Eric Lloyd Wilkinson , Colin Jeffrey Green , Wei Liu , Anthony Joseph Stentz , David McAllister Bradley , Samuel Philip Marden
CPC分类号: G05D1/0088 , B60W30/0953 , B60W30/0956 , B60W30/12 , B60W30/16 , B60W30/18163 , B60W50/0097 , B60W2550/10 , G01C21/20 , G01C21/3453 , G05D1/0212 , G05D1/0214 , G05D1/0221 , G05D1/0223 , G05D2201/0213
摘要: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a constraint solver determines a multi-dimensional space for each phase of a plurality of different phases of a lane change maneuver. For each different phase, objects of interest interacting with first and second lanes of the nominal path can be determined and constraints can be respectively generated. A portion of the multi-dimensional space including corresponding constraints that applies to a respective timeframe associated with each phase can be determined. The respective portions of the multi-dimensional space including corresponding constraints for each phase of the plurality of different phases of the lane change maneuver can be combined to generate a multiplexed space through which a low-cost trajectory path can be determined.
-
公开(公告)号:US20190205765A1
公开(公告)日:2019-07-04
申请号:US15858505
申请日:2017-12-29
发明人: Antonino Mondello , Alberto Troia
CPC分类号: G06N3/088 , G05D1/0088 , G05D1/0221 , G05D1/0223 , G05D1/024 , G05D1/0242 , G05D1/0246 , G05D1/0255 , G05D1/0257 , G05D1/0287 , G05D2201/0213 , G06N3/0454
摘要: A vehicle having the first ANN model initially installed therein to generate outputs from inputs generated by one or more sensors of the vehicle. The vehicle selects an input based on an output generated from the input using the first ANN model. The vehicle has a module to incrementally train the first ANN model through unsupervised machine learning from sensor data that includes the input selected by the vehicle. Optionally, the sensor data used for the unsupervised learning may further include inputs selected by other vehicles in a population. Sensor inputs selected by vehicles are transmitted to a centralized computer server, which trains the first ANN model through supervised machine learning from sensor received inputs from the vehicles in the population and generates a second ANN model as replacement of the first ANN model previously incrementally improved via unsupervised machine learning in the population.
-
公开(公告)号:US20190204842A1
公开(公告)日:2019-07-04
申请号:US15859857
申请日:2018-01-02
CPC分类号: G05D1/0221 , G05D1/0088 , G06N3/04 , G06N3/08
摘要: A vehicle, system and method of autonomous navigation of the vehicle. A reference trajectory for navigating a training traffic scenario along a road section is received at a processor of the vehicle. The processor determines a coefficient for a cost function associated with a candidate trajectory that simulates the reference trajectory. The determined coefficient is provided to a neural network to train the neural network. The trained neural network generates a navigation trajectory for navigating the vehicle using a cost coefficient determined by the neural network. The vehicle is navigated along the road section using the navigation trajectory.
-
公开(公告)号:US20190196484A1
公开(公告)日:2019-06-27
申请号:US16163315
申请日:2018-10-17
CPC分类号: G05D1/0221 , F02D2200/501 , F02D2200/701 , F02D2200/702 , G01C21/3602 , G01S5/16 , G05D1/0088 , G05D1/0223 , G05D1/0246 , G05D1/0274 , G05D1/0278 , G05D2201/0213 , G06K9/00791 , G06K9/6202 , G06K9/6257 , G06K2009/6213 , G06N20/00
摘要: A system for controlling a self-driving vehicle controllable on the basis of direction values and acceleration values, comprising a navigation module, a control module and a camera wherein the navigation module is configured to plan a route, on the basis of a received destination, via a series of previously received navigation points and to convert the route into navigation instructions and to supply the latter at a navigation point to the control module, wherein the control module is configured to receive navigation instructions and to receive live camera images and can compare the latter with previously stored camera images annotated with at least navigation points and to convert the navigation instructions and the camera images into direction values and acceleration values for the controllable self-driving vehicle and to determine that a navigation point has been reached if a live camera image has a predefined degree of correspondence with a camera image annotated with a navigation point, and to report to the navigation module that the navigation point has been reached.
-
6.
公开(公告)号:US20190187705A1
公开(公告)日:2019-06-20
申请号:US15856113
申请日:2017-12-28
申请人: PLUSAI CORP
CPC分类号: G05D1/0088 , B60W40/09 , B60W2040/0872 , B60W2040/089 , B60W2540/30 , G01C21/3484 , G05D1/0217 , G05D1/0221 , G06N7/005
摘要: The present teaching relates to method, system, medium, and implementation of route planning for an autonomous driving vehicle. A source location and a destination location are first obtained, where the destination location is where the autonomous driving vehicle is to drive to. One or more available routes between the source location and the destination location are identified. A self-aware capability model is instantiated with respect to the one or more available routes and is predictive of the operational capability of the autonomous driving vehicle with respect to each of the one or more available routes. The preference of a passenger present in the autonomous driving vehicle is determined in terms of a route to take for the autonomous vehicle to drive to the destination location. Based on the self-aware capability model and the preference of the passenger, a planned route to the destination location is then automatically selected for the autonomous driving vehicle.
-
7.
公开(公告)号:US20190185013A1
公开(公告)日:2019-06-20
申请号:US15845423
申请日:2017-12-18
申请人: PLUSAI CORP
发明人: Mianwei Zhou , Hao Zheng , David Wanqian Liu
CPC分类号: G05D1/0088 , B60W30/18009 , B60W40/09 , B60W2540/30 , G05D1/0221 , G05D2201/0213 , G06N5/04 , G06N20/00
摘要: The present teaching relates to method, system, medium, and implementation of human-like vehicle control for an autonomous vehicle. Recorded human driving data are first received, which include vehicle state data, vehicle control data, and environment data. For each piece of recorded human driving data, a vehicle kinematic model based vehicle control signal is generated in accordance with a vehicle kinematic model based on a corresponding vehicle state and vehicle control data of the piece of recorded human driving data. A human-like vehicle control model is obtained, via machine learning, based on the recorded human driving data as well as the vehicle kinematic model based vehicle control signal generated based on vehicle kinematic model. Such derived human-like vehicle control model is to be used to generate a human-like vehicle control signal with respect to a target motion of an autonomous vehicle to achieve human-like vehicle control behavior.
-
公开(公告)号:US10324467B1
公开(公告)日:2019-06-18
申请号:US15991769
申请日:2018-05-29
发明人: Kenneth A. Abeloe
CPC分类号: G05D1/0088 , B60Q5/006 , B60R11/0217 , B60R11/04 , B60R2300/102 , B60R2300/103 , B60W30/0956 , G05D1/0221 , G05D2201/0213 , G06N3/0454 , G06N3/08 , G06N5/046 , G06N20/00 , G10L13/043 , G10L13/047 , G10L15/16 , G10L15/22 , G10L2015/223
摘要: Systems and methods for automatically self-correcting or correcting in real-time one or more neural networks after detecting a triggering event, or breaching boundary conditions are provided. Such a triggering event may indicate incorrect output signal or data being generated by the one or more neural networks. In particular, machine controllers of the invention limit the operations of neural networks to be within boundary conditions. Autonomous machines of the invention can be self-corrected after a breach of a boundary condition is detected. Autonomous land vehicles of the invention are capable of determining the timing of automatic transition to the manual control from automated driving mode. The controller of the invention filters and saves input-output data sets that fall within boundary conditions for later training of neural networks. The controllers of the invention include security architectures to prevent damages from virus attacks or system malfunctions.
-
9.
公开(公告)号:US20190004529A1
公开(公告)日:2019-01-03
申请号:US15808064
申请日:2017-11-09
发明人: Seong Su Im , Tae Seok Lee , Seok Youl Yang
CPC分类号: G05D1/0223 , G05D1/0061 , G05D1/0088 , G05D1/0221 , G05D1/0231 , G05D2201/0213 , G08G1/166 , G08G1/167
摘要: A method of controlling lane change of an autonomous vehicle is provided. The method includes determining a type of a command for lane change by an autonomous driving logic of an electronic control unit (ECU) in response to the command for lane change being generated. When the command for lane change is not a specific command for lane change, attributes of each of at least one region included in a change target region is determined using information regarding the change target region. The attributes of each of the at least one region are corrected using information regarding a lane in which the autonomous vehicle is driven and a lane change region is determined from the at least one region based on the corrected attributes of each of the at least one region.
-
公开(公告)号:US20180348775A1
公开(公告)日:2018-12-06
申请号:US15615378
申请日:2017-06-06
申请人: Baidu USA LLC
发明人: Xiang YU , Qi KONG , Qi LUO , Fan ZHU , Sen HU , Guang YANG , Jingao WANG
IPC分类号: G05D1/02
CPC分类号: G05D1/0221 , B60W30/14 , B60W40/10 , B60W2050/0028 , G05D2201/0213
摘要: State of an autonomous driving vehicle (ADV) is measured and stored for a location and speed of the ADV. Later, the state of the ADV is measured for the location and speed corresponding to a previously stored state of the ADV at the same location and speed. Fields of the measured stored states of the ADV are compared. If one or more differences between the measured and stored ADV states exceeds a threshold, then one or more control input parameters of the ADV is adjusted, such as steering, braking, or throttle. Differences may be attributable to road conditions or to state of servicing of the ADV. Differences between measured and stored states of the ADV can be passed to a service module. Service module can access crowd sourced data to determine whether one or more control input parameters for a driving state of one or more ADVs should be updated.
-
-
-
-
-
-
-
-
-