WO2022105369A1

WO2022105369A1 - Control method and apparatus of autonomous vehicle

Info

Publication number: WO2022105369A1
Application number: PCT/CN2021/116751
Authority: WO
Inventors: Yao Li; Dixiao CUI; Tong Wang
Original assignee: Suzhou Zhijia Science & Technologies Co., Ltd.
Priority date: 2020-11-20
Filing date: 2021-09-06
Publication date: 2022-05-27
Also published as: CN112373487A; CN112373487B

Abstract

The present invention provides a control method, a control apparatus and an autonomous vehicle, the method comprises: obtaining an initial position of the vehicle; determining a terminal position of the vehicle; obtaining a motion state of an obstacle around the vehicle, and determining an obstacle avoidance position for the vehicle according to the motion state of the obstacle around the vehicle; obtaining a traffic rule restriction of a road segment where the vehicle is located; determining a power control value of the vehicle by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints of the optimization comprise the obstacle avoidance position and the traffic rule restriction; and transmitting the power control value to a control system of the vehicle to control movement of the vehicle.

Description

CONTROL METHOD AND APPARATUS OF AUTONOMOUS VEHICLE

TECHNICAL FIELD

The disclosure relates to the technical field of automated driving, and in particular to a control method and apparatus of an autonomous vehicle.

BACKGROUND

An automated driving technology can automatically and safely control motor vehicles without any active human operation by relying on collaboration among artificial intelligence, visual computing, radar, monitoring apparatuses, navigation and positioning systems, etc. The current automated driving focuses on function implementation of the automated driving, but does not pay attention to the improvement of fuel economy. However, fuel consumption is crucial for autonomous vehicles, especially but not limited to autonomous vehicles deployed in fleets (such as automated-driving taxis, automated trucks and automated-driving logistics vehicles) .

At present, in the methods for improving the fuel economy of an autonomous vehicles, the engine, the transmission, etc. are considered. The fuel economy is improved by improving the efficiency of the engine and the shift schedule of the transmission. However, in these methods, usually only the sensing device information of the vehicles is considered, while other related information is not considered.

SUMMARY OF THE INVENTION

Embodiments of the specification provide a control method and apparatus of an autonomous vehicle, which may improve the efficiency of energy utilization and the travelling efficiency of autonomous vehicles.

One aspect of the present disclosure provides a method of controlling an autonomous vehicle, the method comprising:

obtaining an initial position of the vehicle, the initial position being a position of the vehicle at current time;

determining a terminal position of the vehicle, the terminal position being an expected arrival position of the vehicle;

obtaining a motion state of an obstacle around the vehicle, and determining an obstacle avoidance position for the vehicle according to the motion state of the obstacle around the vehicle;

obtaining a traffic rule restriction of a road segment where the vehicle is located;

determining a power control value of the vehicle by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints of the optimization comprise the obstacle avoidance position and the traffic rule restriction; and

transmitting the power control value to a control system of the vehicle to control motion of the vehicle, such that the travelling cost of the vehicle between the initial position and the terminal position is minimized.

In an embodiment of the specification, the travelling cost of the vehicle in the cost function comprises energy consumption, travelling time and/or a weighted combination of the energy consumption and the travelling time.

In an embodiment of the specification, the cost function is expressed as:

where min represents minimization, x (t) is a position variable of the vehicle, u (t) is a power controlled variable, tf is a predicted duration of travelling, q (u, n _e) is a preset energy consumption function, u is a power control value, n _e is an engine speed, w _f is an energy consumption weight, w _t is a travelling time weight, and t is time.

In an embodiment of the specification, the constraints on the optimization further comprise a kinematic constraint of the vehicle, wherein

the kinematic constraint comprises an initial speed and a terminal speed of the vehicle, the initial speed being a speed of the vehicle at the initial position, and the terminal speed being an expected speed of the vehicle at the terminal position.

In an embodiment of the specification, the terminal position is determined by an onboard sensor.

In an embodiment of the specification, the terminal speed is determined by:

taking a front obstacle speed as the terminal speed of the vehicle when the front obstacle speed does not exceed an upper speed limit of a front road segment; or

taking an upper speed limit of a front road segment as the terminal speed of the vehicle when a front obstacle speed exceeds the upper speed limit of the front road segment.

In an embodiment of the specification, the front obstacle speed is an average speed of one or more vehicles in front of the vehicle.

In an embodiment of the specification, the power control value is an accelerator pedal percentage.

In an embodiment of the specification, the cost function is calculated by using a direct collocation method to determine the power control value of the vehicle.

In another aspect, an embodiment of the specification further provides a control apparatus of an autonomous vehicle, the control apparatus comprising:

an initial position obtaining module configured to obtain an initial position of the vehicle, the initial position being a position of the vehicle at current time;

a terminal position obtaining module configured to determine a terminal position of the vehicle, the terminal position being an expected arrival position of the vehicle;

an obstacle avoidance position determination module configured to obtain a motion state of an obstacle around the vehicle, and determine an obstacle avoidance position of the vehicle according to the motion state of the obstacle around the vehicle;

a traffic rule obtaining module configured to obtain a traffic rule restriction of a road segment where the vehicle is located;

a power control value determination module configured to determine a power control value of the vehicle by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints on the optimization comprise the obstacle avoidance position and the traffic rule restriction; and

a power control value transmission module configured to transmit the power control value to a control system of the vehicle to control motion of the vehicle, such that the travelling cost of the vehicle between the initial position and the terminal position is minimized.

In an embodiment of the specification, the cost function comprises energy consumption, travelling time and/or a weighted combination of the energy consumption and the travelling time.

In an embodiment of the specification, the cost function is expressed as:

where min represents minimization, x (t) is a position variable of the vehicle, u (t) is a power controlled variable, tf is predicted duration of travelling, q (u, n _e) is a preset energy consumption function, u is a power control value, n _e is an engine speed, w _f is an energy consumption weight, w _t is a travelling time weight, and t is time.

In an embodiment of the specification, the terminal speed is determined in the following manner:

In another aspect, an embodiment of the specification further provides an electronic device, the electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, implements the control method.

In another aspect, an embodiment of the specification further provides a computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above control method.

In another aspect, an embodiment of the specification further provides an autonomous vehicle, wherein the autonomous vehicle is equipped with the above electronic device.

It can be seen from the technical solution provided by the above embodiments of the specification that in the embodiments of the specification, when the power control value of the vehicle is determined by using the cost function, such that a cost of the vehicle between the initial position and the terminal position is minimized. Constraints of the cost function used not only consider the obstacle (s) around the vehicle, but also the initial position of the vehicle (that is, a position of the vehicle at current time) , the terminal position (that is, an expected arrival position of the vehicle) , the traffic rule restriction, and may also consider other limiting factors. Therefore, when the vehicle is controlled to travel according to the power control value, the travelling efficiency of the vehicle may be improved (e.g. using less time for travelling between the initial position and the terminal position) . Furthermore, while as well as avoiding collision with the surrounding obstacle, unnecessary braking or acceleration can be reduced or avoided, thereby improving the efficiency of energy utilization of the autonomous vehicle.

BRIEF DESCRIPTION OF THE DRAWINGS

To illustrate the technical solutions in the embodiments of the specification or in the prior art more clearly, the following briefly describes the accompanying drawings required in descriptions of the embodiments or in the prior art. In the accompanying drawings:

Fig. 1 is a flowchart of a control method of an autonomous vehicle according to an embodiment;

Fig. 2 is a schematic diagram of fuel consumption characteristics of an engine according to an embodiment;

Fig. 3 is a schematic diagram of dynamic force analysis of a vehicle according to an embodiment;

Fig. 4 is a schematic diagram of a constraint of an obstacle avoidance position according to an embodiment;

Fig. 5 is a schematic diagram of a constraint of a road speed limit according to an embodiment;

Fig. 6 is a structural block diagram of a control apparatus of an autonomous vehicle according to an embodiment; and

Fig. 7 is a structural block diagram of an electronic device according to an embodiment.

[Description of reference numerals]

20. fuel consumption characteristic curve of an engine;

30. vehicle;

S11. upper limit position line of obstacle avoidance predicted at a moment t ₀;

S12. lower limit position line of obstacle avoidance predicted at the moment t ₀;

S21. upper limit position line of obstacle avoidance predicted at a moment t ₁;

S22. lower limit position line of obstacle avoidance predicted at the moment t ₁;

P1. current predicted duration of travelling predicted at the moment t ₀;

P2. next predicted duration of travelling predicted at the moment t ₁;

51. upper speed limit of a front road segment of the vehicle;

52. speed curve corresponding to a predicted power control value;

53. lower speed limit of the front road segment of the present vehicle;

61. obstacle avoidance position determination module;

62. initial state obtaining module;

63. terminal state obtaining module;

64. traffic rule obtaining module;

65. power control value determination module;

66. power control value transmission module;

702. electronic device;

704. processor;

706. memory;

708. driving mechanism;

710. input/output module;

712. input device;

714. output device;

716. display device;

718. graphical user interface;

720. network interface;

722. communication link; and

724. communication bus.

DETAILED DESCRIPTION OF EMBODIMENTS

To make the technical solutions in the specification to be better understood by a person skilled in the art, the following clearly and completely describes the technical solutions in the embodiments of the specification with reference to the accompanying drawings in the embodiments of the specification. Apparently, the described embodiments are merely some rather than all of the embodiments of the specification. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the specification without creative efforts shall fall within the protection scope of the specification.

For ease of description, some embodiments of the specification may use spatial relative terms such as “front” , “behind” , and “lateral” to describe a relation between one element or component and another element or component (or some other elements or components) as shown in the accompanying drawings of the embodiments. It should be understood that the spatial relative terms are intended to comprise different orientations of the apparatus in use or operation in addition to the orientations described in the accompanying drawings.

The embodiments of the specification mainly relate to a speed planning technology of an autonomous vehicle, aiming to control the autonomous vehicle to achieve energy saving and efficient travelling on the premise of safe travelling (for example, without collision) by reasonable speed planning.

A control method of an autonomous vehicle provided by an embodiment of the specification may be executed by an automated driving system configured in the autonomous vehicle. As shown in Fig. 1, in some embodiments, the control method of the autonomous vehicle may comprise:

S101. an initial position of the vehicle is obtained, the initial position being a position of the vehicle at current time.

S102. a terminal position of the vehicle is determined, the terminal position being an expected arrival position of the vehicle.

S103. a motion state of an obstacle around the vehicle is obtained, and an obstacle avoidance position of the vehicle is determined according to the motion state of the obstacle around the vehicle.

S104. a traffic rule restriction of a road segment where the vehicle is located is obtained.

S105. a power control value of the vehicle is determined by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints on the optimization comprise the obstacle avoidance position and the traffic rule restriction.

S106. the power control value is transmitted to a control system of the vehicle to control motion of the vehicle, such that the travelling cost of the vehicle between the initial position and the terminal position is minimized.

In the above embodiment of the specification, the power control value of the vehicle is determined by using the cost function, such that a cost of the vehicle between the initial position and the terminal position is minimized. The constraints applied to the cost function consider not only the obstacle (s) around the vehicle, but also consider the initial position of the vehicle (that is, a position of the vehicle at current time) , the terminal position (that is, an expected arrival position of the vehicle) , and the traffic rule restriction. A traffic rule restriction is a restriction on movement of the vehicle imposed by rules of the road (such as a speed limit) . In some case other limiting factors may be applied as well. When the vehicle is controlled to travel according to the power control value determined by the cost function, the travelling efficiency of the vehicle may be improved. Furthermore, controlling the vehicle in this way may help not only to avoid collision with the surrounding obstacle, but in addition unnecessary braking or acceleration can be reduced or avoided, thereby improving the efficiency of energy utilization of the autonomous vehicle.

For the sake of travelling safety, the vehicle should avoid colliding with the obstacle during travelling, and therefore, the motion state (or a movement trajectory) of one or more obstacles around the vehicle is obtained. An obstacle around the vehicle is an obstacle in the surroundings of the autonomous vehicle, for instance in front of, behind or to the side of the vehicle. An obstacle around the vehicle may for instance be a dynamic obstacle (such as a vehicle or a pedestrian) or a static obstacle (such as a road green belt, a road guardrail, a road bollards, or a traffic cone) .

The autonomous vehicle is usually equipped with one or more obstacle sensing devices (such as an onboard camera, a laser radar, and/or a millimeter wave radar) . Such obstacle sensing devices may be used to detect, match, and track dynamic and static obstacles in front of, behind and on the side of the vehicle, to obtain the motion state of the obstacle around the vehicle. The motion state may comprise information such as one or more of: a position, a speed, and an acceleration of the obstacle.

In an embodiment, when the one or more obstacle sensing devices are used to detect the obstacle around the vehicle, the one or more obstacle sensing devices may be combined, that is, data information obtained by the one or more obstacle sensing devices may be collected together for comprehensive analysis, so as to describe an external environment around the vehicle more accurately and reliably, thus improving the accuracy of system speed decision-making.

In an embodiment, based on the above combination of the one or more obstacle sensing devices, the obtained motion state of the obstacle around the vehicle may be further combined with high-precision map information, and the motion state of the obstacle around the vehicle may be predicted by using a deep learning algorithm. When the motion state of the obstacle around the vehicle is predicted, historical information of the obstacle, a correlation between the obstacle and a lane, etc. may alternatively be used. In an embodiment, a specific solution of predicting the motion state of the obstacle around the vehicle by using the deep learning algorithm may be performed with reference to Chinese Patent Application Publication No. CN 111002980 A, which will not be described in detail herein.

However, a person skilled in the art may understand that the above solution of predicting the motion state of the obstacle around the vehicle by using the deep learning algorithm is merely an example. In other embodiments, other solutions may be used to predict the motion state of the obstacle around the vehicle. For example, in an exemplary embodiment, other suitable machine learning algorithms may alternatively be used to predict the motion state of the obstacle around the vehicle. In another exemplary embodiment, a non-machine learning algorithm may alternatively be used to predict the motion state of the obstacle around the vehicle, etc.

An obstacle avoidance position of the vehicle is a positon in which it is predicted the vehicle will not collide with a surrounding obstacle. In order to prevent the vehicle from colliding with the obstacle during travelling, it a safety distance between the vehicle and a surrounding obstacle may be considered. Therefore, in some embodiments, the obstacle avoidance position of the vehicle may be generated according to a preset safety distance parameter and the movement trajectory of the obstacle around the vehicle to serve as an obstacle avoidance constraint condition of the vehicle. In an embodiment, the safety distance parameter may be a variable value related to a vehicle speed. For example, when the vehicle speed is 100 KM/h, a safety distance from a front vehicle may be 100 meters. When the vehicle speed is 60 KM/h, a safety distance from the front vehicle may be 60 meters. In another embodiment, the safety distance parameter may alternatively be a fixed value (for example, 30 meters and 50 meters) as required.

The control method of the autonomous vehicle provided by this embodiment of the specification, may seek to achieve one or more of the following: no collision, energy saving, and travelling efficiency. That is, on the premise of no collision, the energy consumption is minimum and the travelling efficiency is the highest. This may be viewed as an optimization problem with constraint conditions. Studies have shown that in addition to the above obstacle avoidance constraint, the vehicle may also be constrained by kinematics, dynamics and/or traffic rules (such as a road speed limit) , etc. Kinematic and dynamic constraints represent transfer constraints between two trajectory points.

The above kinematic constraint is a relation between a position and a speed (for example, an initial speed and a terminal speed of the vehicle) , and such a constraint is related to an initial motion state and a terminal motion state. Therefore, the initial motion state and terminal motion state of the vehicle may be obtained in order to determine the kinematic constraint. For example, in one embodiment, the initial position, the initial speed, the terminal position, and the terminal speed of the vehicle may be obtained. The initial position may be a position of the vehicle at the current time. The terminal position may be an expected arrival position of the vehicle. The initial speed may be a speed of the vehicle at the initial position. The terminal speed may be an expected speed of the vehicle at the terminal position.

In an embodiment, the terminal position of the vehicle may be determined by an onboard sensor. The onboard sensor may include, but is not limited to, a camera, a radar (such as a millimeter wave radar and a laser radar) , etc. For example, in an exemplary embodiment, if an effective observation distance of the onboard camera is 200 meters, an expected arrival position, i.e. the terminal position is 200 meters ahead.

In an embodiment, the terminal speed of the vehicle may be determined in the following manner:

A front obstacle speed may be taken as the terminal speed of the vehicle when the front obstacle speed does not exceed an upper speed limit of a front road segment. Alternatively, an upper speed limit of a front road segment is taken as the terminal speed of the vehicle when a front obstacle speed exceeds the upper speed limit of the front road segment. The front obstacle speed may be an average speed of one or more vehicles in front of (generally located directly in front of, or laterally in front of) the vehicle.

The above dynamic constraint is a relation between the force and the acceleration. According to Newton’s second law, the acceleration is directly proportional to an acting force under the condition that the mass of the vehicle is determined. Generally, kinematic force analysis of the vehicle may be shown in Fig. 3. In Fig. 3, F _d represents a driving force acting on the vehicle 30, F _g represents a gradient resistance acting on the vehicle 30, F _r represents a rolling resistance acting on the vehicle 30, F _a represents an air resistance acting on the vehicle 30, θ represents a gradient, G represents a gravity acting on the vehicle 30, g represents an acceleration of gravity, and m represents the mass of the vehicle 30. The resultant force F _j acting on the vehicle 30 may be expressed as: F _j = F _d -F _g -F _r -F _a, where F _g = mg ·sinθ, F _r = f ·mg ·cosθ, F _a = 0.5ρ _aC _dA _fv ², f represents a rolling resistance coefficient of a road surface, ρ _a represents the air density, C _d represents a wind resistance coefficient of the vehicle 30, A _f represents a windward area of the vehicle 30, and v represents a travelling speed of the vehicle 30. Then an instantaneous acceleration a of the vehicle 30 may be expressed as

Generally, the driving force F _d may be represented by torque of the vehicle 30, and the torque of the vehicle 30 is positively correlated with a power control value of the vehicle 30 when gear parameters (for example, a gear ratio) of a gearbox of the vehicle 30 are determined. Therefore, it is necessary to obtain the power control value of the vehicle.

In some embodiments, the power control value may be represented by an accelerator opening degree and a brake opening degree. In some embodiments, a range of the power control value u may be: -1 ≤ u ≤ 1. When u < 0, it indicates the brake opening degree (also referred to as a “braking percentage” ) , and when u = -1, it indicates that the brake opening degree reaches 100%. When u > 0, it indicates the accelerator opening degree (also referred to as an “accelerator pedal percentage” ) , and when u = 1, it indicates that the accelerator opening degree reaches 100%. In addition, it may be understood by a person skilled in the art that in some other embodiments, when the ride comfort needs to be considered, the power control value u may be made linear-gradient (that is, a change rate of the power control value u is controlled within an appropriate range) to avoid emergency braking or emergency acceleration.

The above road speed limit may comprise a lower speed limit, an upper speed limit, and a turning speed limit of the front road segment of the vehicle. For example, in the exemplary embodiment shown in Fig. 5, the curve 51 is the upper speed limit V _max of the front road segment of the vehicle, the curve 53 is the lower speed limit V _min of the front road segment of the vehicle, and the curve 52 is a speed curve V _target corresponding to a predicted power control value. Apparently, V _target shall meet: V _min ≤ V _target ≤ V _max.

In some embodiments, the power control value of the vehicle may be predicted periodically. Predicted duration of travelling refers to a predetermined time range starting from the current time. For example, in an exemplary embodiment, the predicted duration may be 6 seconds, 8 seconds, 10 seconds, etc. in the future starting from the current time. For example, if the predicted duration is 8 seconds, and the current time point 12: 00: 00 is start time of the predicted duration, the time range for predicting the power control value of the vehicle this time is 12: 00: 00 to 12: 00: 08. In some embodiments, the cost function may be expressed as

Herein, min represents minimization, x (t) is a motion state optimization variable, u (t) is a power controlled variable, tf is predicted duration of travelling, q (u, n _e) is an energy consumption function, u is a power control value, n _e is an engine speed, w _f is an energy consumption weight, w _t is a travelling time weight, and t is time. When the initial position, the obstacle avoidance position, and the terminal position of the vehicle are input as constraint conditions, x ^* (t) and u ^* (t) in the time period tf may be obtained by solving the cost function. Herein, x ^* (t) represents an optimal x (t) in the time period tf and u ^* (t) represents an optimal u (t) in the time period tf.

The energy consumption function q (u, n _e) is a function about u and n _e, that is, there is a certain nonlinear relation between q (u, n _e) and u and n _e. In an embodiment, q (u, n _e) may be obtained through fitting and other manners in advance. For example, if the vehicle is a fuel vehicle, fuel consumption characteristics of an engine of the vehicle may be shown in Fig. 2, and q (u, n _e) may be fitted according to the diagram of fuel consumption characteristics of the engine (as indicated by the fuel consumption characteristic curve 20 of an engine in Fig. 2, etc. ) .

The above energy consumption weight w _f reflects a demand for energy saving in the cost function; and the above travelling time weight w _t reflects a demand for travelling efficiency in the cost function. The energy consumption weight and the travelling time weight may be specifically set as required. Since w _f + w _t = 1, when the demand for energy saving and the demand for travelling efficiency are equal, both w _f and w _t may be set to 0.5. When the demand for energy saving is greater than the demand for travelling efficiency, w _f may be appropriately increased and w _t may be correspondingly decreased (for example, w _f may be set to 0.7 and w _t may be set to 0.3) . When the demand for travelling efficiency is greater than the demand for energy saving, w _t may be appropriately increased and w _f may be correspondingly decreased (for example, w _t may be set to 0.7 and w _f may be set to 0.3) .

In some other embodiments, considering that the optimization of the above cost function is actually a functional problem, it is not easy to solve. In order to improve the computational processing efficiency, the functional problem may be converted into a nonlinear programming problem through a dynamic programming algorithm (such as a direct collocation method) , that is, the cost function may be calculated by using a direct collocation method to determine the power control value of the vehicle. A direct collocation method is a method in which a trajectory of the vehicle is determined using polynomial splines.

In an embodiment, when the cost function is calculated by using the direct collocation method, the above cost function

may be converted into:

The direct collocation method may be any one of several piecewise polynomial spline functions (such as a trapezoid method and a Chebyshev method) . Taking the trapezoid method as an example, the corresponding optimization constraints may comprise:

trapezoid collocation dynamic constraints:

path constraints:

boundary constraints:

number of grid points:

Herein, u ₀ is a 0 ^th power control value within the predicted duration of travelling (that is, an initial power control value within the predicted duration of travelling) , u _N is an N ^th power control value within the predicted duration of travelling, x ₀ is a 0 ^th motion state within the predicted duration of travelling (that is, an initial position within the predicted duration of travelling) , x _N is an N ^th motion state within the predicted duration of travelling, N is the number of discrete points within the predicted duration of travelling (that is, the number of grid points) , k is a time interval serial number within the predicted duration of travelling and its value is a natural number between 1 and N, h _k is the length of a k ^th time interval, q (u _k, v _k) is energy consumption of the k ^th time interval, q (u _k+1, v _k+1) is energy consumption of a (k+1) ^st time interval, where u _k and u _k+1 are respectively power controlled quantities of the k ^th time interval and the (k+1) ^st time interval, and v _k and v _k+1 are respectively engine speeds of the k ^th time interval and the (k+1) ^st time interval, w _f is an energy consumption weight, w _t is a travelling time weight, t is time, and f _k is a state of the k ^th time interval; f _k+1 (that is, f (x _k+1, u _k+1, t _k+1) ) is a state of the (k+1) ^st time interval, s _lb, k is a lower limit of the obstacle avoidance position in the k ^th time interval, and s _ub, k is an upper limit of the obstacle avoidance position in the k ^th time interval; and v _lb, k is a lower speed limit of the k ^th time interval, v _ub, k is an upper speed limit of the k ^th time interval, v ₀ is a 0 ^th speed within the predicted duration of travelling (that is, an initial speed within the predicted duration of travelling) , s _tf is an N ^th position within the predicted duration of travelling, v _tf is a speed of the N ^th position within the predicted duration of travelling, and tf is the predicted duration of travelling.

The number N of discrete points above determines prediction frequency. For example, if the predicted duration of travelling is 8 seconds and N = 9, it means that the predicted duration of travelling of 8 seconds is equally divided into eight time intervals (that is, the length of each interval is 1 second) . Accordingly, the prediction frequency is performing prediction once per second. If the predicted duration of travelling is 8 seconds and N = 5, it means that the predicted duration of travelling of 8 seconds is equally divided into four time intervals (that is, the length of each interval is 2 seconds) . Accordingly, the prediction frequency is performing prediction once every 2 seconds. In the embodiment of the specification, the number N of discrete points may be set according to the needs of actual application scenarios.

In an exemplary embodiment, optimal speed curves predicted at the moment t ₀ and the moment t ₁ (that is, speed curves corresponding to predicted optimal power controlled quantities) are shown in Fig. 4. In Fig. 4, a horizontal coordinate represents time, a vertical coordinate represents a position, and P1 represents a position curve of the vehicle over time in the current predicted duration of travelling tf (that is, future t ₀ to t ₆) that is predicted at the moment t ₀, to represent an optimal speed curve in the future time period t ₀ to t ₆. S11 and S12 are an obstacle avoidance upper limit position line and an obstacle avoidance lower limit position line predicted at the moment t ₀ respectively. P2 represents a position curve of the vehicle over time in next predicted duration of travelling tf (that is, future t ₁ to t ₇, with t ₇ and its corresponding position point not drawn in Fig. 4) that is predicted at the moment t ₁, to represent an optimal speed curve in the future time period t ₁ to t ₇. S21 and S22 are an obstacle avoidance upper limit position line and an obstacle avoidance lower limit position line predicted at the moment t ₁ respectively. An upper parallelogram in Fig. 4 represents a vehicle (an obstacle) in front of the vehicle at the moment t ₀, and a lower parallelogram in Fig. 4 represents a vehicle (an obstacle) in front of the vehicle at the moment t ₁.

Corresponding to the above control method of the autonomous vehicle, an embodiment of the specification further provides a control apparatus of an autonomous vehicle. As shown in Fig. 6, in some embodiments, the control apparatus of the autonomous vehicle may comprise:

an initial position obtaining module 61, which may be configured to obtain an initial position of the vehicle, the initial position being a position of the vehicle at current time;

a terminal position obtaining module 62, which may be configured to determine a terminal position of the vehicle, the terminal position being an expected arrival position of the vehicle;

an obstacle avoidance position determination module 63, which may be configured to obtain a motion state of an obstacle around the vehicle, and determine an obstacle avoidance position of the vehicle according to the motion state of the obstacle around the vehicle;

a traffic rule obtaining module 64, which may be configured to obtain a traffic rule restriction of a road segment where the vehicle is located;

a power control value determination module 65, which may be configured to determine a power control value of the vehicle by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints on the optimization comprise the obstacle avoidance position and the traffic rule restriction; and

a power control value transmission module 66, which may be configured to transmit the power control value to a control system of the vehicle to control motion of the vehicle, such that the travelling cost of the vehicle between the initial position and the terminal position is minimized.

In some embodiments, the cost function comprises energy consumption, travelling time and/or a weighted combination of the energy consumption and the travelling time.

In some embodiments, the cost function is expressed as:

In some embodiments, the constraints on the optimization further comprise a kinematic constraint of the vehicle, wherein the kinematic constraint comprises an initial speed and a terminal speed of the vehicle, the initial speed being a speed of the vehicle at the initial position, and the terminal speed being an expected speed of the vehicle at the terminal position.

In some embodiments, the terminal position is determined by an onboard sensor.

In some embodiments, the terminal speed is determined in the following manner:

In some embodiments, the front obstacle speed is an average speed of one or more vehicles in front of the vehicle.

In some embodiments, the power control value is an accelerator pedal percentage, where a percentage of 0%represents an idle or zero position of the accelerator pedal and a percentage of 100%represents the full or maximum position of the accelerator pedal.

In some embodiments, the cost function is calculated by using a direct collocation method to determine the power control value of the vehicle.

For ease of description, when described, the above apparatus is divided into various units based on functions. Certainly, a function of each unit may be implemented in one or more pieces of software and/or hardware when the specification is implemented.

Corresponding to the above control method of the autonomous vehicle, the specification further provides an electronic device. With reference to Fig. 7, the electronic device 702 may comprise one or more processors 704, such as one or more central processing units (CPUs) or graphics processing units (GPUs) , each processing unit being capable of implementing one or more hardware threads. The electronic device 702 may also comprise a memory 706 for storing any type of information, such as codes, settings, and data. In a particular embodiment, a computer program that may be run on the processor 704 is stored on the memory 706, and the computer program may execute an instruction according to the above method when being run by the processor 704. Without limitation, for example, the memory 706 may include any one or a combination of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disc, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or nonvolatile retention for the information. Further, any memory may represent a fixed or removable component of the electronic device 702. In one case, when the processor 704 executes an associated instruction stored in any memory or combination of memories, the electronic device 702 may perform any operation of the associated instruction. The electronic device 702 further comprises one or more driving mechanisms 708 for interacting with any memory, such as a hard disk driving mechanism and an optical disc driving mechanism.

The electronic device 702 may further comprise an input/output module (I/O) 710 for receiving various inputs (via an input device 712) and for providing various outputs (via an output device 714) . A specific output mechanism may comprise a display device 716 and an associated graphical user interface (GUI) 718. In other embodiments, the electronic device may not comprise the input/output module (I/O) 710, the input device 712, and the output device 714, and only serve as a computer device in the network. The electronic device 702 may also comprise one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above together.

The communication links 722 may be implemented in any manner, for example, through a local area network, a wide area network (for example, the Internet) , a point-to-point connection, etc., or any combination thereof. The communication links 722 may comprise any combination of a hardwired link, a wireless link, a router, a gateway function, a name server, etc. dominated by any protocol or combination of protocols.

Corresponding to the above control method of the autonomous vehicle, the specification further provides an autonomous vehicle. The autonomous vehicle may comprise the above electronic device. In some embodiments, the autonomous vehicle may include, but is not limited to, a fuel vehicle or an electric vehicle with an automated driving function.

Although a process flow described above comprises a plurality of operations occurring in a specific order, it should be clearly understood that these processes may comprise more or less operations, and these operations may be executed sequentially or in parallel (for example, by using a parallel processor or a multi-threaded environment) .

The present application is described with reference to the flowcharts and/or block diagrams of the method, the device (system) , and the computer program product according to the embodiments of the specification. It should be understood that computer program instructions may be used to implement each process and/or each block in the flowcharts and/or the block diagrams and a combination of a process and/or a block in the flowcharts and/or the block diagrams. These computer program instructions may be provided for a general-purpose computer, a special-purpose computer, an embedded processor, or a processor of another programmable data processing device to generate a machine, so that the instructions executed by a computer or a processor of another programmable data processing device generate an apparatus for implementing a specific function in one or more processes in the flowcharts and/or in one or more blocks in the block diagrams.

These computer program instructions may be stored in a computer readable memory that can instruct the computer or another programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory generate an artifact that comprises an instruction apparatus. The instruction apparatus implements a specific function in one or more processes in the flowcharts and/or in one or more blocks in the block diagrams.

These computer program instructions may be loaded onto a computer or another programmable data processing device, such that a series of operations and steps are performed on the computer or the another programmable device, thereby generating computer-implemented processing. Therefore, the instructions executed on the computer or the another programmable device provide steps for implementing a specific function in one or more processes in the flowcharts and/or in one or more blocks in the block diagrams.

In a typical configuration, a computing device comprises one or more central processing units (CPUs) , an input/output interface, a network interface, and a memory.

The memory may include a non-permanent memory, a random access memory (RAM) and/or a non-volatile memory (such as a read-only memory (ROM) or a flash memory (flash RAM) ) and so on in a computer-readable medium. A memory is an example of a computer-readable medium.

A computer-readable medium comprises permanent and non-permanent, movable and non-movable media and may realize information storage by means of any method or technology. Information may be modules of computer-readable instructions, data structures and programs, or other data. Examples of a computer storage medium include but are not limited to a phase-change random access memory (PRAM) , a static random access memory (SRAM) , a dynamic random access memory (DRAM) , other types of random access memories (RAMs) , a read-only memory (ROM) , an electrically erasable programmable read-only memory (EEPROM) , a flash memory or other memory technologies, a compact disc read-only memory (CD-ROM) , a digital versatile disc (DVD) or other optical storage, a cassette tape, tape or disk storage or other magnetic storage devices, or any other non-transmission media that may be used to store information capable of being accessed by a computing device. According to the definitions herein, the computer-readable medium does not comprise transitory media, such as modulated data signals and carrier waves.

A person skilled in the art shall understand that the embodiments of the specification may be provided as a method, a system, or a computer program product. Therefore, the embodiments of the specification may take the form of hardware only embodiments, software only embodiments, or embodiments with a combination of software and hardware. Moreover, the embodiments of the specification may take the form of a computer program product that is implemented on one or more computer-usable storage media (including but not limited to a disk memory, a CD-ROM, an optical memory, etc. ) that comprise computer-usable program codes.

The embodiments of the specification may be described in a general context of a computer-executable instruction, such as a program module, executed by a computer. Generally, the program module comprises a routine, a program, an object, a component, a data structure, etc. that performs a specific task or implements a specific abstract data type. The embodiments of the specification may also be practised in distributed computing environments where a task is performed by a remote processing device connected through a communication network. In the distributed computing environments, the program module may be located in local and remote computer storage media including storage devices.

The embodiments in the specification are all described in a progressive manner, mutual reference may be made to the same or similar parts of the embodiments, and each embodiment focuses on description of differences from other embodiments. In particular, the system embodiment is basically similar to the method embodiment and therefore is described simply, and for a related part, reference may be made to the part of the description of the method embodiment. In the description of the specification, the description with reference to terms such as “an embodiment” , “some embodiments” , “examples” , “particular examples” , or “some examples” means that specific features, structures, materials, or characteristics described in combination with the embodiment (s) or example (s) are included in at least one embodiment or example of the specification. In the specification, the schematic expressions of the terms mentioned above are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described herein may be combined in any suitable manner in any one or more embodiments or examples. In addition, without any contradiction, a person skilled in the art may bind and combine different embodiments or examples and features of the different embodiments or examples described in the specification of the present invention.

The descriptions above are merely embodiments of the present application and are not used to limit the present application. A person skilled in the art may make various changes and variations to the present application. Any modifications, equivalent replacements, and improvements made without departing from the spirit and principle of the present application shall fall within the scope of the claims of the present application.

Claims

A control method of an autonomous vehicle, characterized by comprising:

obtaining an initial position of the vehicle, the initial position being a position of the vehicle at current time;

determining a terminal position of the present vehicle, the terminal position being an expected arrival position of the vehicle;

obtaining a motion state of an obstacle around the vehicle, and determining an obstacle avoidance position for the vehicle according to the motion state of the obstacle around the vehicle;

obtaining a traffic rule restriction of a road segment where the vehicle is located;

determining a power control value of the vehicle by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints of the optimization comprise the obstacle avoidance position and the traffic rule restriction; and

transmitting the power control value to a control system of the vehicle to control movement of the vehicle, such that the travelling cost of the vehicle between the initial position and the terminal position is minimized.
The control method according to claim 1, characterized in that the travelling cost of the vehicle in the cost function comprises an energy consumption, a travelling time and/or a weighted combination of the energy consumption and the travelling time.
The control method according to claim 1, characterized in that the cost function is expressed as:

where min represents minimization, x (t) is a position variable of the vehicle, u (t) is a power control variable, tf is a predicted duration of travelling, q (u, n _e) is a preset energy consumption function, u is a power control value, n _e is an engine speed, w _f is an energy consumption weight, w _t is a travelling time weight, and t is time.
The control method according to claim 1, characterized in that the constraints of the optimization further comprise a kinematic constraint of the vehicle, wherein

the kinematic constraint comprises an initial speed and a terminal speed of the vehicle, the initial speed being a speed of the vehicle at the initial position, and the terminal speed being an expected speed of the vehicle at the terminal position.
The control method according to claim 1, characterized in that the terminal position is determined by an onboard sensor.
The control method according to claim 4, characterized in that the terminal speed is determined by:

taking a front obstacle speed as the terminal speed of the vehicle when the front obstacle speed does not exceed an upper speed limit of a front road segment; or

taking an upper speed limit of a front road segment as the terminal speed of the vehicle when a front obstacle speed exceeds the upper speed limit of the front road segment.
The control method according to claim 6, characterized in that the front obstacle speed is an average speed of one or more vehicles in front of the vehicle.
The control method according to claim 1, characterized in that the power control value is an accelerator pedal percentage.
The control method according to claim 3, characterized in that the cost function is calculated by a direct collocation method to determine the power control value of the vehicle.
A control apparatus of an autonomous vehicle, characterized by comprising:

an initial position obtaining module configured to obtain an initial position of the vehicle, the initial position being a position of the vehicle at current time;

a terminal position obtaining module configured to determine a terminal position of the vehicle, the terminal position being an expected arrival position of the vehicle;

an obstacle avoidance position determination module configured to obtain a motion state of an obstacle around the vehicle, and determine an obstacle avoidance position of the vehicle according to the motion state of the obstacle around the vehicle;

a traffic rule obtaining module configured to obtain a traffic rule restriction of a road segment where the vehicle is located;

a power control value determination module configured to determine a power control value of the vehicle by optimizing a cost function, wherein the cost function is used for calculating a travelling cost of the vehicle between the initial position and the terminal position, and constraints of the optimization comprise the obstacle avoidance position and the traffic rule restriction; and

a power control value transmission module configured to transmit the power control value to a control system of the vehicle to control motion of the vehicle, such that the travelling cost of the vehicle between the initial position and the terminal position is minimized.
The control apparatus according to claim 10, characterized in that the travelling cost of the vehicle in the cost function comprises energy consumption, travelling time and/or a weighted combination of the energy consumption and the travelling time.
The control apparatus according to claim 10, characterized in that the cost function is expressed as:

where min represents minimization, x (t) is a position variable of the present vehicle, u (t) is a power controlled variable, tf is a predicted duration of travelling, q (u, n _e) is a preset energy consumption function, u is a power control value, n _e is an engine speed, w _f is an energy consumption weight, w _t is a travelling time weight, and t is time.
The control apparatus according to claim 10, characterized in that the constraints of the optimization further comprise a kinematic constraint of the vehicle, wherein

the kinematic constraint comprises an initial speed and a terminal speed of the vehicle, the initial speed being a speed of the vehicle at the initial position, and the terminal speed being an expected speed of the vehicle at the terminal position.
The control apparatus according to claim 10, characterized in that the terminal position is determined by an onboard sensor.
The control apparatus according to claim 13, characterized in that the terminal speed is determined by:

taking a front obstacle speed as the terminal speed of the vehicle when the front obstacle speed does not exceed an upper speed limit of a front road segment; or

taking a speed of an upper speed limit of a front road segment as the terminal speed of the vehicle when a front obstacle speed exceeds the upper speed limit of the front road segment.
The control apparatus according to claim 15, characterized in that the front obstacle speed is an average speed of one or more vehicles in front of the vehicle.
The control apparatus according to claim 10, characterized in that the power control value is an accelerator pedal percentage.
The control apparatus according to claim 12, characterized in that the cost function is calculated by a direct collocation method to determine the power control value of the vehicle.
An electronic device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the computer program, when executed by the processor, performs the control method according to any one of claims 1 to 9.
A computer storage medium having a computer program stored therein, characterized in that the computer program, when executed by a processor, performs the control method according to any one of claims 1 to 9.
An autonomous vehicle, characterized in that the autonomous vehicle is equipped with the electronic device according to claim 19.