CN113291142A - Intelligent driving system and control method thereof - Google Patents
Intelligent driving system and control method thereof Download PDFInfo
- Publication number
- CN113291142A CN113291142A CN202110524076.4A CN202110524076A CN113291142A CN 113291142 A CN113291142 A CN 113291142A CN 202110524076 A CN202110524076 A CN 202110524076A CN 113291142 A CN113291142 A CN 113291142A
- Authority
- CN
- China
- Prior art keywords
- push rod
- pressure sensor
- network
- driving
- strategy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000007246 mechanism Effects 0.000 claims abstract description 31
- 239000003638 chemical reducing agent Substances 0.000 claims abstract description 15
- 230000008878 coupling Effects 0.000 claims abstract description 6
- 238000010168 coupling process Methods 0.000 claims abstract description 6
- 238000005859 coupling reaction Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 22
- 230000009471 action Effects 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000011217 control strategy Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000005653 Brownian motion process Effects 0.000 claims description 3
- 238000005537 brownian motion Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000036962 time dependent Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 239000000853 adhesive Substances 0.000 description 4
- 230000001070 adhesive effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000006096 absorbing agent Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000035939 shock Effects 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 239000010720 hydraulic oil Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D61/00—Motor vehicles or trailers, characterised by the arrangement or number of wheels, not otherwise provided for, e.g. four wheels in diamond pattern
- B62D61/12—Motor vehicles or trailers, characterised by the arrangement or number of wheels, not otherwise provided for, e.g. four wheels in diamond pattern with variable number of ground engaging wheels, e.g. with some wheels arranged higher than others, or with retractable wheels
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G1/00—Suspensions with rigid connection between axle and frame
- B60G1/04—Suspensions with rigid connection between axle and frame with divided axle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K1/00—Arrangement or mounting of electrical propulsion units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K17/00—Arrangement or mounting of transmissions in vehicles
- B60K17/04—Arrangement or mounting of transmissions in vehicles characterised by arrangement, location, or kind of gearing
- B60K17/06—Arrangement or mounting of transmissions in vehicles characterised by arrangement, location, or kind of gearing of change-speed gearing
- B60K17/08—Arrangement or mounting of transmissions in vehicles characterised by arrangement, location, or kind of gearing of change-speed gearing of mechanical type
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Body Structure For Vehicles (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an intelligent driving system and a control method thereof, wherein the intelligent driving system consists of a driving bearing device and an intelligent controller, the driving bearing device consists of a driving bearing mechanism and an auxiliary bearing mechanism, and the driving bearing mechanism consists of a first bracket, a first guide rail, a first slide block, a first push rod, a first lifting frame, a speed reducer, a first wheel shaft, a first wheel, a power motor and a coupling; the auxiliary bearing mechanism consists of a second support, a second guide rail, a second sliding block, a second push rod, a second lifting frame, a second wheel shaft and a second wheel. The intelligent driving system can be used for reconstructing a traditional automobile chassis, meanwhile, a control method based on a depth certainty strategy gradient control algorithm is designed, automatic driving and intelligent automobile posture adjustment are achieved, the telescopic positions of push rods on the left side and the right side are controlled under the condition that driving force is guaranteed, and the automobile body is kept in a horizontal state or an expected state.
Description
Technical Field
The invention relates to the technical field of vehicle control systems, in particular to an intelligent driving system and a control method thereof.
Background
When a construction road vehicle, a greening work vehicle, a sanitation vehicle, or the like is operated, it is necessary to frequently change the traveling, reversing, and stopping states. When the automobile chassis of the traditional manual transmission is adopted, the operation labor intensity of operators is high. And the frequent switching state enables the automobile clutch to be in a transitional engagement state for a long time, so that the clutch is quickly worn and the failure rate of the machine is high. And engineering road vehicles, greening operation vehicles, sanitation vehicles and the like which are transformed by adopting the traditional automobile chassis are not easy to realize automatic operation, and the production labor efficiency is seriously restricted.
At present, certain research results are obtained around the related technology of the intelligent driving system in China. The invention patent application of 201911329633.6 provides an adaptive bearing system, which can automatically adjust the working state of a hydraulic rod when the weight of a load is larger than the limit of the bearing system, and simultaneously adjust the position of a connecting disc arranged at the working end of the hydraulic rod and the positions of connecting rods hinged with the connecting disc respectively, thereby adjusting the bearing limit of the bearing system to prevent the bearing system from being damaged.
The utility model discloses an application number 201920730258.5's utility model provides a self-adaptation bears chassis, and when this utility model's self-adaptation bore chassis transportation article, the weight share of article has guaranteed the frictional force between drive wheel and the ground on drive wheel and first activity foot wheelset and second activity foot wheelset.
The invention patent application with the application number of 201710421571.6 provides a system and a control method for actively increasing the adhesive force of an automobile, wherein the device comprises a controller, a normally open solenoid valve, an energy storage device, a shock absorber, a shaft cylinder, a one-way valve and the like, hydraulic oil in the control process is controlled to flow according to a set direction by actively increasing the adhesive force of the automobile, the spring of the shock absorber of the automobile is contracted when the automobile is accelerated and emergently braked by combining the shaft cylinder, the adhesive force of the automobile is increased, safer braking and faster acceleration are realized, and the system can be repeatedly used and automatically reset.
However, the existing intelligent bearing chassis, load-bearing devices and automobile active adhesion force increasing system still have the defects of low system response speed, poor anti-interference capability of a control algorithm, poor robustness, incapability of fully ensuring the adhesion coefficient of a driving wheel and the ground, difficulty in ensuring accurate pose of the load-bearing devices and the like.
Disclosure of Invention
The invention aims to provide an intelligent driving system and a control method thereof, which are used for improving the traditional automobile chassis and can realize automatic walking, accurate position control, automobile bearing and intelligent posture adjustment.
In order to achieve the purpose, the invention discloses an intelligent driving system, which consists of a driving bearing device and an intelligent controller;
the driving bearing device consists of a driving bearing mechanism and an auxiliary bearing mechanism, the driving bearing mechanism is arranged on one side of the vehicle chassis frame, and the auxiliary bearing mechanism is arranged on the other side of the vehicle chassis frame;
the driving bearing mechanism consists of a first bracket, a first guide rail, a first slide block, a first push rod, a first lifting frame, a speed reducer, a first wheel shaft, a first wheel, a power motor and a coupling; the auxiliary bearing mechanism consists of a second bracket, a second guide rail, a second sliding block, a second push rod, a second lifting frame, a second wheel shaft and a second wheel;
the upper end of the first support is fixedly connected with a vehicle chassis frame, the first guide rail is fixedly installed on the first support along the vertical direction, the first sliding block is connected with the first guide rail and can slide along the vertical direction, the first sliding block is fixedly connected with the first lifting frame, the upper end of the first push rod is connected with the first support, the power motor is fixedly installed on the first lifting frame, the output shaft of the power motor is connected with the speed reducer through the coupler, the speed reducer is fixedly connected with the first lifting frame, one end of the first wheel shaft is installed in the output hole of the speed reducer, and the other end of the first wheel shaft is fixedly connected with the first wheel.
The upper end of the second support is fixedly connected with a chassis frame of the vehicle, the second guide rail is fixedly installed on the second support along the vertical direction, the second sliding block is connected with the second guide rail and can slide along the vertical direction, the second sliding block is fixedly connected with the second lifting frame, the upper end of the second push rod is connected with the second support, one end of the second wheel shaft is fixedly connected with the second lifting frame, and the other end of the second wheel shaft is rotatably connected with the second wheel.
The intelligent controller comprises a laser radar, a gyroscope, a first pressure sensor, a second pressure sensor, an upper computer controller and a lower computer controller;
the laser radar is arranged in the middle of a bumper at the front end of a vehicle chassis and is responsible for collecting road roughness data;
the gyroscope is arranged at the geometric center of the wheel and is responsible for acquiring road surface inclination data;
the first pressure sensor is fixedly connected with the lower end of the first lifting frame, the first pressure sensor is also connected with the lower end of the first push rod, and the first pressure sensor is responsible for collecting supporting force data of one side, where the driving bearing device is installed, of the driving bearing device;
the second pressure sensor is fixedly connected with the lower end of the second lifting frame, the second pressure sensor is also connected with the lower end of the second push rod, and the second pressure sensor is responsible for collecting supporting force data of one side, where the auxiliary bearing device is installed, of the auxiliary bearing device;
the laser radar, the gyroscope, the first pressure sensor and the second pressure sensor are connected with an upper computer controller through signal lines, the upper computer controller is connected with a lower computer controller through signal lines, and the lower computer controller is connected with the first push rod and the second push rod through signal lines respectively; the upper computer controller receives data signals from the laser radar, the gyroscope, the first pressure sensor and the second pressure sensor, the upper computer controller calculates and processes the data signals through a control algorithm to obtain control signals and then outputs the control signals to the lower computer controller, and the lower computer controller outputs the control signals to the first push rod and the second push rod.
In a possible implementation manner, the upper end of the first push rod is connected with the first bracket through a first pin, and the upper end of the second push rod is connected with the second bracket through a second pin.
In a possible implementation manner, the first push rod and the second push rod are electric push rods driven by a servo motor.
The control method of the intelligent driving system comprises the following steps:
(1) data acquisition and state definition: the laser radar acquires road inclination data, the gyroscope acquires road inclination data, the first pressure sensor acquires supporting force data of one side, where the driving bearing device is installed, of the first pressure sensor, the second pressure sensor acquires supporting force data of one side, where the auxiliary bearing device is installed, of the second pressure sensor, and the acquired data are stored in a sample pool M;
the state vector S is composed of the strategy initialization error e (t), the error integral e (t) dt, and the feedback y (t) valuet，St＝[e(t),∫e(t)dt,y(t)]TFor representing the status characteristic of the system at the current time, and similarly, the status characteristic at the next time is St+1；
(2) Setting a target reward function: setting an objective function fusing the sum of the discount rewards for body roll and vehicle speed hold to J (theta)μ):
J(θμ)＝Eθ'[r1+γr2+γ2r3+…] (1-1)
Where gamma is a decay (discount) factor, with values of 0 to 1, r1,r2… is the prize value that the system achieves per interaction with the environment, defined as: r isi＝α1r1(t)+α2r2(t)，i＝1,2,…，α1，α2Represents the reward factor, r1(t) and r2(t) awards corresponding to the vehicle body side inclination and the vehicle speed keeping at each moment are defined as:
r1(t)＝50(25-θ)2+50
where θ represents the roll angle of the vehicle body with respect to the horizontal plane, r1(t) indicates that the higher the reward obtained when the body roll is closer to the horizontal state, i.e., θ → 0, r2(t) represents a reward, J (theta), for obtaining sufficient driving force in the vehicle while ensuring that the horizontal attitude of the vehicle is not damagedμ) Used for representing the accumulated expected return obtained in the process of the interaction between the bearing system and the environment;
(3) setting a strategy: the control algorithm integrates experience playback and target network in the Deep Q Network (DQN) and adoptsUsing an Actor-Critic algorithm framework based on a deterministic strategy; wherein the deterministic strategy a ═ pi (s | θ)μ) Sum function Q (s, a | θ)Q) Using a parameter of theta respectivelyμAnd thetaQThe deep neural network of (2) shows that the neural network structure is 50 × 50 and the number of layers is 5. a ═ pi (s | θ)μ) For updating the strategy, corresponding to the Actor in Actor-Critic, Q (s, a | θ)Q) The value function is used for evaluating the action and providing gradient information, and corresponds to criticic in Actor-criticic;
in order to avoid trapping local optimality when the optimal Action is explored in a continuous Action space, an OU Noise method is added on the basis of the Action to solve the problem:
where N represents noise, which is a time-dependent random process, for a continuous system, the OU noise differential equation is expressed as:
dSt＝-θ(St-μ)dt+σdWt (1-4)
where μ is the mean, θ and σ are both greater than zero, WtDenotes Brownian motion, Wt-Ws～N(0,σ2(t-s)). For the inertia drive bearing system, the OU noise strategy is introduced to improve the algorithm exploration efficiency;
(4) updating the strategy: according to the method of random gradient descent, the objective function is optimized to obtain the theta of the objective functionμIs equivalent to the Q function with respect to thetaμDesired gradient of (a):
by deterministic strategy a ═ pi (s | theta)μ) Obtaining:
therefore, the update process of the policy network can be expressed as:
where α is learning efficiency. And then updating the critic network by a DQN median network method:
wherein,
and
parameters representing a target policy network and a target value network, respectively; in the whole control algorithm, an experience playback mechanism is adopted to obtain a training sample from a sample pool M, gradient information of an action is transmitted from an evaluation network (criterion network) to an action network (Actor network), and parameters of a strategy network are updated along the direction of improving a Q value according to a formula (1-5); the updating method comprises the following steps:
wherein tau is the update rate and the value is far less than 1;
(5) and (3) control quantity output: and according to the acquired state information, accurate servo stretching amounts of the first push rod and the second push rod are output through learning, calculation and iterative updating of a control strategy.
Compared with the prior art, the invention has the following beneficial effects:
(1) the intelligent driving system can be additionally installed or modified on the basis of the original vehicle chassis, so that the technical cost is reduced, and automatic walking, accurate position control and vehicle posture adjustment are realized;
(2) compared with the existing intelligent control method, the control method for the intelligent driving system based on the depth deterministic strategy gradient control algorithm (DDPG) is intelligently advanced, an experience playback meter mechanism is introduced in training iteration, the efficiency of searching the optimal control quantity by the algorithm is improved, and meanwhile, when the system is interfered by the outside, the control method has quick dynamic response and strong robustness, presents small steady-state error when the internal parameters of the system change, improves the control precision, and can meet the requirement of realizing the adjustment of the horizontal posture of the vehicle body under the condition of ensuring the driving adhesive force;
(3) meanwhile, under the condition of realizing the functions of supporting, bearing and stabilizing the vehicle body, the invention ensures enough driving force during vehicle operation and realizes the autonomous running of the vehicle.
Drawings
FIG. 1 is a schematic view of the construction of the drive carrier of the present invention;
FIG. 2 is an exploded view of the drive carrier mechanism of the present invention;
FIG. 3 is an exploded view of the auxiliary load bearing mechanism of the present invention;
FIG. 4 is a schematic illustration of the position of the drive carrier of the present invention mounted to the chassis of a vehicle;
FIG. 5 is a schematic diagram of the intelligent controller of the present invention;
fig. 6 is a schematic diagram of a control method of the intelligent travel system of the present invention.
In the figure, 1-a driving bearing mechanism, 2-an auxiliary bearing mechanism, 3-a vehicle chassis frame, 4-a first bracket, 5-a first guide rail, 6-a first slide block, 7-a first push rod, 8-a first pin, 9-a first pressure sensor, 10-a first lifting frame, 11-a speed reducer, 12-a first wheel shaft, 13-a first wheel, 14-a power motor, 15-a coupler, 16-a second bracket, 17-a second guide rail, 18-a second slide block, 19-a second push rod, 20-a second pin, 21-a second pressure sensor, 22-a second lifting frame, 23-a second wheel, 24-a second wheel shaft, 25-a laser radar, 26-a gyroscope and 27-an upper computer controller, 28-lower computer controller.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
The intelligent driving system consists of a driving bearing device and an intelligent controller;
fig. 1 shows a schematic structural view of a drive carrier according to a preferred embodiment of the present invention, which is composed of a drive carrier 1 and an auxiliary carrier 2, as shown in fig. 4, the drive carrier 1 is disposed on the left side of a vehicle chassis frame 3, and the auxiliary carrier 2 is disposed on the right side of the vehicle chassis frame 3;
the driving bearing mechanism 1 consists of a first bracket 4, a first guide rail 5, a first slide block 6, a first push rod 7, a first lifting frame 10, a speed reducer 11, a first wheel shaft 12, a first wheel 13, a power motor 14 and a coupling 15; the auxiliary bearing mechanism 2 is composed of a second bracket 16, a second guide rail 17, a second slide block 18, a second push rod 19, a second lifting frame 22, a second wheel shaft 24 and a second wheel 23, and the first push rod 7 and the second push rod 19 are electric push rods driven by a servo motor.
Fig. 2 shows an exploded view of a drive carrier 1 according to a preferred embodiment of the present invention, referring to fig. 2, an upper end of a first support 4 is fixedly connected to a chassis frame 3 of a vehicle, a first guide rail 5 is fixedly installed on the first support 4 along a vertical direction, a first slider 6 is connected to the first guide rail 5 and can slide along the vertical direction, the first slider 6 is fixedly connected to a first lifting frame 10, an upper end of a first push rod 7 is connected to the first support 4, a power motor 14 is fixedly installed on the first lifting frame 10, an output shaft of the power motor 14 is connected to a speed reducer 11 through a coupling 15, the speed reducer 11 is fixedly connected to the first lifting frame 10, one end of a first wheel shaft 12 is installed in an output hole of the speed reducer 11, the other end of the first wheel shaft 12 is fixedly connected to a first wheel 13, and an upper end of the first push rod 7 is connected to the first support 4 through a first pin 8.
Fig. 3 shows an exploded view of the auxiliary carrying mechanism 2 according to the preferred embodiment of the present invention, referring to fig. 3, the upper end of the second bracket 16 is fixedly connected with the vehicle chassis frame 3, the second guide rail 17 is fixedly installed on the second bracket 16 along the vertical direction, the second slider 18 is connected with the second guide rail connection 17 and can slide along the vertical direction, the second slider 18 is fixedly connected with the second crane 22, the upper end of the second push rod 19 is connected with the second bracket 16, one end of the second wheel axle 24 is fixedly connected with the second crane 22, the other end of the second wheel axle 24 is rotatably connected with the second wheel 23, and the upper end of the second push rod 19 is connected with the second bracket 16 through the second pin 20.
Fig. 5 shows a schematic structural diagram of an intelligent controller according to a preferred embodiment of the present invention, and referring to fig. 5, the intelligent controller includes a laser radar 25, a gyroscope 26, a first pressure sensor 9, a second pressure sensor 21, an upper computer controller 27, and a lower computer controller 28;
the laser radar 25 is arranged in the middle of a bumper at the front end of the vehicle chassis and is responsible for collecting road roughness data;
the gyroscope 26 is arranged at the geometric center of the vehicle and is responsible for acquiring road surface inclination data;
the first pressure sensor 9 is fixedly connected with the lower end of the first lifting frame 10, the first pressure sensor 9 is also connected with the lower end of the first push rod 7, and the first pressure sensor 9 is responsible for collecting supporting force data on the left side of the vehicle chassis;
the second pressure sensor 21 is fixedly connected with the lower end of the second lifting frame 22, the second pressure sensor 21 is also connected with the lower end of the second push rod 19, and the second pressure sensor 21 is responsible for supporting force data on the right side of the vehicle chassis;
the laser radar 25, the gyroscope 26, the first pressure sensor 9 and the second pressure sensor 21 are connected with an upper computer controller 27 through signal lines, the upper computer controller 27 is connected with a lower computer controller 28 through signal lines, and the lower computer controller 28 is connected with the first push rod 7 and the second push rod 19 through signal lines respectively; the upper computer controller 27 receives data signals from the laser radar 25, the gyroscope 26, the first pressure sensor 9 and the second pressure sensor 21, the upper computer controller 27 calculates and processes the data signals through a control algorithm to obtain control signals, and then outputs the control signals to the lower computer controller 28, and the lower computer controller 28 outputs the control signals to the first push rod 7 and the second push rod 19.
When the vehicle normally runs on a road, the intelligent running system does not work, the driving bearing mechanism 1 and the auxiliary bearing mechanism 2 are both in a lifting state, namely the first wheel 13 and the second wheel 23 are not grounded;
when the vehicle is in an operating state, the vehicle is in a neutral gear, the intelligent driving system starts to work, the driving bearing mechanism 1 and the auxiliary bearing mechanism 2 are both in a lowering state, namely the first wheel 13 and the second wheel 23 land, the first push rod 7 and the second push rod 19 support the vehicle chassis frame 3, the first pressure sensor 9 and the second pressure sensor 21 detect the pressure of the vehicle chassis on the first wheel 13 and the second wheel 23 in real time, the laser radar 25, the gyroscope 26, the first pressure sensor 9 and the second pressure sensor 21 detect state signals at various working positions in real time, the control method calculates the appropriate servo expansion amount of the first push rod 7 and the second push rod 19 in the current state, and the driving bearing device is controlled by the first push rod 7 and the second push rod 19; meanwhile, the power motor 14 can make the first wheel 13 obtain driving force through the coupling 15 and the reducer 11.
Fig. 6 shows a schematic diagram of the control method of the present invention, and referring to fig. 6, the control method consists of the following steps:
(1) data acquisition and state definition: the method comprises the following steps that a laser radar collects road inclination data, a gyroscope collects road inclination data, a first pressure sensor collects supporting force data of one side, where a driving bearing device is installed, of a driving bearing device, a second pressure sensor collects supporting force data of one side, where an auxiliary bearing device is installed, of the driving bearing device, and the collected data are stored in a sample cell M;
the state vector S is composed of the strategy initialization error e (t), the error integral e (t) dt, and the feedback y (t) valuet，St＝[e(t),∫e(t)dt,y(t)]TFor representing the status characteristic of the system at the current time, and similarly, the status characteristic at the next time is St+1；
(2) Setting a target reward function: setting an objective function fusing the sum of the discount rewards for body roll and vehicle speed hold to J (theta)μ):
J(θμ)＝Eθ'[r1+γr2+γ2r3+…] (1-1)
Where gamma is a decay (discount) factor, with values of 0 to 1, r1,r2… is the prize value that the system achieves per interaction with the environment, defined as: r isi＝α1r1(t)+α2r2(t)，i＝1,2,…，α1，α2Represents the reward factor, r1(t) and r2(t) awards corresponding to the vehicle body side inclination and the vehicle speed keeping at each moment are defined as:
r1(t)＝50(25-θ)2+50
where θ represents the roll angle of the vehicle body with respect to the horizontal plane, r1(t) indicates that the higher the reward obtained when the body roll is closer to the horizontal state, i.e., θ → 0, r2(t) represents a reward, J (theta), for obtaining sufficient driving force in the vehicle while ensuring that the horizontal attitude of the vehicle is not damagedμ) Used for representing the accumulated expected return obtained in the process of the interaction between the bearing system and the environment;
(3) setting a strategy: the control algorithm is fused with experience playback and a target network in a Deep Q Network (DQN), and an Actor-Critic algorithm framework based on a deterministic strategy is adopted; wherein the deterministic strategy a ═ pi (s | θ)μ) Sum function Q (s, a | θ)Q) Using a parameter of theta respectivelyμAnd thetaQDeep neural network look-up tableThe neural network structure is 50 x 50 with 5 layers. a ═ pi (s | θ)μ) For updating the strategy, corresponding to the Actor in Actor-Critic, Q (s, a | θ)Q) The value function is used for evaluating the action and providing gradient information, and corresponds to criticic in Actor-criticic;
in order to avoid trapping local optimality when the optimal Action is explored in a continuous Action space, an OU Noise method is added on the basis of the Action to solve the problem:
where N represents noise, which is a time-dependent random process, for a continuous system, the OU noise differential equation is expressed as:
where μ is the mean, θ and σ are both greater than zero, WtDenotes Brownian motion, Wt-Ws～N(0,σ2(t-s)). For the inertia drive bearing system, the OU noise strategy is introduced to improve the algorithm exploration efficiency;
(4) updating the strategy: according to the method of random gradient descent, the objective function is optimized to obtain the theta of the objective functionμIs equivalent to the Q function with respect to thetaμDesired gradient of (a):
by deterministic strategy a ═ pi (s | theta)μ) Obtaining:
therefore, the update process of the policy network can be expressed as:
where α is learning efficiency. And then updating the critic network by a DQN median network method:
wherein,
and
parameters representing a target policy network and a target value network, respectively; in the whole control algorithm, an experience playback mechanism is adopted to obtain a training sample from a sample pool M, gradient information of an action is transmitted from an evaluation network (criterion network) to an action network (Actor network), and parameters of a strategy network are updated along the direction of improving a Q value according to a formula (1-5); the updating method comprises the following steps:
wherein tau is the update rate and the value is far less than 1;
(5) the system initializes the parameters of the controller, and obtains a strengthening action a by mapping according to the current Actor on-line strategy mu and the random Noise control strategyt' outputting servo extension and retraction amounts of the first push rod 7 and the second push rod 19, and adjusting the posture of the vehicle body through extension and retraction of the first push rod 7 and the second push rod 19;
(6) after the action is executed, a reward value r is returned to the systemtAnd the state S at the next momentt+1And will beThis state transition process (S)t,at,rt,St+1) Storing the data in a sample pool M, updating according to an updating strategy, outputting the next strengthening action and executing, repeating the updating iteration process, obtaining the proper servo expansion amount in the current working state after multiple times of updating, self-learning and self-setting, and adjusting the posture of the vehicle body under the condition of ensuring the driving force;
(7) when the working condition changes, the system decides proper output according to the state of the current moment and a control strategy, ensures that the system outputs accurate servo stretching amount under different working states, and realizes self-adaptive adjustment of the body posture under the condition of keeping the driving force.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (3)
1. An intelligent driving system, characterized in that: the intelligent driving system consists of a driving bearing device and an intelligent controller;
the driving bearing device consists of a driving bearing mechanism and an auxiliary bearing mechanism, the driving bearing mechanism is arranged on one side of the vehicle chassis frame, and the auxiliary bearing mechanism is arranged on the other side of the vehicle chassis frame;
the driving bearing mechanism consists of a first bracket, a first guide rail, a first slide block, a first push rod, a first lifting frame, a speed reducer, a first wheel shaft, a first wheel, a power motor and a coupling; the auxiliary bearing mechanism consists of a second bracket, a second guide rail, a second sliding block, a second push rod, a second lifting frame, a second wheel shaft and a second wheel;
the upper end of the first support is fixedly connected with a vehicle chassis frame, the first guide rail is fixedly installed on the first support along the vertical direction, the first sliding block is connected with the first guide rail and can slide along the vertical direction, the first sliding block is fixedly connected with the first lifting frame, the upper end of the first push rod is connected with the first support, the power motor is fixedly installed on the first lifting frame, the output shaft of the power motor is connected with the speed reducer through the coupler, the speed reducer is fixedly connected with the first lifting frame, one end of the first wheel shaft is installed in the output hole of the speed reducer, and the other end of the first wheel shaft is fixedly connected with the first wheel.
The upper end of the second support is fixedly connected with a chassis frame of the vehicle, the second guide rail is fixedly installed on the second support along the vertical direction, the second sliding block is connected with the second guide rail and can slide along the vertical direction, the second sliding block is fixedly connected with the second lifting frame, the upper end of the second push rod is connected with the second support, one end of the second wheel shaft is fixedly connected with the second lifting frame, and the other end of the second wheel shaft is rotatably connected with the second wheel.
The intelligent controller comprises a laser radar, a gyroscope, a first pressure sensor, a second pressure sensor, an upper computer controller and a lower computer controller;
the laser radar is arranged in the middle of a bumper at the front end of a vehicle chassis and is responsible for collecting road roughness data;
the gyroscope is arranged at the geometric center of the vehicle and is responsible for acquiring road surface inclination data;
the first pressure sensor is fixedly connected with the lower end of the first lifting frame, the first pressure sensor is also connected with the lower end of the first push rod, and the first pressure sensor is responsible for collecting supporting force data of one side, where the driving bearing device is installed, of the driving bearing device;
the second pressure sensor is fixedly connected with the lower end of the second lifting frame, the second pressure sensor is also connected with the lower end of the second push rod, and the second pressure sensor is responsible for collecting supporting force data of one side, where the auxiliary bearing device is installed, of the auxiliary bearing device;
the laser radar, the gyroscope, the first pressure sensor and the second pressure sensor are connected with an upper computer controller through signal lines, the upper computer controller is connected with a lower computer controller through signal lines, and the lower computer controller is connected with the first push rod and the second push rod through signal lines respectively; the upper computer controller receives data signals from the laser radar, the gyroscope, the first pressure sensor and the second pressure sensor, the upper computer controller calculates and processes the data signals through a control algorithm to obtain control signals and then outputs the control signals to the lower computer controller, and the lower computer controller outputs the control signals to the first push rod and the second push rod.
2. The intelligent running system according to claim 1, wherein: the upper end of the first push rod is connected with the first support through a first pin, the upper end of the second push rod is connected with the second support through a second pin, and the first push rod and the second push rod are driven by an electric push rod of a servo motor.
3. The control method of the intelligent traveling system according to claim 1, comprising the steps of:
(1) data acquisition and state definition: the laser radar acquires road inclination data, the gyroscope acquires road inclination data, the first pressure sensor acquires supporting force data of one side, where the driving bearing device is installed, of the first pressure sensor, the second pressure sensor acquires supporting force data of one side, where the auxiliary bearing device is installed, of the second pressure sensor, and the acquired data are stored in a sample pool M;
the state vector S is composed of the strategy initialization error e (t), the error integral e (t) dt, and the feedback y (t) valuet，St＝[e(t),∫e(t)dt,y(t)]TFor representing the status characteristic of the system at the current time, and similarly, the status characteristic at the next time is St+1；
(2) Setting a target reward function: setting an objective function fusing the sum of the discount rewards for body roll and vehicle speed hold to J (theta)μ):
J(θμ)＝Eθ'[r1+γr2+γ2r3+…] (1-1)
Where gamma is a decay (discount) factor, with values of 0 to 1, r1,r2… is the prize value that the system achieves per interaction with the environment, defined as: r isi＝α1r1(t)+α2r2(t)，i＝1,2,…，α1，α2Represents the reward factor, r1(t) and r2(t) awards corresponding to the vehicle body side inclination and the vehicle speed keeping at each moment are defined as:
r1(t)＝50(25-θ)2+50
where θ represents the roll angle of the vehicle body with respect to the horizontal plane, r1(t) indicates that the higher the reward obtained when the body roll is closer to the horizontal state, i.e., θ → 0, r2(t) represents a reward, J (theta), for obtaining sufficient driving force in the vehicle while ensuring that the horizontal attitude of the vehicle is not damagedμ) Used for representing the accumulated expected return obtained in the process of the interaction between the bearing system and the environment;
(3) setting a strategy: the control algorithm is fused with experience playback and a target network in a Deep Q Network (DQN), and an Actor-Critic algorithm framework based on a deterministic strategy is adopted; wherein the deterministic strategy a ═ pi (s | θ)μ) Sum function Q (s, a | θ)Q) Using a parameter of theta respectivelyμAnd thetaQThe deep neural network of (2) shows that the neural network structure is 50 × 50 and the number of layers is 5. a ═ pi (s | θ)μ) For updating the strategy, corresponding to the Actor in Actor-Critic, Q (s, a | θ)Q) The value function is used for evaluating the action and providing gradient information, and corresponds to criticic in Actor-criticic;
in order to avoid trapping local optimality when the optimal Action is explored in a continuous Action space, an OU Noise method is added on the basis of the Action to solve the problem:
where N represents noise, which is a time-dependent random process, for a continuous system, the OU noise differential equation is expressed as:
where μ is the mean, θ and σ are both greater than zero, WtDenotes Brownian motion, Wt-Ws～N(0,σ2(t-s)). For the inertia drive bearing system, the OU noise strategy is introduced to improve the algorithm exploration efficiency;
(4) updating the strategy: according to the method of random gradient descent, the objective function is optimized to obtain the theta of the objective functionμIs equivalent to the Q function with respect to thetaμDesired gradient of (a):
by deterministic strategy a ═ pi (s | theta)μ) Obtaining:
therefore, the update process of the policy network can be expressed as:
where α is learning efficiency. And then updating the critic network by a DQN median network method:
wherein,
and
parameters representing a target policy network and a target value network, respectively; in the whole control algorithm, an experience playback mechanism is adopted to obtain a training sample from a sample pool M, gradient information of an action is transmitted from an evaluation network (criterion network) to an action network (Actor network), and parameters of a strategy network are updated along the direction of improving a Q value according to a formula (1-5); the updating method comprises the following steps:
wherein tau is the update rate and the value is far less than 1;
(5) and (3) control quantity output: and according to the acquired state information, accurate servo stretching amounts of the first push rod and the second push rod are output through learning, calculation and iterative updating of a control strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524076.4A CN113291142B (en) | 2021-05-13 | 2021-05-13 | Intelligent driving system and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524076.4A CN113291142B (en) | 2021-05-13 | 2021-05-13 | Intelligent driving system and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113291142A true CN113291142A (en) | 2021-08-24 |
| CN113291142B CN113291142B (en) | 2022-11-11 |
Family
ID=77321961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110524076.4A Active CN113291142B (en) | 2021-05-13 | 2021-05-13 | Intelligent driving system and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113291142B (en) |
Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5113345A (en) * | 1989-05-29 | 1992-05-12 | Fuji Jukogyo Kabushiki Kaisha | System for controlling active suspensions of a vehicle |
| JPH10181330A (en) * | 1996-12-26 | 1998-07-07 | Takenaka Komuten Co Ltd | Vehicular suspension device |
| WO2000069702A1 (en) * | 1999-05-19 | 2000-11-23 | Giok Djien Go | Rescue system of a train or vehicle |
| JP2005090616A (en) * | 2003-09-17 | 2005-04-07 | Toyota Motor Corp | Active suspension device |
| JP2005125992A (en) * | 2003-10-27 | 2005-05-19 | Matsushita Electric Works Ltd | Level difference traveling mechanism |
| US20070272458A1 (en) * | 2004-12-09 | 2007-11-29 | Kabushikikaisha Equos Research | Wheel Supporting and Driving Device |
| US20080086240A1 (en) * | 1995-06-07 | 2008-04-10 | Automotive Technologies International, Inc. | Vehicle Computer Design and Use Techniques |
| WO2010066541A1 (en) * | 2008-12-10 | 2010-06-17 | Zf Friedrichshafen Ag | Method for determining the roadway condition of a road section driven upon by a motor vehicle |
| US20110089647A1 (en) * | 2009-10-15 | 2011-04-21 | Agco Corporation | Variable Chassis Adjustment System |
| EP2366562A1 (en) * | 2010-03-01 | 2011-09-21 | Scania CV AB | Method and system for improving the drivability of a motor vehicle |
| US20130075170A1 (en) * | 2010-07-15 | 2013-03-28 | Hitachi Construction Machinery Co., Ltd. | Electric working vehicle |
| CN103222395A (en) * | 2013-05-14 | 2013-07-31 | 广西大学 | Hedge trimmer carrying mechanism |
| WO2014017089A1 (en) * | 2012-07-26 | 2014-01-30 | 日産自動車株式会社 | Auxiliary steering device for vehicle and auxiliary steering method for same, and elevation device for auxiliary wheel |
| CN103621326A (en) * | 2013-12-06 | 2014-03-12 | 广西大学 | Hedgerow trimmer bearing mechanism with self-adapting function |
| CN106864249A (en) * | 2015-12-11 | 2017-06-20 | 成都德善能科技有限公司 | Electric motor car |
| US20180001887A1 (en) * | 2016-06-30 | 2018-01-04 | Aisin Seiki Kabushiki Kaisha | Traveling support device |
| CN109466268A (en) * | 2017-09-08 | 2019-03-15 | 松下知识产权经营株式会社 | Moving body |
| US20190361456A1 (en) * | 2018-05-24 | 2019-11-28 | GM Global Technology Operations LLC | Control systems, control methods and controllers for an autonomous vehicle |
| CN110606142A (en) * | 2019-08-15 | 2019-12-24 | 燕山大学 | Series-parallel supporting leg based on ground sealing and movable posture adjusting platform thereof |
| US20200033869A1 (en) * | 2018-07-27 | 2020-01-30 | GM Global Technology Operations LLC | Systems, methods and controllers that implement autonomous driver agents and a policy server for serving policies to autonomous driver agents for controlling an autonomous vehicle |
| CN110758042A (en) * | 2019-10-10 | 2020-02-07 | 点狮科技(浙江)有限公司 | Self-balancing moving platform and self-balancing moving method |
| CN110775877A (en) * | 2019-11-27 | 2020-02-11 | 扬州力德工程技术有限公司 | AGV intelligent trolley and control method thereof |
| US20200081436A1 (en) * | 2017-06-02 | 2020-03-12 | Honda Motor Co., Ltd. | Policy generation device and vehicle |
| US20200156431A1 (en) * | 2018-11-19 | 2020-05-21 | Hyundai Motor Company | Apparatus and method for controlling lift axle of vehicle |
| CN111201554A (en) * | 2017-10-17 | 2020-05-26 | 本田技研工业株式会社 | Travel model generation system, vehicle in travel model generation system, processing method, and program |
| CN111622293A (en) * | 2019-02-28 | 2020-09-04 | 斗山英维高株式会社 | Control method and system of wheel loader |
| US20200307692A1 (en) * | 2019-03-28 | 2020-10-01 | Volkswagen Aktiengesellschaft | On-road localization methodologies and equipment utilizing road surface characteristics |
| WO2020239099A1 (en) * | 2019-05-29 | 2020-12-03 | 张大朋 | Electric vehicle, automatic driving method and equipment, automatic freight transportation method and system |
| US20210024081A1 (en) * | 2019-07-09 | 2021-01-28 | Refraction Ai, Inc. | Method and system for autonomous vehicle control |
-
2021
- 2021-05-13 CN CN202110524076.4A patent/CN113291142B/en active Active
Patent Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5113345A (en) * | 1989-05-29 | 1992-05-12 | Fuji Jukogyo Kabushiki Kaisha | System for controlling active suspensions of a vehicle |
| US20080086240A1 (en) * | 1995-06-07 | 2008-04-10 | Automotive Technologies International, Inc. | Vehicle Computer Design and Use Techniques |
| JPH10181330A (en) * | 1996-12-26 | 1998-07-07 | Takenaka Komuten Co Ltd | Vehicular suspension device |
| WO2000069702A1 (en) * | 1999-05-19 | 2000-11-23 | Giok Djien Go | Rescue system of a train or vehicle |
| JP2005090616A (en) * | 2003-09-17 | 2005-04-07 | Toyota Motor Corp | Active suspension device |
| JP2005125992A (en) * | 2003-10-27 | 2005-05-19 | Matsushita Electric Works Ltd | Level difference traveling mechanism |
| US20070272458A1 (en) * | 2004-12-09 | 2007-11-29 | Kabushikikaisha Equos Research | Wheel Supporting and Driving Device |
| WO2010066541A1 (en) * | 2008-12-10 | 2010-06-17 | Zf Friedrichshafen Ag | Method for determining the roadway condition of a road section driven upon by a motor vehicle |
| US20110089647A1 (en) * | 2009-10-15 | 2011-04-21 | Agco Corporation | Variable Chassis Adjustment System |
| EP2366562A1 (en) * | 2010-03-01 | 2011-09-21 | Scania CV AB | Method and system for improving the drivability of a motor vehicle |
| US20130075170A1 (en) * | 2010-07-15 | 2013-03-28 | Hitachi Construction Machinery Co., Ltd. | Electric working vehicle |
| WO2014017089A1 (en) * | 2012-07-26 | 2014-01-30 | 日産自動車株式会社 | Auxiliary steering device for vehicle and auxiliary steering method for same, and elevation device for auxiliary wheel |
| CN103222395A (en) * | 2013-05-14 | 2013-07-31 | 广西大学 | Hedge trimmer carrying mechanism |
| CN103621326A (en) * | 2013-12-06 | 2014-03-12 | 广西大学 | Hedgerow trimmer bearing mechanism with self-adapting function |
| CN106864249A (en) * | 2015-12-11 | 2017-06-20 | 成都德善能科技有限公司 | Electric motor car |
| US20180001887A1 (en) * | 2016-06-30 | 2018-01-04 | Aisin Seiki Kabushiki Kaisha | Traveling support device |
| US20200081436A1 (en) * | 2017-06-02 | 2020-03-12 | Honda Motor Co., Ltd. | Policy generation device and vehicle |
| CN109466268A (en) * | 2017-09-08 | 2019-03-15 | 松下知识产权经营株式会社 | Moving body |
| CN111201554A (en) * | 2017-10-17 | 2020-05-26 | 本田技研工业株式会社 | Travel model generation system, vehicle in travel model generation system, processing method, and program |
| US20190361456A1 (en) * | 2018-05-24 | 2019-11-28 | GM Global Technology Operations LLC | Control systems, control methods and controllers for an autonomous vehicle |
| US20200033869A1 (en) * | 2018-07-27 | 2020-01-30 | GM Global Technology Operations LLC | Systems, methods and controllers that implement autonomous driver agents and a policy server for serving policies to autonomous driver agents for controlling an autonomous vehicle |
| US20200156431A1 (en) * | 2018-11-19 | 2020-05-21 | Hyundai Motor Company | Apparatus and method for controlling lift axle of vehicle |
| CN111622293A (en) * | 2019-02-28 | 2020-09-04 | 斗山英维高株式会社 | Control method and system of wheel loader |
| US20200307692A1 (en) * | 2019-03-28 | 2020-10-01 | Volkswagen Aktiengesellschaft | On-road localization methodologies and equipment utilizing road surface characteristics |
| WO2020239099A1 (en) * | 2019-05-29 | 2020-12-03 | 张大朋 | Electric vehicle, automatic driving method and equipment, automatic freight transportation method and system |
| US20210024081A1 (en) * | 2019-07-09 | 2021-01-28 | Refraction Ai, Inc. | Method and system for autonomous vehicle control |
| CN110606142A (en) * | 2019-08-15 | 2019-12-24 | 燕山大学 | Series-parallel supporting leg based on ground sealing and movable posture adjusting platform thereof |
| CN110758042A (en) * | 2019-10-10 | 2020-02-07 | 点狮科技(浙江)有限公司 | Self-balancing moving platform and self-balancing moving method |
| CN110775877A (en) * | 2019-11-27 | 2020-02-11 | 扬州力德工程技术有限公司 | AGV intelligent trolley and control method thereof |
Non-Patent Citations (4)
| Title |
|---|
| ANONYMOUS: "《IP.COM非专利全文库》", 11 October 2001, IP.COM * |
| 吴伟斌等: "基于模糊PID的山地果园运输机动力稳定系统的设计与试验", 《湖南农业大学学报(自然科学版)》 * |
| 姬晓等: "四轮独立驱动电动汽车驱动控制策略研究", 《汽车实用技术》 * |
| 张斌等: "改进DDPG算法在自动驾驶中的应用", 《计算机工程与应用》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113291142B (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102331677B1 (en) | Inertia adjustment active suspension system and control method based on vehicle attitude deviation | |
| DE60102335T2 (en) | Suspension device with an electric actuator with a parallel spring | |
| DE69131595T2 (en) | METHOD AND DEVICE FOR DYNAMIC LEVEL REGULATION | |
| CN105480299B (en) | Homing guidance can configure trackless launch train and progress control method | |
| JP2962046B2 (en) | Suspension vibration input estimation device | |
| CN103434359B (en) | Multi-target control method of automobile driving suspension system | |
| CN105539052B (en) | A kind of controllable suspension sliding formwork tracking controller using vehicle plateau as reference | |
| EP0541735A1 (en) | System for generating signals to control or regulate a chassis of which the movement cycles can be controlled or regulated | |
| CN110949366A (en) | Terminal sliding mode control method of RBF neural network applying intelligent vehicle longitudinal speed control | |
| CN114379583A (en) | Automatic driving vehicle trajectory tracking system and method based on neural network dynamics model | |
| CN111596671A (en) | Unmanned intelligent sweeper track tracking control method and system | |
| JP2023541311A (en) | Vehicle active suspension inertia control method and control system based on wheel support force | |
| US20230017774A1 (en) | Proactive control of vehicle systems | |
| CN113291142B (en) | Intelligent driving system and control method thereof | |
| CN107985404A (en) | A kind of automobile lateral stability control device | |
| Muhammed et al. | Linear-control vs. ADRC for automatic management of the handling-comfort contradiction of a quarter-car system | |
| Freitas et al. | Terrain model-based anticipative control for articulated vehicles with low bandwidth actuators | |
| CN115107904B (en) | Reconfigurable wheel-track universal distributed driving unmanned vehicle and control method thereof | |
| CN116882096A (en) | Wheel-leg type multi-mode unmanned platform vibration reduction control method, system and equipment | |
| US20210394575A1 (en) | Vehicle and methods for improving stability and occupant comfort | |
| AU2022202485A1 (en) | Sprayer boom control for improved ride and control | |
| Ding et al. | The design of automotive electronic control suspension system based on digital simulation | |
| US20240166011A1 (en) | System and method for an agricultural vehicle | |
| US20240166004A1 (en) | System and method for an agricultural vehicle | |
| Cronje | Improving off-road vehicle handling using an active anti-roll bar |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |