Intelligent transportation platform

Abstract

The invention discloses an intelligent transportation platform, belongs to the technical field of intelligent manufacturing, and realizes seamless switching among a manual mode, a semi-automatic mode and an automatic mode through collaborative design of a manual lock and a power connector. By arranging a multi-source heterogeneous sensor, the target detection precision is improved; the steering angle and speed are adjusted through the horizontal rotator and the pitching rotator; the electromagnetic brake assembly is combined with sensors such as a gyroscope, and operation safety and posture stability are guaranteed. The platform solves the problems that a traditional structure is complex in switching and strenuous in operation, and is suitable for efficient transportation in complex scenes.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent transportation platform. Background Art

[0002] With the rapid development of automation technology, automatic transportation platforms are increasingly used in logistics, warehousing, intelligent manufacturing, public services and other fields. The key technology for the application of automatic transportation platforms lies in improving target detection accuracy and intelligent control.

[0003] Traditional transportation platforms often rely on a single sensor (such as lidar or millimeter-wave radar) for environmental perception and target tracking. These sensors are often limited by performance in complex scenarios, leading to reduced tracking accuracy or even failure. For example, vision systems struggle to stably detect targets in low-light or obstructed environments. While millimeter-wave radar offers strong penetration and robust interference resistance, it lacks the ability to precisely identify target types.

[0004] Traditional automated transport platforms typically use mechanical clutches or electromagnetic relays to switch between manual and automatic modes. Mechanical clutches require manual operation, are cumbersome to switch, and are prone to wear, leading to unstable power transmission. While electromagnetic relays can achieve electronic switching, they are complex and costly, and can cause current surges during switching, impacting system life.

[0005] In terms of mode control, the manual and automatic modes of existing platforms are usually designed independently. In manual mode, the connection between the motor power output and the manually operated components lacks flexibility, making it impossible to achieve seamless switching between manual and automatic modes. Power interruptions or shocks may occur during the switching process, affecting the stability and reliability of the transport platform. In manual mode, the resistance of the motor increases the labor intensity of the operator. For example, for a trolley-type transport platform, when the trolley is manually pushed, the motor is still connected to the transmission system, generating greater resistance and making the operation laborious. When the automatic mode is switched back to manual mode, complex initialization settings are required, which wastes time and reduces work efficiency. In addition, due to the independent design of manual and automatic modes, the control algorithm needs to process a large amount of mode switching logic, which increases the difficulty and cost of software development and also reduces the response speed of the system. Summary of the Invention

[0006] The purpose of the present invention is to overcome the technical problems existing in existing transportation platforms and provide an intelligent transportation platform.

[0007] The object of the present invention is achieved through the following technical solutions:

[0008] Provided is an intelligent transportation platform, comprising:

[0009] A vehicle body, which is provided with a frame plate and a material box arranged on the frame plate;

[0010] Front wheels and rear wheels are arranged under the vehicle body, wherein the rear wheels include a left wheel and a right wheel that are arranged symmetrically on the left and right sides;

[0011] The power motors are symmetrically arranged on the left and right sides and are connected to the left and right wheels via power output shafts respectively;

[0012] A power connector, a manual lock, and a wheel lock switch are provided on the rear wheel. The manual lock includes a retractable manual lock tongue, which is used to extend in automatic mode to engage with the power connector to transmit power from the power motor to the corresponding wheel, and retract in manual mode to disconnect power from the power motor. The wheel lock switch is used to manually control the extension and retraction of the manual lock tongue.

[0013] A handlebar connected to the frame via a connecting rod, the connecting rod being provided with a horizontal rotator and a pitch rotator; the handlebar being provided with a multi-source heterogeneous sensor; in automatic mode, the horizontal rotator and the pitch rotator are used to adjust the angle of the multi-source heterogeneous sensor; in semi-automatic mode, the horizontal rotator is used to detect the manual steering angle, and the pitch rotator is used to adjust the forward speed;

[0014] A hand brake assembly, comprising a left-hand brake lever and a right-hand brake lever provided on the handlebar;

[0015] an automatic brake assembly, disposed on the vehicle body;

[0016] A main control board is arranged on the vehicle body and is connected to the power motor, the horizontal rotator, the multi-source heterogeneous sensor and the automatic brake component.

[0017] In some embodiments, the multi-source heterogeneous sensor includes a binocular camera and a millimeter-wave radar.

[0018] In some embodiments, a gyroscope is provided on the connecting rod, and the gyroscope is connected to the main control board via an I2C bus for real-time detection of the platform attitude and angular velocity.

[0019] In some embodiments, the pitch rotator is used to adjust the forward speed, including:

[0020] The pitch rotator changes the resistance value of the potentiometer by pressing down or lifting up to adjust the output power of the power motor.

[0021] In some embodiments, the pitch rotator has a built-in limit block.

[0022] In some embodiments, the automatic brake assembly is an electromagnetic brake assembly, and the electromagnetic brake assembly is connected to a power supply circuit of the power motor.

[0023] In some embodiments, a quick-release switch is provided on the material box, and the left and right sides of the material box are fixed by baffles.

[0024] In some embodiments, the front wheels are universal wheels.

[0025] In some embodiments, a symmetrical mechanical connection structure is used between the power motor and the rear wheel to ensure synchronization of left and right power output.

[0026] In some embodiments, the pitch rotator housing is provided on the pitch rotator.

[0027] It should be further explained that the technical features corresponding to the above embodiments can be combined or replaced with each other to form a new technical solution if there is no conflict.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] This invention utilizes multi-source heterogeneous sensors to track targets using multiple sensor types, reducing reliance on a single sensor and improving target detection accuracy. The collaborative design of a manual lock and power connector enables seamless switching between manual, semi-automatic, and automatic modes. Steering angle and speed are adjusted using horizontal and vertical rotators. Electromagnetic brake assemblies, combined with sensors such as gyroscopes, ensure operational safety and posture stability. This platform forms a highly efficient control system integrating power transmission, steering control, speed regulation, and safe braking, enabling reliable operation and flexible mode switching for intelligent transportation platforms in complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a bottom view of the right side of an intelligent transportation platform shown in an embodiment of the present invention;

[0031] Figure 2 This is a left side top view of an intelligent transportation platform shown in an embodiment of the present invention;

[0032] Figure 3 A wheel structure diagram of an intelligent transportation platform according to an embodiment of the present invention;

[0033] In the figure: 1-right brake handle; 2-left brake handle; 3-horizontal rotator; 4-pitch rotator; 5-pitch rotator housing; 6-gyroscope; 7-material box; 8-power bracket; 9-automatic brake assembly; 10-battery compartment; 11-frame plate 11; 12-front wheel; 13-power output shaft; 14-left wheel; 15-left baffle of material box; 16-wheel lock switch; 17; manual lock; 18-manual lock tongue; 19-power connector; 20-wheel hub; 21-wheel hub connecting rod; 22-tire; 23-right camera; 24-millimeter wave radar; 25-right camera; 26-connecting rod; 27-main control board; 28-right baffle of material box; 29-right wheel; 30-right power motor; 31-left power motor; 32-quick release switch. DETAILED DESCRIPTION

[0034] The technical solutions of the present invention are described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings herein can be arranged and designed in various different configurations. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0035] It should be noted that the defects existing in the solutions in the above-mentioned prior art are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above-mentioned problems and the solutions proposed in the embodiments of this application below for the above-mentioned problems should be the contributions made by the inventor to this application in the process of invention and creation, and should not be understood as technical contents known to technical personnel in this field.

[0036] In response to the technical problems pointed out in the background technology, the embodiments provided by the present invention are as follows:

[0037] Reference Figure 1-Figure 3 In an exemplary embodiment, an intelligent transportation platform is provided, which is a small vehicle and includes:

[0038] A vehicle body, on which a frame plate 11 and a material box 7 are provided on the frame plate 11;

[0039] Front and rear wheels disposed under the vehicle body, the rear wheels comprising a left wheel 14 and a right wheel 29 disposed symmetrically on the left and right;

[0040] The left and right symmetrically arranged power motors (mounted on the power bracket 8) include a left power motor 31 and a right power motor 30, which are connected to the left wheel 14 and the right wheel 29 respectively through the power output shaft 13;

[0041] The rear wheels are provided with a power connector 19, a manual lock 17, and a wheel lock switch 16. The manual lock 17 includes a retractable manual lock tongue 18, which is used to extend in automatic mode to engage with the power connector 19 to transmit power from the power motor to the corresponding wheel, and retract in manual mode to disconnect power from the power motor. The wheel lock switch 16 is used to manually control the extension and retraction of the manual lock tongue 18.

[0042] The handlebars are connected to the frame via a connecting rod 26, on which a horizontal rotator 3 and a pitch rotator 4 are provided. The handlebars are provided with a multi-source heterogeneous sensor. In automatic mode, the horizontal rotator 3 and the pitch rotator 4 are used to adjust the angle of the multi-source heterogeneous sensor. In semi-automatic mode, the horizontal rotator 3 is used to detect the manual steering angle, and the pitch rotator 4 is used to adjust the forward speed.

[0043] A manual brake assembly, comprising a left brake handle 2 and a right brake handle 1 arranged on the handlebar;

[0044] An automatic brake assembly 9, arranged on the vehicle body;

[0045] The main control board 27 is arranged on the vehicle body and is connected to the power motor, the horizontal rotator 3, the multi-source heterogeneous sensor and the automatic brake component 9.

[0046] In this example, the multi-source heterogeneous sensor includes a binocular camera and a millimeter wave radar 24. Figure 1 As shown in the figure, the binocular camera consists of a left camera mounted on the left handlebar and a right camera mounted on the right handlebar. By setting up multi-source heterogeneous sensors, multi-type sensing and tracking of targets are performed, reducing dependence on a single sensor. At the same time, combined with certain sensor data fusion methods, target detection accuracy is improved.

[0047] In this example, a gyroscope 6 is provided on the connecting rod 26 , and the gyroscope 6 is connected to the main control board 27 via an I2C bus for detecting the posture and angular velocity of the vehicle in real time.

[0048] In this example, the automatic brake assembly 9 is an electromagnetic brake assembly connected to the power circuit of the power motor (the battery is located in the battery compartment 10). The material box 7 is provided with a quick-release switch 32, and the left and right sides of the material box 7 are fixed by baffles (the right baffle 28 and the left baffle 15).

[0049] In this example, the front wheels are universal wheels, enabling arbitrary steering operations.

[0050] In this example, a symmetrical mechanical connection structure is used between the power motor and the rear wheel to ensure synchronization of left and right power output.

[0051] In this example, the pitch rotator 4 is provided with the pitch rotator housing 5 to provide certain protection for the pitch rotator 4 .

[0052] Further, if Figure 3 As shown, the rear wheel structure includes a manual lock 17 (in this example, X6), a manual lock tongue 18, a power connector 19, an inner wheel hub 20, a wheel hub connecting rod 21, and a tire 22. In semi-automatic and automatic modes, the manual lock tongue 18 extends and connects to the power connector 19. The power source is the power motor output. In manual mode, the manual lock tongue 18 retracts to disconnect the power, reducing the effort required to push the vehicle. The extension and retraction of the manual lock tongue 18 is manually activated by the wheel lock switch 16.

[0053] The left-hand brake handle 2 and the right-hand brake handle 1 have two functions: an emergency brake and a switch to semi-automatic operation. In automatic mode, the vehicle automatically tracks targets detected by the radar and camera. The horizontal rotator 3 and the pitch rotator 4 adjust different angles for real-time tracking. In semi-automatic mode, the horizontal rotator 3 is used for angle sensing for left and right turns. The pitch rotator 4 adjusts the vehicle's forward speed. Pressing down faster results in slower speeds when lifting up. The power motor now generates power. The automatic brake assembly 9 can be activated in both semi-automatic and automatic modes.

[0054] Furthermore, the left power motor 31 and the right power motor 30 work in coordination with various actuators through a precise mechanical structure and control link, ensuring flexible control of the automatic transport platform in different modes.

[0055] In the power transmission system, the left power motor 31 is connected to the inner wheel hub 20, the hub connecting rod 21, and the tire 22 via the power output shaft 13, driving the left wheel 14. The right power motor 30 is symmetrically connected to the right wheel 29, driving the right wheel 29. Both motors work with the manual lock 17 via the power connector 19 to achieve manual / automatic power switching: in automatic mode, the manual lock tongue 18 extends and engages the power connector 19, and the power of the power motor is transmitted to the wheel through the transmission assembly; in manual mode, the manual lock tongue 18 retracts and disconnects, allowing the wheel to rotate freely to facilitate manual pushing.

[0056] In the actuator component, the horizontal rotator 3 receives commands from the main control board 27 in automatic mode to adjust the steering angle and control the wheel steering. In semi-automatic mode, the horizontal rotator 3 acts as an angle sensor, transmitting the manual steering angle signal to the main control board 27, enabling precise analysis and control of the steering angle. The pitch rotator 4 is connected to the pitch rotator housing 5 and the motor speed control module (located in the main control board 27). In semi-automatic mode, the potentiometer resistance is adjusted to change the motor output power by pressing down or lifting up, achieving speed control. Pressing down accelerates (maximum 1.5 m / s) and lifting up decelerates (minimum 0.3 m / s). Built-in limit blocks prevent overuse. The automatic brake assembly 9 uses electromagnetic brakes and is connected to the left and right motor power circuits. In an emergency, the right brake handle 1 or the left brake handle 2 triggers a brake signal, cutting off the power supply and achieving emergency braking. In both semi-automatic and automatic modes, the platform brakes smoothly according to the control command, ensuring a safe stop.

[0057] The connection between sensors and motors ensures intelligent control of the system. The gyroscope 6 detects the platform's attitude and angular velocity in real time, transmitting this data to the main control board 27 via the I2C bus. This data is used to adjust the left and right motor speeds and steering to maintain platform balance. The wheel lock switch 16 manually controls the manual lock tongue 18, switching the power connection. In manual mode, feedback is provided to the main control board 27 via motor speed and operating current (when speed is stable, the current is significantly lower than the operating current), allowing the system to adjust the control strategy (path planning is disabled in manual mode, and sensor fusion is enabled in automatic mode).

[0058] Through the above-mentioned connection relationship, the left and right motors work together with the horizontal rotator 3, pitch rotator 4, brake assembly and other actuators, as well as the gyroscope 6, wheel lock switch 16 and other sensors to form an efficient control system integrating power transmission, steering control, speed regulation and safety braking, realizing the reliable operation and flexible mode switching of the automatic transport platform in complex scenarios.

[0059] Furthermore, the example provides a method for the car to use fused sensor data for path planning, specifically including:

[0060] The binocular camera uses a target detection algorithm (such as YOLOv11) to process the images captured by the camera to identify and locate the targets in the image. The output includes the bounding box and category of the target. The target detection algorithm divides the image into multiple grids and predicts whether the target exists in each grid. It then directly outputs the bounding box coordinates (x, y, w, h) and confidence level. Then, for each frame of the image, the center coordinates (x, y) of the target are extracted. Based on these coordinates, the direction and speed of the person's movement are calculated by the changes between consecutive frames. Specifically, it includes:

[0061] Motion tracking: The motion tracking algorithm uses a Kalman filter to track the position of the target in different frames. By calculating the changes between each frame, the direction and speed of the person's movement are obtained.

[0062] Speed and direction calculation: Calculate the speed of the target based on the changes in the target coordinates in consecutive image frames. The speed is obtained by dividing the displacement between two frames by the time interval: the specific calculation formula is as follows:

[0063]

[0064] The direction is obtained by calculating the change in coordinates between the two frames. The method is: in two consecutive frames, the position coordinates of the target in the image (x1, y1) and (x2, y2) are obtained, and the direction angle θ is calculated as follows:

[0065] θ=atan2(y2-y1,x2-x1)

[0066] This method can be used to calculate the direction angle between -180 degrees and 180 degrees.

[0067] In target tracking, millimeter-wave radar accurately measures target distance and estimates target speed by transmitting and receiving millimeter waves. Specifically, it includes:

[0068] Signal processing: Millimeter-wave radar measures the time difference between the reflected electromagnetic waves it transmits and the reflected time, calculating the target's distance using the wave speed and reflection time. It also calculates the target's relative speed using the Doppler effect.

[0069] Target positioning: The reflected signal of the millimeter-wave radar provides the distance between the target and the radar. Combining multiple measurements at different angles, the target's position can be determined. The radar antenna in this invention is an antenna array that can perform angle measurement.

[0070] Movement direction and speed: Millimeter-wave radar uses the Doppler effect to calculate the speed, and then obtains the target's movement trajectory and direction through continuous measurement.

[0071] The formula for speed calculation is:

[0072]

[0073] Where c is the speed of light, f0 is the operating frequency of the radar, Δf is the frequency shift, and v is the velocity of the target.

[0074] Furthermore, because the binocular camera processes image data at a frame rate of 30Hz to 60Hz, while the millimeter-wave radar provides data at 10Hz to 20Hz. To synchronize these data streams and improve accuracy, a buffer is used to store binocular camera and millimeter-wave radar data for a certain period of time. The two data streams are then aligned and fused using a Kalman filter synchronization algorithm.

[0075] The fusion algorithm's workflow involves setting the system's state equation and separately modeling the binocular camera and millimeter-wave radar data. The two sensor measurements are then weighted and fused to ultimately achieve the optimal state estimate. The fusion algorithm, with its adaptive noise handling capabilities, uses visual and radar measurements as observation inputs and, through prediction and update steps, obtains the fused target state.

[0076] Specific implementation process of data fusion:

[0077] 1. Setting the system state equation

[0078] Assume that the state vector of the target in the two-dimensional plane is x = [x, y, vx, vy] T, where (x, y) is the target position and (vx, vy) is the target velocity. The state transition equation is:

[0079] x k =Ax k-1 +Bu k-1 +w k

[0080] Among them, x k Represents the state variable at the current moment, x k-1 is the state variable at the previous moment, u k-1 is the input variable of the previous moment, A is the state transfer matrix, which describes how the system state transfers from one moment to the next, △t is the time interval; B is the control input matrix, where it is assumed that the target moves at a uniform speed, u k-1 =0;w k is process noise, which obeys a Gaussian distribution with a mean of 0 and a covariance of Q. The state transfer matrix is as follows:

[0081]

[0082] 2. Vision and radar data modeling

[0083] Binocular camera: output target center coordinates (xv, yv), the measurement equation is zv = H v x+V v , where V v is the visual measurement noise, and the covariance matrix is defined as R v , H v Represents the visual measurement matrix. The two matrices are as follows:

[0084]

[0085]

[0086] Among them, σ vx 2 and σ vy 2 They represent the variance of the visual sensor’s measurement noise in the x-direction and y-direction respectively.

[0087] Millimeter-wave radar: Outputs target distance r and velocity vr, and obtains target position (xr, yr) and velocity (vrx, vry) through coordinate conversion. The measurement equation is zr = H r x+V r , where H r is the radar measurement matrix, V r is the radar measurement noise, and the covariance matrix is defined as R r .

[0088] 3. Weighted fusion and Kalman filtering steps

[0089] Prediction steps:

[0090]

[0091] P k|k-1 =AP k-1|k-1 A T +Q

[0092] in, It represents the predicted value of the state at time k based on all the information at time k-1. It represents the optimal estimate based on all the information at time k-1, P k|k-1 P represents the covariance matrix of the state estimate at time k based on all the information at time k-1. k-1|k-1 represents the covariance matrix of the optimal estimate obtained at time k-1 based on all the information at time k-1. Q represents the process noise covariance matrix, which describes the uncertainty in the system model.

[0093] Update steps:

[0094] Calculating Kalman Gain for Vision and Radar:

[0095]

[0096] Among them, K v，k is the Kalman gain of the visual sensor (binocular camera) at time k, K r，k is the Kalman gain of the millimeter-wave radar at time k.

[0097] Calculate the state updates of vision and radar separately:

[0098]

[0099] in, and are the state estimates based on the visual sensor and millimeter-wave radar at time k respectively. is the predicted state value, the same as in the state prediction step. v , k represents the actual measurement value of the binocular camera at time k, z r , k represents the actual measurement value of the millimeter-wave radar at time k.

[0100] Weighted fusion state estimation:

[0101]

[0102] in, Represents the final state estimate obtained by weighted fusion of the measurements of the visual sensor and the radar sensor at time k. v ) represents R v trace, tr(R r ) represents R r traces, Indicates the target state update corresponding to the binocular camera, Represents the target state update corresponding to the millimeter-wave radar. The trace of the covariance matrix is used to measure the magnitude of the sensor measurement noise, and the weight is inversely proportional to the noise.

[0103] Covariance update:

[0104] P k|k =(IK k H k ) Pk|k-1

[0105] Among them, P k|k represents the covariance matrix of the optimal estimate obtained at time k based on all the information at time k. I is the identity matrix, which is used to ensure the dimensional consistency of matrix operations. K k and H k are the fused gain matrix and measurement matrix respectively.

[0106] Aiming at the frequency difference between visual and radar data, the present invention adopts a buffer combined with a Kalman filter synchronization algorithm to achieve time alignment, introduces a weighted average algorithm, and dynamically assigns weights according to the visual pixel error and the radar range error covariance to improve the fusion accuracy.

[0107] After obtaining the fused target state through the fusion method, path planning is performed. Specifically, the optimal path is calculated based on the path planning and obstacle avoidance algorithm. The core purpose of the path planning and obstacle avoidance algorithm is to calculate the optimal path based on the target position and obstacles in the environment. The algorithm optimizes the search process by the distance between the target position and the current position. The algorithm combines breadth-first search and greedy algorithms, divides the path into multiple nodes, evaluates the cost of each node, and calculates the shortest path from the starting point to the end point without building a map in advance. In complex environments, the path planning algorithm combines synchronous positioning and map building technology to generate dynamic maps and path planning, and adjusts the path in real time to avoid new obstacles.

[0108] The specific implementation process of the path planning and obstacle avoidance algorithm is as follows:

[0109] 1. Environment modeling and node division

[0110] The current environment is divided into a grid, with each grid cell representing a node. Node coordinates are (i, j), where i and j are grid indices. Node status includes whether it is an obstacle or reachable. A node graph is constructed, starting from the current position of the autonomous transport platform and ending at the target location.

[0111] 2. Cost function definition

[0112] Distance cost:

[0113]

[0114] Among them, x n Represents the horizontal coordinate of the node on the two-dimensional plane, y n Represents the vertical coordinate of the node on the two-dimensional plane, x goal Indicates the horizontal coordinate of the target point on the two-dimensional plane, y goal Indicates the vertical coordinate of the target point on the two-dimensional plane, g dist (n) represents the Euclidean distance from node n to the target location, guiding the path towards the target.

[0115] Obstacle cost: If node n is an obstacle, then gobs(n) = ∞; otherwise gobs(n) = 0, ensuring that the path avoids obstacles.

[0116] Turning cost: gturn(n) = θprev,n, where θprev,n is the turning angle between the current node and the previous node, to avoid frequent path turns.

[0117] The comprehensive cost function is: g total (n) = αg dist (n)+βg obs (n)+γg 转向 (n)

[0118] Among them, α, β, and γ are weight coefficients, which are adjusted dynamically according to the environment.

[0119] 3. Path search and optimization

[0120] Search initialization: add the starting point to the queue and record the shortest distance from the starting point to each node.

[0121] The greedy strategy selects the next node: select the node with the smallest comprehensive cost in the queue as the current node, and expand its adjacent nodes (up, down, left, right, upper left, lower left, upper right, lower right).

[0122] Real-time obstacle detection and path adjustment: When a new obstacle is detected, the obstacle node status is updated, the node cost of the affected area is recalculated, and the path search is restarted from the current position.

[0123] Path smoothing: Bezier curve fitting is performed on the generated path to reduce inflection points and make the transport platform run more smoothly.

[0124] 4. Combining simultaneous positioning and map construction

[0125] This part is the core technology for autonomous transportation platforms to achieve autonomous navigation in environments without prior maps. By integrating visual and millimeter-wave radar data, it estimates the platform's position in real time and constructs an environmental map, providing dynamically updated, high-precision environmental information for path planning. The following are the specific implementation details:

[0126] 4.1. Simultaneous Positioning and Mapping System Status Definition

[0127] Platform posture state: Let the posture vector of the platform in the two-dimensional plane be s = [x, y, θ] T , where (x, y) is the position of the platform in the global coordinate system (unit: meter); θ is the platform heading angle (unit: radian, defined as the angle between the platform axis and the positive direction of the x-axis).

[0128] Environmental feature state: static obstacles and dynamic features in the environment are modeled as a feature point set m = [m1, m2, m n ] T , each feature point m i =[x i ,y i ] T ) represents its position in the global coordinate system.

[0129] System state vector: Combine the posture and environment features to form an extended state vector: X = [S T ,m T ] T .

[0130] 4.2. Implementation of a simultaneous positioning and mapping system

[0131] State transition model:

[0132] Assume that an automatic transport platform adopts wheel drive, including front wheels and driven rear wheels, and the driven rear wheels include left and right wheels. The platform motion adopts differential drive model. Assume that the speeds of the left and right wheels are v l and v r (Unit: m / s), then within the time interval △t, the pose update equation is:

[0133]

[0134] Where, L is the wheelbase of the left and right wheels (unit: meter); w x ,w y ,w θ The process noise obeys Gaussian distribution, and the covariance matrix is Q.

[0135] Observation model:

[0136] Visual sensor observation: The visual module detects environmental feature points (such as corners and landmarks) through YOLOv11. After coordinate transformation, the coordinates (u, v) of the feature points in the camera coordinate system are obtained and converted into the observation equation in the global coordinate system:

[0137]

[0138] Millimeter-wave radar observation: The radar detects the distance r and angle Φ of the target and converts them into the observation equation in the global coordinate system:

[0139]

[0140] The iterative steps of the algorithm are as follows:

[0141] 1. Prediction stage

[0142] Pose prediction:

[0143] Covariance prediction:

[0144] in, represents the predicted value of the system state s at time k based on all the information at time k-1\. f(.) is the state transition function, which describes how the system state transitions from one moment to the next. Represents the optimal estimate of the system state at time k-1 based on all the information at time k-1. l Indicates the speed of the left wheel of the transport platform, υ rIndicates the speed of the right wheel of the transport platform. F k-1 is the Jacobian matrix of the state transfer matrix.

[0145] 2. Update phase

[0146] Calculate the observation Jacobian matrix H v,k and H r,k Among them, H v,k Represents the visual sensor observation equation for the state vector X The first-order partial derivative matrix at ; H r,k Represents the millimeter wave radar observation equation for the state vector X in The first-order partial derivative matrix at .

[0147] Algorithm gain: Among them, K k is the Kalman gain matrix, which determines how much we should trust the measured and predicted values when updating the state estimate. k H v,k and / H r,k， Depends on which sensor is used for observation. k The measurement noise covariance matrix describes the uncertainty in the measurement process.

[0148] Status Update: in, Represents the predicted state value, which is the same as the state prediction step Similarly, X here is the extended state vector, which contains information such as system state and environmental characteristics. According to the predicted status The calculated predicted value of the measurement.

[0149] Covariance update: P k|k =(IK k H k )P k|k-1 .

[0150] 3. Map Update

[0151] When a new feature point is detected, it is added to the environment feature vector m, the state vector is expanded and the covariance matrix is updated to achieve incremental construction of the map.

[0152] This method achieves complementary perception of environmental information by combining multi-source heterogeneous sensors; uses Kalman filtering and weighted averaging algorithms to time synchronize and suppress noise in heterogeneous frequency sensor data, ensuring temporal consistency and spatial matching of the data and improving target positioning accuracy; at the same time, combined with an improved path planning algorithm, it dynamically generates obstacle avoidance paths in scenarios without prior maps.

[0153] The above specific implementation methods are detailed descriptions of the present invention. It cannot be considered that the specific implementation methods of the present invention are limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, they can make several simple deductions and substitutions without departing from the concept of the present invention, which should be regarded as falling within the scope of protection of the present invention.

Claims

1. An intelligent transportation platform, characterized in that: include: A vehicle body, which is provided with a frame plate and a material box arranged on the frame plate; Front wheels and rear wheels are arranged under the vehicle body, wherein the rear wheels include a left wheel and a right wheel that are arranged symmetrically on the left and right sides; The power motors are symmetrically arranged on the left and right sides and are connected to the left and right wheels via power output shafts respectively; A power connector, a manual lock, and a wheel lock switch are provided on the rear wheel. The manual lock includes a retractable manual lock tongue, which is used to extend in automatic mode to engage with the power connector to transmit power from the power motor to the corresponding wheel, and retract in manual mode to disconnect power from the power motor. The wheel lock switch is used to manually control the extension and retraction of the manual lock tongue. A handlebar connected to the frame via a connecting rod, the connecting rod being provided with a horizontal rotator and a pitch rotator; the handlebar being provided with a multi-source heterogeneous sensor; in automatic mode, the horizontal rotator and the pitch rotator are used to adjust the angle of the multi-source heterogeneous sensor; in semi-automatic mode, the horizontal rotator is used to detect the manual steering angle, and the pitch rotator is used to adjust the forward speed; A hand brake assembly, comprising a left-hand brake lever and a right-hand brake lever provided on the handlebar; an automatic brake assembly, disposed on the vehicle body; A main control board is arranged on the vehicle body and is connected to the power motor, the horizontal rotator, the multi-source heterogeneous sensor and the automatic brake component.

2. The intelligent transportation platform according to claim 1, characterized in that: The multi-source heterogeneous sensor includes a binocular camera and a millimeter-wave radar.

3. The intelligent transportation platform according to claim 1, characterized in that: The connecting rod is provided with a gyroscope, which is connected to the main control board via an I2C bus and is used for real-time detection of the platform attitude and angular velocity.

4. The intelligent transportation platform according to claim 1, characterized in that: The pitch rotator is used to adjust the forward speed and includes: The pitch rotator changes the resistance value of the potentiometer by pressing down or lifting up to adjust the output power of the power motor.

5. The intelligent transportation platform according to claim 1, characterized in that: The pitch rotator has a built-in limit block.

6. The intelligent transportation platform according to claim 1, characterized in that: The automatic brake assembly is an electromagnetic brake assembly, and the electromagnetic brake assembly is connected to the power supply circuit of the power motor.

7. The intelligent transportation platform according to claim 1, characterized in that: The material box is provided with a quick release switch, and the left and right sides of the material box are fixed by baffles.

8. The intelligent transportation platform according to claim 1, characterized in that: The front wheels are universal wheels.

9. The intelligent transportation platform according to claim 1, characterized in that: A symmetrical mechanical connection structure is adopted between the power motor and the rear wheel to ensure the synchronization of left and right power output.

10. The intelligent transportation platform according to claim 1, characterized in that: The pitch rotator is provided with the pitch rotator housing.

Images