Vehicle motion trail prediction method and system based on quantum computing

Abstract

The invention discloses a vehicle motion trail prediction method and system based on quantum computing, and relates to the technical field of vehicles, and the method comprises the steps: recording the basic information of a vehicle, and detecting environment data through a plurality of sensors; monitoring the emotion of the driver by using a brain-computer interface, and evaluating the driving intention of the driver; based on the basic information of the vehicle, kinematics parameters of the vehicle are calculated, and a driver behavior information base is constructed in combination with the environment data and the driving intention of the driver; preliminarily predicting the path of the vehicle, evaluating the possibility by using quantum calculation, and outputting an optimal path; and calculating an ideal transverse position of the vehicle according to the latest environmental data and the basic information of the vehicle, and integrating the kinematics parameters and the optimal path to obtain a predicted complete motion track of the vehicle. By introducing the brain-computer interface technology, the emotional state of the driver is monitored in real time, the driving intention of the driver is evaluated, and the accuracy of vehicle motion trail prediction is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and particularly to a vehicle motion trajectory prediction method and system based on quantum computing. Background Art

[0002] With the rapid development of autonomous driving technology, vehicle motion trajectory prediction has become a key research area in intelligent transportation systems. In recent years, sensor-based environmental perception and data fusion technologies have been widely applied. In particular, the combination of multiple sensors such as lidar, cameras, and radars enables vehicles to obtain real-time information about the surrounding environment. At the same time, the progress of brain-computer interface (BCI) technology has also provided new possibilities for driver emotion monitoring. By analyzing the driver's brain wave signals and facial expressions in real time, the understanding and prediction ability of driving behavior have been further enhanced. However, the existing technologies still face many deficiencies in dealing with complex traffic environments. First, traditional prediction methods often ignore the influence of the driver's emotions and intentions on driving behavior, which may lead to poor prediction accuracy. Second, the existing technologies lack an effective risk assessment mechanism in path planning. Summary of the Invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a vehicle motion trajectory prediction method based on quantum computing to solve the problems of neglecting the driver's emotions and intentions in the existing vehicle motion trajectory prediction model and lacking an effective risk assessment mechanism.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a vehicle motion trajectory prediction method based on quantum computing, which includes tracking the vehicle, recording the basic information of the vehicle, and detecting environmental data using multiple sensors;

[0007] Monitoring the driver's emotions using a brain-computer interface and evaluating the driver's driving intention;

[0008] Based on the basic information of the vehicle, calculating the kinematic parameters of the vehicle, and combining the environmental data and the driver's driving intention to construct a driver behavior information database;

[0009] Matching the current environmental data and the current driver's driving intention in the driver behavior information database, making a preliminary prediction of the vehicle's path, and using quantum computing to evaluate the possibility and output the optimal path;

[0010] According to the latest environmental data and the basic information of the vehicle, calculating the ideal lateral position of the vehicle, integrating the kinematic parameters and the optimal path to obtain the predicted complete motion trajectory of the vehicle.

[0011] As a preferred solution of the vehicle motion trajectory prediction method based on quantum computing according to the present invention, wherein: the multiple sensors include cameras, radars, lidars, and acoustic sensors;

[0012] The environmental data includes the number and position of obstacles in the environment, the number and position of lane lines, the number and position of traffic signals, and the number and position of pedestrians;

[0013] The basic vehicle information includes the initial position, speed, and heading angle;

[0014] The kinematic parameters include the position change rate, heading angle change rate, and acceleration.

[0015] As a preferred solution of the vehicle motion trajectory prediction method based on quantum computing according to the present invention, wherein: a brain-computer interface is used to monitor the driver's emotions and evaluate the driver's driving intention, including the following steps,

[0016] Start the BCI device to capture the driver's brain wave signals in real time;

[0017] Analyze the brain wave signals through a band-pass filter, wavelet transform, and support vector machine to identify the emotional state;

[0018] Start the in-vehicle camera to monitor the driver's facial expressions in real time, capture the position changes of facial key points, use facial recognition technology to extract facial features and expression action units, train a convolutional neural network to analyze facial expressions, and identify the emotional state;

[0019] Fuse the driver's emotional state and emotional state through a timeline to obtain an emotion profile;

[0020] Analyze historical driving data, identify driving behavior patterns in different emotional states, and establish an association model between the emotion profile and driving behavior;

[0021] According to the current emotional state, find relevant driving behaviors in the emotion profile to obtain the driver's driving intention.

[0022] As a preferred solution of the vehicle motion trajectory prediction method based on quantum computing according to the present invention, wherein: based on the basic vehicle information, calculate the kinematic parameters of the vehicle, and combine the environmental data and the driver's driving intention to construct a driver behavior information library, including the following steps,

[0023] According to the vehicle's speed, heading angle, and angular velocity, calculate the position change rate, heading angle change rate, and acceleration of the vehicle;

[0024] Collect the environmental data around the vehicle through multiple sensors;

[0025] Integrate environmental data, vehicle kinematic parameters, and driver driving intentions to establish a driver behavior information database.

[0026] As a preferred embodiment of the vehicle motion trajectory prediction method based on quantum computing according to the present invention, wherein: use the current environmental data and the current driver driving intention to match in the driver behavior information database, and preliminarily predict the path of the vehicle to obtain multiple predicted paths, including the following steps.

[0027] Extract key features including vehicle position, speed, acceleration, heading angle, and obstacle distance from the environmental data and driver driving intention.

[0028] According to the extracted key features, use a similarity calculation method to evaluate the matching degree between the current state and the historical behavior patterns in the driver behavior information database.

[0029] Generate multiple predicted paths according to the matched historical behavior patterns.

[0030] As a preferred embodiment of the vehicle motion trajectory prediction method based on quantum computing according to the present invention, wherein: use quantum computing to evaluate the possibility of multiple predicted paths and output the optimal path, including the following steps.

[0031] Calculate the collision risk value of each predicted path based on the number of obstacles and the distance between obstacles.

[0032] Input the collision risk values of multiple predicted paths into a quantum computing model, and use a quantum algorithm to evaluate the possibility of each path.

[0033] According to the evaluation result of quantum computing, select the path with the highest possibility and safety as the optimal path of the vehicle.

[0034] As a preferred embodiment of the vehicle motion trajectory prediction method based on quantum computing according to the present invention, wherein: calculate the ideal lateral position of the vehicle according to the latest environmental data and vehicle basic information, integrate the kinematic parameters and the optimal path to obtain the predicted complete motion trajectory of the vehicle, including the following steps.

[0035] Use the unit vector in the vertical direction of the current position and the current heading angle to calculate the ideal lateral position of the vehicle.

[0036] Combine the calculated ideal lateral position with the kinematic parameters of the vehicle to form new kinematic parameters.

[0037] According to the environmental data of the optimal path, integrate the new kinematic parameters with the optimal path to form the complete predicted motion trajectory of the vehicle.

[0038] Using the OpenCV tool, visualize the generated complete predicted motion trajectory.

[0039] In a second aspect, the present invention provides a vehicle motion trajectory prediction system based on quantum computing, including:

[0040] A vehicle tracking module, responsible for tracking the vehicle, recording the basic information of the vehicle, and detecting environmental data using a variety of sensors;

[0041] An emotion monitoring module, responsible for monitoring the driver's emotion using a brain-computer interface and evaluating the driver's driving intention;

[0042] A behavior library construction module, responsible for calculating the kinematic parameters of the vehicle based on the basic information of the vehicle, and combining the environmental data and the driver's driving intention to construct a driver behavior information library;

[0043] A preliminary prediction module, responsible for matching the current environmental data and the current driver's driving intention in the driver behavior information library, making a preliminary prediction of the vehicle's path, and using quantum computing to evaluate the possibility and output the optimal path;

[0044] A trajectory generation module, responsible for calculating the ideal lateral position of the vehicle according to the latest environmental data and the basic information of the vehicle, integrating the kinematic parameters and the optimal path, and obtaining the predicted complete motion trajectory of the vehicle.

[0045] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the vehicle motion trajectory prediction method based on quantum computing as described in the first aspect of the present invention is implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the vehicle motion trajectory prediction method based on quantum computing as described in the first aspect of the present invention is implemented.

[0047] The beneficial effects of the present invention are as follows: By introducing brain-computer interface technology, the emotional state of the driver is monitored in real time and their driving intention is evaluated, significantly improving the accuracy of vehicle motion trajectory prediction. Combining environmental data and kinematic parameters to construct a driver behavior information database enables more accurate path prediction based on historical data. In addition, using quantum computing to evaluate the collision risk of multiple predicted paths can quickly process complex environmental information, output the optimal path, and reduce the accident risk. This comprehensive prediction method not only enhances the understanding of driving behavior but also improves the adaptability to dynamic environments, thus ensuring the safe driving and efficient operation of the vehicle in complex traffic scenarios. Through this innovative approach, the correlation between the driver's emotional changes and behavior patterns is effectively captured, providing new ideas and methods for the development of future intelligent driving technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0049] Figure 1 FIG. is a flowchart of the vehicle motion trajectory prediction method based on quantum computing in Embodiment 1.

[0050] Figure 2 FIG. is a schematic diagram of the vehicle motion trajectory prediction system based on quantum computing in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0052] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0053] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude other embodiments.

[0054] Embodiment 1, refer to Figure 1 and Figure 2, which is the first embodiment of the present invention. This embodiment provides a vehicle motion trajectory prediction method based on quantum computing, including the following steps:

[0055] S1. Track the vehicle, record the basic information of the vehicle, and use a variety of sensors to detect environmental data, including the following:

[0056] The variety of sensors include cameras, radars, lidars, and acoustic sensors;

[0057] The environmental data includes the number and location of obstacles in the environment, the number and location of lane lines, the number and location of traffic signals, and the number and location of pedestrians;

[0058] The basic information of the vehicle includes the initial position, speed, and heading angle;

[0059] Use the radar and lidar to track the vehicle in real time and obtain the vehicle position and vehicle speed;

[0060] It should be noted that environmental data, including obstacle, lane line, traffic signal, and pedestrian information, is collected through multi-source sensors such as cameras, radars, lidars, and acoustic sensors; at the same time, basic information such as the initial position, speed, and heading angle of the vehicle is recorded; achieving a comprehensive perception of the vehicle and its surrounding environment, ensuring the data basis for the subsequent steps.

[0061] S2. Use a brain-computer interface to monitor the driver's emotions and evaluate the driver's driving intention, including the following steps:

[0062] Start the BCI device and capture the driver's brain wave signals in real time;

[0063] It should be noted that ensure the correct wearing of the BCI (brain-computer interface) device (such as an EEG (electroencephalogram) helmet or headband), perform device calibration to ensure accurate signals, start the signal acquisition process, set the sampling frequency (usually 250Hz to 1000Hz), ensure the acquisition of high-quality brain wave data, monitor the changes in brain waves (such as α waves, β waves, θ waves, etc.) in real time, and record the amplitude and duration of different brain wave frequencies;

[0064] Analyze the brain wave signals through a band-pass filter, wavelet transform, and support vector machine to identify the emotional state (such as anxiety, relaxation, concentration, etc.);

[0065] It should be noted that a band-pass filter is used to remove noise and artifacts, purify the brain electrical signals, use wavelet transform to extract the power spectral density related to emotions, and apply support vector machine to analyze the power spectral density to identify the emotional state (such as anxiety, relaxation, concentration, etc.);

[0066] Start the in-vehicle camera to monitor the driver's facial expressions in real time, capture the position changes of facial key points (such as eyes, mouth corners, eyebrows), use facial recognition technologies (such as OpenFace (Open Face Analysis Toolkit) or Dlib (Dlib Library)) to extract facial features and expression action units, train a convolutional neural network to analyze facial expressions, and recognize emotional states (such as happiness, anger, sadness, etc.);

[0067] Fuse the driver's mood state and emotional state through a timeline to obtain an emotion profile;

[0068] Analyze historical driving data (historical driving data includes historical environmental data and historical vehicle basic information), and identify driving behavior patterns in different emotional states (such as acceleration or deceleration behaviors in emergency situations);

[0069] Specifically, label the emotional state at each time point, such as anxiety, relaxation, concentration, etc., and associate it with the corresponding driving behaviors (such as acceleration, deceleration, lane change, etc.). Denoise the collected historical driving data to remove outliers and noise interference; perform normalization processing on numerical data to ensure comparison of different features on the same scale. The rate of change of speed, acceleration, steering angle, etc., which are highly correlated with emotional changes and driving behaviors after processing, are used to reduce redundant information;

[0070] Use an association rule learning algorithm (such as the Apriori algorithm) to mine the association rules between emotional states and specific driving behaviors. Based on the mined association rules, use a logistic regression model to predict the most likely driving behaviors in a given emotional state, calculate the probability of each behavior occurring, and use a decision tree algorithm to construct an emotion-behavior mapping relationship diagram, that is, establish an association model between the emotion profile and driving behaviors;

[0071] According to the current emotional state, search for relevant driving behaviors in the emotion profile to obtain the driver's driving intention.

[0072] It should be noted that the BCI device is started to capture brain wave signals in real time. After filtering, transformation, and support vector machine analysis, the emotional state is recognized; combined with facial expression analysis to further improve the emotion profile, and based on historical driving data analysis of behavior patterns in different emotions; the accurate capture of the driver's emotional state and the intelligent evaluation of driving intention are realized, improving driving safety.

[0073] S3. Based on the vehicle basic information, calculate the kinematic parameters of the vehicle, and combine the environmental data and the driver's driving intention to construct a driver behavior information library, including the following steps,

[0074] The kinematic parameters include the rate of change of position, the rate of change of heading angle, and acceleration.

[0075] Calculate the rate of change of the vehicle's position based on the vehicle's speed and heading angle, expressed as,

[0076]

[0077] where, represents the rate of change of the vehicle's position at time t. By decomposing the speed v(t) into lateral and longitudinal components along the current heading angle θ(t), the change in the vehicle's position at the next moment is calculated. v(t) represents the linear speed of the vehicle at time t (i.e., the speed of forward or backward movement), with the unit of meters per second (m / s). θ(t) represents the heading angle of the vehicle at time t (i.e., the angle the vehicle is facing), usually referenced to the due north direction, with the positive direction being clockwise, and the unit being radians (rad). cos(θ(t)) and sin(θ(t)) are used to decompose the vehicle's speed into lateral and longitudinal components to ensure the vehicle moves along its current heading;

[0078] Calculate the rate of change of the vehicle's heading angle through the angular velocity, expressed as,

[0079]

[0080] where, represents the rate of change of the vehicle's heading angle at time t, taking into account the vehicle's speed v(t), wheelbase L, and front wheel steering angle δ(t). Through these parameters, the steering rate (i.e., the rate of change of the heading angle) of the vehicle is calculated. δ(t) represents the front wheel steering angle, i.e., the deflection angle of the front wheel relative to the vehicle's longitudinal axis, with the unit of radians, and L represents the wheelbase of the vehicle, i.e., the distance between the front and rear wheels, with the unit of meters;

[0081] Calculate the acceleration of the vehicle, expressed as,

[0082]

[0083] where, represents the acceleration of the vehicle at time t (i.e., the rate of change of speed). u(t) represents the commanded acceleration at time t, i.e., the acceleration instruction issued by the driver, which can be obtained through the driver's operation or the change in the vehicle's acceleration, with the unit of meters per second 2 , bv(t) represents the damping term, which means that as the speed increases at time t, the air resistance and rolling resistance also increase, thereby slowing down the vehicle's speed. b represents the damping coefficient, which reflects the influence of air resistance, rolling resistance, etc. on the vehicle's speed, with the unit of seconds;

[0084] Collect the environmental data around the vehicle through multiple sensors;

[0085] Specifically, computer vision technologies (such as YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), etc.) are used to process camera images to identify and track other vehicles, pedestrians, and static obstacles on the road. Radar and lidar data are used for 3D reconstruction through point cloud processing algorithms to provide high-precision distance and speed information. Lane detection algorithms (such as Hough transform) are used to identify lane lines and determine lane width and curvature. The status of traffic lights (red / green lights, arrow indications, etc.) is captured through the camera;

[0086] The environmental data, kinematic parameters of the vehicle, and driver's driving intention are fused together to establish a driver behavior information database;

[0087] Specifically, the Kalman filtering algorithm is used to fuse data from multiple sensors to form an environmental perception model. Combining with the vehicle's historical kinematic parameters, a driver behavior information database is established to record typical driving behavior patterns under different conditions (such as different weather conditions, traffic flow). Analyze the vehicle's historical kinematic parameters to identify the driver's driving intention in different emotional states (such as accelerating or decelerating behaviors in emergency situations). Establish a correlation model between the emotion profile and driving behavior. Through machine learning algorithms (such as random forest, neural network, etc.), train the correlation model to identify the impact of emotion changes on driving intention, providing a basis for predicting future driving behaviors.

[0088] It should be noted that kinematic parameters such as the rate of change of position, rate of change of heading angle, and acceleration are calculated; the environmental data, kinematic parameters, and driving intention are fused to establish a driver behavior information database; the accurate calculation of vehicle kinematic parameters and the construction of the behavior information database are realized, enhancing the ability to predict future paths.

[0089] S4. Use the current environmental data and the current driver's driving intention to match in the driver behavior information database, make a preliminary prediction of the vehicle's path, and use quantum computing to evaluate the possibility and output the optimal path, including the following steps,

[0090] Extract key features such as vehicle position, speed, acceleration, heading angle, and obstacle distance from the environmental data and the driver's driving intention;

[0091] According to the extracted key features, use similarity calculation methods (such as Euclidean distance, cosine similarity) to evaluate the matching degree between the current state (i.e., the current environmental data and the current driver's driving intention) and the historical behavior patterns in the driver behavior information database;

[0092] Specifically, calculate the similarity (Euclidean distance), expressed as,

[0093]

[0094] Among them, d(C, H) represents the Euclidean distance between the current state and the historical behavior pattern, that is, the current state C = (c 1 , c 2 , …, c n ) and the similarity of the historical behavior pattern H = (h 1 , h 2 , …, h n ). n represents the number of key features, i represents the index of the key feature, c i represents the i-th key feature in the current state, and h i represents the i-th key feature in the historical behavior pattern;

[0095] According to the average similarity, set the similarity threshold. When the similarity between the calculated current state and the historical behavior pattern is greater than or equal to the similarity threshold, this historical behavior pattern is matched, otherwise it is eliminated;

[0096] Generate multiple prediction paths according to the matched historical behavior pattern.

[0097] Calculate the collision risk value (or path length and estimated time, etc.) of each prediction path, expressed as

[0098]

[0099] Among them, R represents the collision risk value. A smaller R value indicates a higher collision risk. m represents the number of obstacles, j represents the index of the obstacle, and d j represents the distance between the path and the j-th obstacle;

[0100] Input the collision risk values of multiple prediction paths into the quantum computing model, and use quantum algorithms (such as quantum genetic algorithms or quantum simulated annealing) to evaluate the possibility of each path. Quantum computing can quickly process a large number of possibilities and evaluate the safety and effectiveness of each path;

[0101] It should be noted that a hybrid quantum-classical architecture is adopted, and the core algorithm selects a fusion scheme of the Quantum Annealing algorithm and the Quantum Approximate Optimization Algorithm (QAOA): Quantum Annealing is responsible for handling the global optimization problem of the path collision risk value, and QAOA is used to solve the local optimization of the path continuity constraint. The dual-algorithm collaborative calculation is realized through the quantum gate circuit; the physical parameters of each path are encoded into 16 qubits. For example, the three-dimensional quantum encoding of the path heading angle each occupies 3 bits, the distances to the nearest 4 obstacles each occupy 2 bits, the speed state occupies 2 bits, the acceleration state occupies 2 bits, and the amplitude encoding of the collision risk value occupies 3 bits; 100,000 sets of historical driving scenario data (including environmental parameters, vehicle states, driver emotion labels) are collected, 500,000 sets of simulated scenarios are generated through data augmentation, and hybrid training is carried out using a classical-quantum collaborative training framework. Hybrid training is to alternately use a classical neural network to extract environmental features and a quantum optimization algorithm to adjust parameters, and transfer the optimization gradient between the two to achieve collaborative learning, and finally make the quantum model adapt to the path evaluation requirements of complex driving scenarios; the parameter settings include setting the number of qubits to 16, the annealing step size to 1000, the number of QAOA layers to 3, the learning rate to 0.01, the number of sampling times to 1000, and the temperature coefficient to 0.5 → 1.2; the quantum computing process encodes the path data into a quantum state, uses quantum entanglement and an optimization algorithm (quantum kernel function) to evaluate the risks of all paths in parallel, and finally selects the optimal path based on the probability distribution of the quantum measurement results.

[0102] It should be noted that the collision risk value of each predicted path is encoded into a quantum state, input into the quantum computing model, an appropriate quantum algorithm (such as the quantum genetic algorithm or quantum simulated annealing) is selected, and relevant parameters (such as the number of iterations, convergence threshold, etc.) are set. The quantum computing model is started, and the algorithm is run to evaluate the safety and effectiveness of each path. The evaluation results of each path are collected from the quantum computing model to obtain the score of the path;

[0103] According to the evaluation results of the quantum computing, the path with the highest probability and safety is selected as the optimal path of the vehicle.

[0104] It should be noted that key features are extracted from the environmental data and driving intentions, and a similarity calculation method is used to evaluate the matching degree; multiple predicted paths are generated and their collision risk values are evaluated; the safety and effectiveness of the paths are quickly evaluated using quantum computing, and the optimal path is selected. The efficient matching of the current state and historical behavior patterns and path optimization are realized, ensuring the safety and efficiency of driving.

[0105] S5. According to the latest environmental data and vehicle basic information, calculate the ideal lateral position of the vehicle, integrate the kinematic parameters and the optimal path, and obtain the predicted complete motion trajectory of the vehicle, including the following steps,

[0106] Calculate the ideal lateral position of the vehicle. When calculating the ideal lateral position, consider the influence of surrounding obstacles and lane lines to ensure that the calculated lateral position will not cause collisions or lane departures, expressed as,

[0107]

[0108] where p ⊥ (t) represents the ideal lateral position of the vehicle at time t. Calculating the ideal lateral position helps to control the position of the vehicle on the road or in the lane, ensuring that the vehicle does not collide with obstacles, other vehicles or pedestrians during driving. p(t) represents the current position of the vehicle at time t, usually represented in the form of two-dimensional coordinates, such as p(t)=[x(t),y(t)], where x(t) and y(t) are the positions of the vehicle in the horizontal and vertical directions respectively, and L ⊥ represents the ideal lateral distance, that is, the distance that the vehicle should maintain in the vertical direction of the current heading angle, which can be adjusted according to the vehicle's characteristics, lane width or environmental conditions. represents the unit vector in the vertical direction of the current heading angle. Specifically, gives the lateral component in the vertical direction, gives the longitudinal component in the vertical direction;

[0109] Combine the calculated ideal lateral position with the vehicle's kinematic parameters (such as current speed, acceleration, heading angle) to form new kinematic parameters;

[0110] Integrate the new kinematic parameters with the optimal path according to the environmental data of the optimal path to form the complete predicted motion trajectory of the vehicle;

[0111] Specifically, a kinematic model (such as a uniform linear motion or uniformly accelerated motion model) can be used to predict the motion trajectory of the vehicle in the future time period, expressed as,

[0112]

[0113] where p(t + Δt) represents the position of the object at time t + Δt, and Δt represents the time interval;

[0114] Use the OpenCV (Open Source Computer Vision Library) tool to visualize the generated complete predicted motion trajectory, showing the motion path of the vehicle in the future time period and its changes relative to the environment.

[0115] It should be noted that when the lateral deviation > 0.3m or the heading angle deviation > 1°, the trajectory correction mode is activated. The path is re-planned in the local map through the quantum genetic algorithm, and at the same time, haptic feedback (such as steering wheel vibration) is pushed to the driver. When the acceleration deviation from the predicted value > 0.2g, a red warning icon is displayed on the dashboard, and a voice prompt detects abnormal acceleration and requests to take over control. When a sudden turn causes the trajectory deviation > 0.5m, an emergency avoidance is executed, the automatic emergency braking (AEB) is activated, and at the same time, the event log (including brain waves and vehicle dynamics data) is uploaded to the cloud.

[0116] It should be explained that the ideal lateral position of the vehicle is calculated considering the influence of obstacles and lane lines; combined with the new kinematic parameters and the optimal path, a complete predicted motion trajectory is formed; the OpenCV tool is used for visual display. The calculation of the ideal lateral position of the vehicle and the prediction of the complete motion trajectory are realized, ensuring the stability and safety of driving.

[0117] This embodiment also provides a vehicle motion trajectory prediction system based on quantum computing, including:

[0118] A vehicle tracking module, responsible for tracking the vehicle, recording the basic information of the vehicle, and detecting environmental data using a variety of sensors;

[0119] An emotion monitoring module, responsible for monitoring the driver's emotion using a brain-computer interface and evaluating the driver's driving intention;

[0120] A behavior library construction module, responsible for calculating the kinematic parameters of the vehicle based on the basic information of the vehicle, and constructing a driver behavior information library in combination with environmental data and the driver's driving intention;

[0121] A preliminary prediction module, responsible for matching the current environmental data and the current driver's driving intention in the driver behavior information library, making a preliminary prediction of the vehicle's path, and evaluating the possibility using quantum computing to output the optimal path;

[0122] A trajectory generation module, responsible for calculating the ideal lateral position of the vehicle according to the latest environmental data and the basic information of the vehicle, integrating the kinematic parameters and the optimal path, and obtaining the predicted complete motion trajectory of the vehicle.

[0123] This embodiment also provides a computer device applicable to the case of the vehicle motion trajectory prediction method based on quantum computing, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the vehicle motion trajectory prediction method based on quantum computing as proposed in the above embodiment.

[0124] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0125] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for predicting the vehicle motion trajectory based on quantum computing proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0126] In summary, the present invention: by introducing brain-computer interface technology, it can monitor the driver's emotional state in real time and evaluate their driving intention, significantly improving the accuracy of vehicle motion trajectory prediction. By combining environmental data and kinematic parameters, a driver behavior information database is constructed, enabling more accurate path prediction based on historical data. In addition, by using quantum computing to evaluate the collision risks of multiple predicted paths, it can quickly process complex environmental information, output the optimal path, and reduce accident risks. This comprehensive prediction method not only enhances the understanding of driving behavior but also improves the adaptability to dynamic environments, thus ensuring the safe driving and efficient operation of vehicles in complex traffic scenarios. Through this innovative approach, the correlation between the driver's emotional changes and behavior patterns is effectively captured, providing new ideas and methods for the development of future intelligent driving technologies.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A vehicle motion trajectory prediction method based on quantum computing, characterized in that: include, Track vehicles, record basic vehicle information, and use a variety of sensors to detect environmental data; Use brain-computer interfaces to monitor the driver's emotions and assess the driver's driving intentions; Based on the basic information of the vehicle, the kinematic parameters of the vehicle are calculated, and the driver behavior information database is constructed by combining the environmental data and the driver's driving intention; Use the current environment data and the current driver's driving intention to match in the driver behavior information database, make a preliminary prediction of the vehicle's path, and use quantum computing to evaluate the possibility and output the optimal path; Based on the latest environmental data and basic vehicle information, the ideal lateral position of the vehicle is calculated, and the kinematic parameters and optimal path are integrated to obtain the predicted complete motion trajectory of the vehicle.

2. The method for predicting vehicle motion trajectory based on quantum computing as claimed in claim 1, characterized in that: The multiple sensors include cameras, radars, lidars, and acoustic sensors; The environmental data includes the number and location of obstacles in the environment, the number and location of lane lines, the number and location of traffic signals, and the number and location of pedestrians; The basic information of the vehicle includes initial position, speed and heading angle; The kinematic parameters include position change rate, heading angle change rate and acceleration.

3. The method for predicting vehicle motion trajectory based on quantum computing as claimed in claim 2, characterized in that: Using brain-computer interface to monitor the driver's emotions and evaluate the driver's driving intention includes the following steps: Start the BCI device to capture the driver's brain wave signals in real time; Analyze brain wave signals through bandpass filters, wavelet transforms, and support vector machines to identify emotional states; Start the on-board camera to monitor the driver's facial expressions in real time, capture the position changes of key facial points, use facial recognition technology to extract facial features and expression action units, train convolutional neural networks to analyze facial expressions, and identify emotional states; The driver's emotional state and affective state are integrated through the timeline to obtain an emotional profile; Analyze historical driving data, identify driving behavior patterns under different emotional states, and establish a correlation model between emotional profiles and driving behavior; According to the current emotional state, relevant driving behaviors are found in the emotional profile to obtain the driver's driving intention.

4. The method for predicting vehicle motion trajectory based on quantum computing as claimed in claim 3, characterized in that: Based on the basic information of the vehicle, the kinematic parameters of the vehicle are calculated, and the driver behavior information database is constructed by combining the environmental data and the driver's driving intention, including the following steps: Calculate the vehicle's position change rate, heading angle change rate and acceleration based on the vehicle's speed, heading angle and angular velocity; Collect environmental data around the vehicle through a variety of sensors; The environmental data, vehicle kinematic parameters and driver driving intention are integrated to establish a driver behavior information database.

5. The method for predicting vehicle motion trajectory based on quantum computing as claimed in claim 4, characterized in that: The current environment data and the current driver's driving intention are matched in the driver behavior information database to make a preliminary prediction of the vehicle's path and obtain multiple predicted paths, including the following steps: Extract key features including vehicle position, speed, acceleration, heading angle, and obstacle distance from environmental data and driver driving intention; Based on the extracted key features, a similarity calculation method is used to evaluate the matching degree between the current state and the historical behavior pattern in the driver behavior information database; Generate multiple prediction paths based on the matched historical behavior patterns.

6. The method for predicting vehicle motion trajectory based on quantum computing as claimed in claim 5, characterized in that: Using quantum computing to evaluate the possibility of multiple prediction paths and output the optimal path includes the following steps: Calculate the collision risk value of each predicted path by the number of obstacles and the distance between them; Input the collision risk values ​​of multiple predicted paths into the quantum computing model, and use quantum algorithms to evaluate the possibility of each path; Based on the evaluation results of quantum computing, the most likely and safe path is selected as the optimal path for the vehicle.

7. The method for predicting vehicle motion trajectory based on quantum computing as claimed in claim 6, characterized in that: Based on the latest environmental data and basic vehicle information, the ideal lateral position of the vehicle is calculated, and the kinematic parameters and optimal path are integrated to obtain the predicted complete motion trajectory of the vehicle, including the following steps: Calculate the ideal lateral position of the vehicle using the vertical unit vector of the current position and the current heading angle; The calculated ideal lateral position is combined with the kinematic parameters of the vehicle to form new kinematic parameters; Based on the environmental data of the optimal path, the new kinematic parameters are integrated with the optimal path to form a complete predicted motion trajectory of the vehicle; Use OpenCV tools to visualize the generated complete predicted motion trajectory.

8. A vehicle motion trajectory prediction system based on quantum computing, based on the vehicle motion trajectory prediction method based on quantum computing according to any one of claims 1 to 7, characterized in that: include, The vehicle tracking module is responsible for tracking the vehicle, recording basic vehicle information, and detecting environmental data using a variety of sensors; The emotion monitoring module is responsible for using the brain-computer interface to monitor the driver's emotions and assess the driver's driving intentions; The behavior library building module is responsible for calculating the vehicle's kinematic parameters based on the vehicle's basic information, and building a driver behavior information library based on environmental data and the driver's driving intention; The preliminary prediction module is responsible for matching the current environmental data and the current driver's driving intention in the driver behavior information database, making a preliminary prediction of the vehicle's path, and using quantum computing to evaluate the possibility and output the optimal path; The trajectory generation module is responsible for calculating the ideal lateral position of the vehicle based on the latest environmental data and basic vehicle information, integrating kinematic parameters and optimal path, and obtaining the predicted complete motion trajectory of the vehicle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the vehicle motion trajectory prediction method based on quantum computing described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle motion trajectory prediction method based on quantum computing according to any one of claims 1 to 7 are implemented.

Images