Cross-country environment intelligent driving assistance system and method based on cloud sharing

Abstract

The invention provides an off-road environment intelligent driving assistance system and method based on cloud sharing, and the method comprises the steps: 1, collecting the environment information around a vehicle in real time when the vehicle enters a current region for the first time; step 2, constructing a map according to the environment information for the intelligent driving vehicle to perform auxiliary driving; 3, recording operation behavior data of the driver in the manual driving process; 4, the communication module uploads the collected environment information and the recorded operation behavior data to a cloud server, so that the cloud server receives and stores the environment information and the recorded operation behavior data; 5, when a subsequent vehicle enters the current area, the cloud server issues the stored environment information and driving behavior data of the current area to the subsequent vehicle; and step 6, according to the environment information and the driving behavior data issued by the cloud server, a subsequent vehicle realizes an intelligent driving assistance function of the vehicle through a path planning algorithm, an obstacle avoidance algorithm and a speed control algorithm.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to an intelligent driving assistance system and method for off-road environments based on cloud sharing. Background Art

[0002] Off-road environments present complex and varied terrain, and detailed electronic maps are often lacking. For novice drivers, relying solely on manual driving presents significant safety risks. Current intelligent driving technologies rely heavily on high-precision / lightweight maps and advanced sensor systems, but these requirements are often difficult to meet in off-road environments. Therefore, a solution that can provide intelligent driving assistance in off-road environments is urgently needed. Summary of the Invention

[0003] In view of this, the present invention provides an off-road environment intelligent driving assistance system and method based on cloud sharing to solve technical problems such as the inability of existing technologies to adapt to driving needs in off-road environments and the lack of sharing of driver's operating behavior data.

[0004] The present invention provides an off-road environment intelligent driving assistance system based on cloud sharing. The system includes: a sensor input module, disposed on the intelligent driving vehicle, for collecting environmental information around the vehicle; a map construction module, disposed on the intelligent driving vehicle and connected to the sensor input module, for constructing a map based on the environmental information for use by the intelligent driving vehicle in assisted driving; a data acquisition module, disposed on the intelligent driving vehicle, for recording operational behavior data of the driver during manual driving; a communication module, disposed on the intelligent driving vehicle, respectively connected to the sensor input module, the map construction module, and the data acquisition module, and connected to a cloud server via a network, for uploading collected environmental information and recorded operational behavior data to the cloud server, and for receiving environmental information and operational behavior data uploaded by other vehicles and sent from the cloud server; the cloud server exchanges data with the communication module via wireless communication technology, for storing and managing the environmental information and driving behavior data uploaded by the vehicle, and for sending the relevant data to subsequent vehicles when they enter the same area; and an intelligent driving control module, disposed on the intelligent driving vehicle and connected to the communication module, for implementing the vehicle's intelligent driving assistance function based on the environmental information and driving behavior data sent from the cloud server.

[0005] Furthermore, the environmental information includes terrain, obstacles, and road slope.

[0006] Furthermore, the operating behavior data includes steering wheel angle, accelerator pedal position, and brake pedal pressure.

[0007] Furthermore, the sensor input module includes a laser radar, a camera, and a millimeter-wave radar.

[0008] The present invention also provides a method for an off-road environment intelligent driving assistance system based on cloud sharing, the method comprising: step 1, when a vehicle enters the current area for the first time, real-time collection of environmental information around the vehicle; step 2, building a map based on the environmental information for use by the intelligent driving vehicle for assisted driving; step 3, recording the driver's operating behavior data during manual driving; step 4, the communication module uploads the collected environmental information and recorded operating behavior data to the cloud server for the cloud server to receive and store; step 5, when a subsequent vehicle enters the current area, the cloud server sends the stored environmental information and driving behavior data of the current area to the subsequent vehicle; step 6, the subsequent vehicle implements the vehicle's intelligent driving assistance function through a path planning algorithm, an obstacle avoidance algorithm, and a speed control algorithm based on the environmental information and driving behavior data sent by the cloud server.

[0009] Furthermore, the intelligent driving assistance functions include automatic obstacle avoidance, path planning, and speed control.

[0010] Furthermore, step 2 includes: step 21, performing data calibration and synchronization, noise filtering, and data enhancement processing on the received environmental information; step 22, using lidar positioning, camera visual perception, and multi-sensor fusion positioning and mapping methods to realize map construction; step 23, using point cloud map, grid map, and topological map to store the constructed map; step 24, using incremental update, closed-loop detection and optimization, data compression and simplification methods to realize map update and optimization.

[0011] Furthermore, the step 3 includes: step 31, obtaining the driver's operating behavior data through the vehicle's electronic control unit; step 32, transmitting the operating behavior data to the data acquisition module through the vehicle's communication bus, and recording it in real time.

[0012] Furthermore, step 5 includes: step 51, after the subsequent vehicle enters the current area, it sends location information to the cloud server through the communication module; step 52, the cloud server retrieves and finds matching environmental information and driving behavior data based on the location information through a location matching algorithm; step 53, the cloud server sends the retrieved data to the corresponding vehicle through the communication module.

[0013] Furthermore, the cloud server adopts a distributed storage and computing architecture to efficiently store and manage large amounts of data.

[0014] The present invention provides an intelligent driving assistance system and method for off-road environments based on cloud sharing. This technical solution collects environmental information and manual driving behavior data when a vehicle passes through an unfamiliar environment for the first time, and shares it to the cloud, thereby realizing intelligent driving assistance functions for subsequent vehicles in the same area, thereby ensuring the driving safety of drivers, especially novice drivers, in off-road environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the framework of an off-road environment intelligent driving assistance system based on cloud sharing provided by the present invention; Figure 2 This is a flow chart of an intelligent driving assistance method for off-road environments based on cloud sharing provided by the present invention; Figure 3 It is a flow chart of the method for constructing a map based on environmental information provided by the present invention; Figure 4 It is a flowchart of a method provided by the present invention for a cloud server to send the stored environmental information and driving behavior data of the current area to subsequent vehicles. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] Device Item Example: The present invention provides an off-road environment intelligent driving assistance system based on cloud sharing, such as Figure 1 As shown in the figure, the system includes a sensor input module, a map construction module, a data acquisition module, a communication module, a cloud server, and an intelligent driving control module. Among them, the sensor input module, map construction module, data acquisition module, communication module, and intelligent driving control module are set up on the vehicle side, while the cloud server is set up in the cloud.

[0018] A sensor input module is provided on the intelligent driving vehicle and is used to collect environmental information around the vehicle; The map construction module is installed on the intelligent driving vehicle and connected to the sensor input module. It is used to select natural objects with stable geological structures as feature points based on environmental information, integrate the feature points with geometric shape, material reflectivity, and terrain slope, and generate feature codes with rotational invariance. The code is matched with a pre-established seasonal feature library to extract off-road features. The off-road features are used to construct a map for the intelligent driving vehicle to use for assisted driving. A data acquisition module is provided on the intelligent driving vehicle and is used to record the operation intensity characteristics, dynamic response characteristics, and environmental adaptation characteristics of the driver during manual driving in the off-road area; a communication module, which is provided on the intelligent driving vehicle and is connected to the sensor input module, the map construction module, and the data acquisition module, respectively, and is connected to the cloud server via the network. The communication module is used to upload the newly constructed map and recorded operation behavior data to the cloud server, and receive the adjusted map information and simulated driving style data sent by the cloud server; The cloud server exchanges data with the communication module via wireless communication technology. It generates simulated driving style data based on recorded operational behavior data using a multi-scenario classifier. Hidden Markov modeling is then used to model driving style data so that it changes over time and in different scenarios. A deep learning-based difference detection network is used to downgrade the original map information in the cloud server based on the newly constructed map using a map confidence decay model. This is then adaptively adjusted to achieve map updates and optimization. The adjusted map information and simulated driving style data are then distributed to subsequent vehicles. The intelligent driving control module is installed on the intelligent driving vehicle and connected to the communication module. It is used to realize the vehicle's intelligent driving assistance function through path planning algorithm, obstacle avoidance algorithm and speed control algorithm based on the map information and simulated driving style data sent by the cloud server.

[0019] The present invention provides an off-road environment intelligent driving assistance system based on cloud sharing. The system includes a sensor input module, a map construction module, a data acquisition module, a communication module, a cloud server and an intelligent driving control module. By collecting map environment information and manual driving behavior data when a vehicle passes through an unfamiliar environment for the first time and sharing them to the cloud, the intelligent driving assistance function of subsequent vehicles in the same area is realized, which solves the technical problems of the existing technology that lacks a data sharing mechanism, is not adapted to the needs of off-road driving, and lacks real-time performance.

[0020] Method Example: The present invention provides an off-road environment intelligent driving assistance system based on cloud sharing, such as Figure 2 As shown, the method includes the following steps.

[0021] Step 1: When the vehicle first enters the current off-road area, the vehicle's surrounding environmental information is collected in real time, and natural objects with stable geological structures are selected as feature points; Building off-road maps differs fundamentally from traditional urban road maps in the following key aspects: 1. Unstructured terrain processing: Without clear road boundaries and lane lines, terrain features are complex and variable (slope, surface material, and obstacle distribution), requiring the identification of natural features as navigational benchmarks (landmarks such as rocks and trees); 2. Dynamic environmental adaptability: Surface conditions change in real time with weather (mudiness, humidity, etc.), temporary obstacles frequently appear (fallen trees, animal activity), and vegetation growth causes seasonal variations; 3. Multi-dimensional information fusion: The simultaneous recording of geometric information, surface properties, and dynamic characteristics is crucial. Different vehicle types exhibit significant differences in their ability to navigate the same terrain. Therefore, prior to map construction, environmental information must be collected to eliminate dynamic interference such as vegetation, and natural feature points with stable geological structure must be selected. Furthermore, a seasonal feature library (corresponding to dry and rainy season features) must be established to extract off-road features. The relationship between the selected natural feature points and geometric parameters is shown in Table 1.

[0022]

[0023] Table 1 Geometric parameters of natural feature points Step 2: The feature points are fused with geometric shapes, material reflectivity, and terrain slope to generate rotationally invariant feature codes. This code is then matched against a pre-established seasonal feature library to extract off-road features. This off-road feature is then used to construct a map for use by intelligent vehicles for assisted driving. In addition to the geometric parameters mentioned above, feature points also incorporate material reflectivity and terrain slope when generating feature codes, as shown in Tables 2 and 3.

[0024]

[0025] Table 2 LiDAR reflectivity of typical off-road materials

[0026] Table 3 Terrain slope and category The map includes: traversable area division, terrain difficulty rating, recommended passing paths and special risk marking. The intelligent driving assistance function includes automatic obstacle avoidance, path planning, and speed control. Figure 3 As shown, the method for constructing a map includes: Step 21, performing data calibration and synchronization, noise filtering, and data enhancement processing on the received off-road feature information; Step 22: Map construction is achieved by using laser radar positioning, camera visual perception, and multi-sensor fusion positioning and mapping methods; Step 23, using a point cloud map, a grid map, or a topological map to store the constructed map; Step 24: map update and optimization are achieved by using incremental update, closed-loop detection and optimization, and data compression and simplification methods.

[0027] Step 3: Record the driver's operational intensity characteristics, dynamic response characteristics, and environmental adaptation characteristics during manual driving in the off-road area. The communication module uploads the newly constructed map and recorded operational behavior data to the cloud server. This step records the driver's driving style during the manual driving process, including: 1. Operation intensity characteristics: throttle / brake pedal change rate (Δ% / s) (aggressive driving is often accompanied by rapid and deep accelerator application or sudden braking), steering wheel angular velocity (° / s) (aggressive driving leads to sharper steering, conservative driving leads to smoother steering); 2. Dynamic response characteristics: longitudinal acceleration peak (m / s²) (reflecting the intensity of acceleration / braking), lateral acceleration standard deviation (reflecting cornering stability, with conservative driving having a lower standard deviation); 3. Environmental adaptation characteristics: the match between terrain type and operation (e.g., aggressive driving in sandy areas is more likely to cause tire slip, and the slip rate is calculated by the difference in wheel speed sensors), special terrain clearance time (aggressive driving in rocky areas has a shorter clearance time but a higher degree of bumpiness).

[0028] This application collects map environment information and driving style data from a vehicle's first trip through an unfamiliar environment and shares it with the cloud. Subsequent vehicles can use this data to implement intelligent driving assistance functions. Compared to existing technologies, this application focuses more on the sharing and application of driving behavior data. The cloud server uses a distributed storage and computing architecture to efficiently store and manage large amounts of data.

[0029] Step 4: The cloud server generates simulated driving style data based on the recorded operating behavior data using a multi-scenario classifier. Then, a hidden Markov model is used to adjust the driving style data to change over time and in different scenarios. The multi-scenario classifier integrates terrain labels (sand, mud, rocks, etc.), operating characteristics, and dynamics data to achieve a three-category classification (aggressive, balanced, and conservative). It also supports soft classification (e.g., 70% aggressive + 30% balanced). It uses a Generative Adversarial Network (GAN) to simulate extreme driving style data to address sample imbalance. A Hidden Markov Model (HMM) is used to model how driving style changes over time and in different scenarios. For example, the same driver may switch to an aggressive mode (fast hill-climbing) on ​​sandy terrain and a conservative mode (low speed to avoid sinking) on ​​muddy roads. A cloud server maintains a style state transition matrix for each driver, recording the probability of style preference under different terrain conditions.

[0030] Step 5: Using a deep learning-based difference detection network, based on the newly constructed map, the original map information in the cloud server is downgraded through a map confidence decay model, and the map is updated and optimized through adaptive adjustment. Adaptive adjustment is a map update strategy that adapts based on the degree of change: small changes result in a local update; large changes result in a global re-optimization. As previously mentioned, step 5 for off-road and urban road environments also includes quality verification and supplementary standards for the newly constructed map to handle special scenarios. This special scenario handling includes marking vehicle roll angle safety thresholds on cross-axle sections, marking water depth gradients and riverbed hardness in flooded areas, and marking tire pressure adjustment recommendations and passing speeds on soft surfaces.

[0031] Step 6: When a subsequent vehicle enters the current area, the cloud server sends the adjusted map information and simulated driving style data to the subsequent vehicle; As we can see from the previous article, the cloud server will generate a driving style based on the driver's operating behavior data, and send it to subsequent vehicles according to the distribution strategy. The distribution strategy includes: 1. Recommendation by style: When a subsequent vehicle requests data, the cloud automatically pushes the corresponding style data according to its current terrain (such as pushing 1 set of data each for aggressive, balanced, and conservative types in a sandy scene); 2. Distribution according to user selection: The driver can manually select a style through the on-board HMI (such as "imitating aggressive driving data"), and the cloud will distribute the corresponding style map annotations (such as aggressive route markings) and control parameters; 3. Hybrid mode: The system defaults to the "balanced + current driver style compensation" strategy. For example, a conservative driver can choose "balanced data but relax the throttle response by 10%. If Figure 4 As shown, step 6 includes: Step 61: After a subsequent vehicle enters the current area, it sends location information to the cloud server through the communication module; Step 62 : The cloud server searches and finds matching maps and driving style data based on the location information using a location matching algorithm. The cloud server sends map elements on demand: global path planning needs, local decision-making needs, and real-time control needs.

[0032] Step 63: The cloud server sends the retrieved data to the corresponding vehicle through the communication module. Step 64: When there is an environmental change or a new obstacle is added, an update request is triggered to correct and update the map.

[0033] After a subsequent vehicle enters the same area, it sends its location information to the cloud server. Since the cloud server has already received the environmental information and driving behavior data uploaded by the first vehicle entering each area, it can now retrieve and find the corresponding environmental information and driving behavior data for that area based on the subsequent vehicle's location information and send it to the subsequent vehicle. Based on the received data, the subsequent vehicle implements intelligent driving assistance functions, including automatic obstacle avoidance, path planning, and speed control.

[0034] In step 7, subsequent vehicles implement intelligent driving assistance functions based on the map information and simulated driving style data sent by the cloud server through path planning algorithms, obstacle avoidance algorithms, and speed control algorithms.

[0035] The present invention provides an intelligent driving assistance method for off-road environments based on cloud sharing. The method collects map environment information and manual driving behavior data when a vehicle passes through an unfamiliar environment for the first time, and shares it to the cloud, thereby realizing intelligent driving assistance functions for subsequent vehicles in the same area. This solves the technical problems of the existing technology, such as the lack of a data sharing mechanism, a narrow data range, and unsuitability for off-road driving needs.

[0036] In summary, the embodiments of the present invention provide an intelligent driving assistance system and method for off-road environments based on cloud-based sharing. By sharing the map environment information and driving behavior data collected when first passing through an unfamiliar environment, this technical solution enables subsequent vehicles to achieve intelligent driving assistance in the same area, reducing the safety risks for novice drivers in off-road environments, thereby improving off-road driving safety. The intelligent driving assistance function can help drivers better cope with complex off-road environments, reduce the driving burden, improve driving comfort, and enhance the driving experience. As more and more vehicles participate in data collection and sharing, the cloud server will accumulate a large amount of off-road environment data, realize data sharing and accumulation, and further improve the performance and reliability of the intelligent driving assistance system.

[0037] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for an off-road environment intelligent driving assistance system based on cloud sharing, characterized in that: The method comprises: Step 1: When the vehicle first enters the current off-road area, the vehicle's surrounding environmental information is collected in real time, and natural objects with stable geological structures are selected as feature points; Step 2: The feature points are fused with geometric shapes, material reflectivity, and terrain slope to generate rotationally invariant feature codes. This code is then matched against a pre-established seasonal feature library to extract off-road features. This off-road feature is then used to construct a map for use by intelligent vehicles for assisted driving. Step 3: Record the driver's operational intensity characteristics, dynamic response characteristics, and environmental adaptation characteristics during manual driving in the off-road area. The communication module uploads the newly constructed map and recorded operational behavior data to the cloud server. Step 4: The cloud server generates simulated driving style data based on the recorded operating behavior data using a multi-scenario classifier. Then, a hidden Markov model is used to adjust the driving style data to change over time and in different scenarios. Step 5: Using a deep learning-based difference detection network, based on the newly constructed map, the original map information in the cloud server is downgraded through a map confidence decay model, and the map is updated and optimized through adaptive adjustment. Step 6: When a subsequent vehicle enters the current area, the cloud server sends the adjusted map information and simulated driving style data to the subsequent vehicle; In step 7, subsequent vehicles implement intelligent driving assistance functions based on the map information and simulated driving style data sent by the cloud server through path planning algorithms, obstacle avoidance algorithms, and speed control algorithms.

2. The off-road environment intelligent driving assistance method based on cloud sharing according to claim 1, characterized in that: The intelligent driving assistance functions include automatic obstacle avoidance, path planning, and speed control.

3. The off-road environment intelligent driving assistance method based on cloud sharing according to claim 1, characterized in that: The method for constructing a map includes: Step 21, performing data calibration and synchronization, noise filtering, and data enhancement processing on the received off-road feature information; Step 22: Map construction is achieved by using laser radar positioning, camera visual perception, and multi-sensor fusion positioning and mapping methods; Step 23, using a point cloud map, a grid map, or a topological map to store the constructed map; Step 24: map update and optimization are achieved by using incremental update, closed-loop detection and optimization, and data compression and simplification methods.

4. The off-road environment intelligent driving assistance method based on cloud sharing according to claim 1, characterized in that: The map includes: traversable area division, terrain difficulty rating, recommended passage routes and special risk markings.

5. The off-road environment intelligent driving assistance method based on cloud sharing according to claim 1, characterized in that: The step 5 also includes: performing quality verification and supplementary standards on the newly constructed map to process special scenarios.

6. The off-road environment intelligent driving assistance method based on cloud sharing according to claim 5, characterized in that: The special scenario processing includes: marking the vehicle roll angle safety threshold on the cross-axle section, marking the water depth change gradient and riverbed hardness in the wading area, and marking the tire pressure adjustment suggestion and passing speed on soft ground.

7. The off-road environment intelligent driving assistance method based on cloud sharing according to claim 1, characterized in that: The step 6 comprises: Step 61: After a subsequent vehicle enters the current area, it sends location information to the cloud server through the communication module; Step 62 : The cloud server searches and finds matching maps and driving style data based on the location information using a location matching algorithm. In step 63 , the cloud server sends the retrieved data to the corresponding vehicle via the communication module.

8. The cloud-based shared off-road environment intelligent driving assistance method according to claim 7, characterized in that: The step 6 also includes: step 64, when there is an environmental change or a new obstacle, triggering an update request to correct and update the map.

9. An off-road environment intelligent driving assistance system based on cloud sharing according to claims 1-8, characterized in that: The system comprises: A sensor input module is provided on the intelligent driving vehicle and is used to collect environmental information around the vehicle; The map construction module is installed on the intelligent driving vehicle and connected to the sensor input module. It is used to select natural objects with stable geological structures as feature points based on environmental information, integrate the feature points with geometric shape, material reflectivity, and terrain slope, and generate feature codes with rotational invariance. The code is matched with a pre-established seasonal feature library to extract off-road features. The off-road features are used to construct a map for the intelligent driving vehicle to use for assisted driving. A data acquisition module is provided on the intelligent driving vehicle and is used to record the operation intensity characteristics, dynamic response characteristics, and environmental adaptation characteristics of the driver during manual driving in the off-road area; a communication module, which is provided on the intelligent driving vehicle and is connected to the sensor input module, the map construction module, and the data acquisition module, respectively, and is connected to the cloud server via the network. The communication module is used to upload the newly constructed map and recorded operation behavior data to the cloud server, and receive the adjusted map information and simulated driving style data sent by the cloud server; The cloud server exchanges data with the communication module via wireless communication technology. It generates simulated driving style data based on recorded operational behavior data using a multi-scenario classifier. Hidden Markov modeling is then used to model driving style data so that it changes over time and in different scenarios. A deep learning-based difference detection network is used to downgrade the original map information in the cloud server based on the newly constructed map using a map confidence decay model. This is then adaptively adjusted to achieve map updates and optimization. The adjusted map information and simulated driving style data are then distributed to subsequent vehicles. The intelligent driving control module is installed on the intelligent driving vehicle and connected to the communication module. It is used to realize the vehicle's intelligent driving assistance function through path planning algorithm, obstacle avoidance algorithm and speed control algorithm based on the map information and simulated driving style data sent by the cloud server.

10. The cloud-based shared off-road environment intelligent driving assistance system according to claim 9, characterized in that: The sensor input module includes a laser radar, a camera, and a millimeter-wave radar.

Images