593 results about "Driving simulation" patented technology

The invention provides an intelligent driving simulation test method and system for an internal combustion locomotive, and relates to the technical field of intelligent driving, and the method comprises the steps: collecting the driving state information and scene complexity data of the internal combustion locomotive through constructing a virtual simulation environment; acquiring multi-modal information of the obstacle by using a virtual sensor and performing fusion processing; and constructing a deep reinforcement learning network comprising a prediction branch network and a dual-channel control network, dynamically adjusting safety, comfort and efficiency index weights based on scene complexity, and generating driving control parameters. On the premise of guaranteeing safety, dynamic balance of high efficiency and comfort of intelligent driving of the diesel locomotive can be achieved, and adaptability and reliability of an intelligent driving system are improved.

The invention discloses a single-view large-scale outdoor scene three-dimensional reconstruction method based on three-dimensional Gaussian splashing, and the method comprises the steps: collecting a pseudo aerial image, and constructing a panoramic multi-mode supervision end-to-end single-view three-dimensional reconstruction model; meanwhile, panoramic consistency supervision, semantic constraint depth regularization and a radial weighted luminosity loss and Gaussian cutting mechanism are introduced, so that the defect of insufficient geometric constraint of traditional single-view three-dimensional reconstruction is effectively overcome, and high-efficiency and high-fidelity three-dimensional modeling of a large-scale outdoor scene under single image input is realized; the method is suitable for various actual scenes such as smart city construction, automatic driving simulation, virtual reality / augmented reality, digital twinning and the like.

The invention relates to a data-driven intersection vehicle complex interaction behavior strategy simulation method and system. The method comprises the following steps: acquiring real intersection vehicle traffic trajectory data, constructing a plurality of interaction scenes, extracting observation information of each time step, and obtaining real vehicle trajectory data; taking each vehicle as an intelligent agent, based on a Gaussian strategy network pre-constructed according to the vehicle type, calculating a reward by using a reward based on a target guiding gain and a reward estimator from a discriminator, and generating simulated vehicle trajectory data; based on the real vehicle trajectory data and the simulated vehicle trajectory data, respectively extracting observed value-action pair information, updating a discriminator of an intelligent agent by taking distinguishing different attribute information to the greatest extent as a target, and updating a Gaussian strategy network and a value estimator network in a generator by taking confusing the discriminator to the greatest extent as a target, so as to obtain the real vehicle trajectory data and the simulated vehicle trajectory data. And vehicle complex interaction behavior strategy simulation based on multi-agent countermeasure reverse reinforcement learning is realized.

The invention discloses a vehicle driving assistance system and method based on AR glasses. The system comprises an environment sensing module, a driver state monitoring module, a danger early warning and avoiding module, an automatic driving and auxiliary driving module, a driving simulation and training module, an abnormal behavior recognition module, a road information and navigation module and a health and emergency response module. The environment perception module is used for solving the problem of poor sight in extreme weather and road perception in a complex environment; by means of sensors such as the laser radar and the camera, road obstacles, pedestrians and vehicles can be accurately recognized, highlighted marking in the AR visual field is achieved, accidents caused by sight blind areas or distraction are reduced, indexes such as the blinking frequency and the head posture of a driver can be monitored, immediate reminding is conducted when fatigue or distraction is found, and parking and resting are forcibly suggested when necessary; and when the driver does not respond in time, the system can automatically brake or adjust the direction to avoid collision.

The present invention proposes an autonomous driving testing method based on multi-alliance cluster confrontation, aiming to improve the efficiency and accuracy of autonomous driving simulation test, and comprising S1—initialization of testing environment of autonomous driving; S2—decision-making for dividing background vehicle clusters; S3—decision-making for confrontation behaviors of the background vehicles; S4—trajectory planning for the background vehicles; and S5—looping through the steps S2, S3, and S4 until cluster confrontation testing tasks are completed. The method of the present invention uses reinforcement learning and alliance games to dynamically generate testing scenarios that are highly confrontational to vehicles being tested, which can find dangerous boundary scenarios for autonomous driving more quickly and improve the efficiency of simulation testing.

The invention provides a text-to-dynamic three-dimensional scene generation method and device. The method comprises the following steps: acquiring a first natural language description input by a user and a plurality of scene images shot at different angles; generating a static three-dimensional scene according to the first natural language description and the plurality of scene images; a second natural language description input by the user to the large language model is obtained, the second natural language description comprises relative scale information and constraint information of the multiple objects, and the relative scale information is used for describing actual physical sizes of the multiple objects in the static three-dimensional scene; the constraint information is used for describing physical conflicts existing in the moving process of the multiple objects; and according to the second natural language description and the static three-dimensional scene, generating reasoning motion tracks and reasoning sizes of the plurality of objects in the static three-dimensional scene so as to obtain a dynamic three-dimensional scene. Through the scheme, the authenticity and richness of the automatic driving simulation test are improved.

The invention discloses a three-dimensional scene reconstruction method, a method for intelligent driving analog simulation, computer equipment, a storage medium and a program product. The three-dimensional scene reconstruction method comprises the steps that an earth space is divided into a plurality of blocks, and the earth space comprises a spherical space in a preset range above the earth surface; acquiring scene data of the earth space for three-dimensional reconstruction to obtain a three-dimensional reconstruction result, the three-dimensional reconstruction result comprising a reconstruction model and reconstruction model information; and dividing the reconstruction model into corresponding blocks according to the reconstruction model information. According to the embodiment of the invention, the spherical space in the preset range above the earth surface is divided into the plurality of blocks, the three-dimensional reconstruction is carried out according to the acquired scene data in the spherical space to obtain the plurality of reconstruction models, and finally the plurality of reconstruction models obtained by reconstruction are distributed and stored in the corresponding blocks of the spherical space according to the reconstruction model information. And unified management of a plurality of reconstruction models is realized.

The invention provides an anthropomorphic automatic driving simulation test scene construction method. The method comprises the steps that all vehicles in a traffic scene are divided into two types of intelligent agents including a test vehicle and an environment vehicle, the traffic scene is modeled into a Markov decision process, the test vehicle is a vehicle controlled by an automatic driving algorithm, and the environment vehicle is a vehicle controlled by a GAIL-GRU driving strategy model; a Markov decision process is utilized to extract a driving track from the human driving data set, and an expert track data set is generated; and training a GAIL-GRU driving strategy model by using the expert track data set, realizing interaction between an environment vehicle and a test vehicle by using the trained GAIL-GRU driving strategy model, and constructing a simulation test scene. The automatic driving simulation test scene constructed by the invention can effectively expose decision defects of an automatic driving algorithm in a complex interaction situation, has good anthropomorphism and relatively high risk scene coverage, and provides support for a decision control simulation test of a high-level automatic driving vehicle.

The invention discloses an agricultural meteorological disaster monitoring and early warning method and system based on a remote sensing technology, and the method comprises the steps: generating a multi-dimensional data set through obtaining and processing multi-source remote sensing data, and generating a comprehensive data set through weighted average fusion. Then, extracting land surface temperature data, comparing the land surface temperature data with a historical value, calculating a temperature deviation value, and generating temperature anomaly distribution data; and calculating a disaster intensity index by combining the soil humidity and vegetation index data change trend, and generating disaster intensity distribution data. The data meteorology is imported into a driving simulation system, disaster evolution is simulated, and the disaster influence range and duration are predicted. And if the prediction data exceeds an early warning threshold, generating early warning data including disaster categories, influence areas and prediction time, and generating disaster risk distribution data by using a spatial interpolation method for dynamic monitoring. According to the invention, the accuracy and timeliness of disaster monitoring and early warning are improved.

The invention relates to a digital twin simulation and optimization method for a large-scale stamping production line, and the method comprises a rapid lightweight modeling technology, a multifunctional fault indicator feedback technology, a three-dimensional dynamic real-time driving simulation technology, and a big data analysis intelligent optimization decision technology. According to the method, virtual-real fusion and a three-dimensional dynamic technology are combined, a three-dimensional visual user interface oriented to the whole manufacturing process is developed based on Unity, the whole stamping production line is simulated in real time, potential problems are predicted and solved through real-time monitoring of the stamping production line, various problems influencing the production efficiency in the production process are optimized, and the manual management and control difficulty is reduced.

The invention discloses a VR-HIL multi-sensor closed-loop test platform for remote driving, and particularly relates to the technical field of remote driving analogue simulation control, and the VR-HIL multi-sensor closed-loop test platform comprises a time calibration module, a scene disturbance module, a fusion judgment module, a response management module and a closed-loop driving module. Through multi-source time alignment, three-dimensional environment disturbance simulation, multi-channel fusion judgment and control instruction dynamic scheduling, high-precision closed-loop interaction among perception, control and disturbance is realized, the reproduction and response capability of a system to positioning abnormity and perception uncertainty in a complex urban environment is enhanced, and the overall authenticity and stability of a test platform are improved; according to the method, high-precision time alignment of multi-source sensing data is realized, the reproduction capability to a city complex interference environment is enhanced, adaptive optimization of fusion precision and stable control response rhythm are realized through a fusion-feedback-strategy linkage mechanism, and the closed-loop reliability and sensing control collaboration of a test platform are improved.

The invention provides an intelligent driving simulation method and device based on big data joint training, relates to the field of intelligent driving, and solves the technical problem of performance degradation of a world model in a real scene due to distribution difference between virtual data and real data in the prior art. The method comprises the following steps: carrying out noise reduction processing on first environment data, carrying out feature analysis on the first environment data to determine an importance weight, and taking an area of which the clustering density of the importance weight meets a preset condition as a target scene; processing the first environment data based on a diffusion model to generate second environment data; using the second environment data and the target scene to construct a world model; processing the first environment data based on a visual language model to obtain dense description information of the target scene; generating a simulation scene according to the dense description information of the target scene and the world model, and performing an intelligent driving algorithm simulation test according to the generated simulation scene; the method and the device are used in an intelligent driving simulation training process.

The invention provides an airspace simulation deduction method and system based on digital twinning, and belongs to the technical field of airspace simulation, and the method comprises the steps: integrating geographic bottom plate data and airspace element data, carrying out the meshing based on an airspace grid engine, and constructing an airspace digital twinning model; receiving at least one flight plan, and mapping the flight plan to the airspace digital twin model to generate a corresponding simulation aircraft entity; based on a preset simulation engine, driving the simulation aircraft entity to perform flight simulation in the airspace digital twin model, and calculating a simulation flight situation; in the simulation process, airspace conflict detection and early warning are carried out based on the simulation flight situation and the airspace digital twin model; and outputting a simulation deduction result, performing three-dimensional visual output on the simulation flight situation data and the early warning information, and generating an analysis report including conflict statistics and airspace evaluation. The airspace resource allocation is optimized, the flight safety is improved, and intelligent and efficient management is realized.

The invention discloses an urban rail vehicle simulation driving training method and system based on scene simulation, and belongs to the technical field of driving simulation, and the method specifically comprises the steps: collecting rail line parameters, weather data, passenger flow density, vehicle equipment state and driving data in real time, carrying out the preprocessing, constructing a dynamic personalized simulation scene, and simulating driving operation. According to operation of a driver and a preset simulation scene, micro features of eye-brow areas of the driver are recognized, the psychological stress of the driver is analyzed in combination with historical data, the simulation scene is dynamically adjusted according to a psychological stress analysis result, the performance of the driver in the training is scored according to a preset evaluation standard, and a detailed training report is generated. According to the method, pressure analysis is carried out on the eyebrow area, pressure evaluation is carried out in combination with the physiological dimension, the pressure of the driver in a simulation scene can be judged in real time, different simulation scenes are provided for different drivers, and the training effect is greatly improved.

The invention discloses an automatic driving evaluation system based on artificial intelligence, and relates to the technical field of automatic driving, and the system comprises the following components: a meteorological model coupling module, a sensor parameter adjustment module, an automatic driving simulation module and an evaluation analysis module. According to the invention, data connection is established between the meteorological model coupling module and an external meteorological model, comprehensive meteorological data including temperature, humidity, wind speed, rainfall, snowfall, visibility and the like are acquired in real time, and a simulated extreme weather scene is constructed based on the data. The sensor parameter adjusting module automatically adjusts performance parameters of a vehicle sensor according to different weather types to ensure the accuracy of sensor data under extreme weather conditions, and the automatic driving simulation module operates an automatic driving system model in a simulated extreme weather scene to simulate the vehicle driving process.

The invention provides a lane changing intention recognition method based on a driving style. The method comprises the following steps: firstly, acquiring driving behavior data in a car-following scene through a driving simulation experiment, and constructing a multi-dimensional data set comprising a self-car state, a front-car state and time-space car-following characteristics; then, on the basis of an expected safety margin model, identifying reaction characteristics, steady-state risk characteristics and operation characteristics of a driver, and extracting behavior parameters forming a driving style, including indexes such as reaction time, an expected safety margin interval and operation sensitivity; and further dividing the drivers into different style types by using a clustering algorithm, and endowing style labels with the drivers. On the basis, lane changing intention time information subjectively marked by a driver is collected through a non-control observation experiment and is aligned with the trajectory data, and a trajectory data set with a real intention label is constructed. And finally, constructing a dynamic Bayesian network model based on the data set, taking a historical driving state sequence in a fixed time window as input, fusing a driving style, interaction characteristics of a vehicle and surrounding vehicles and traffic flow characteristics, and realizing real-time identification of whether a lane changing intention exists at the current moment. The method has good interpretability, individual difference adaptability and engineering deployment, and is suitable for dynamic identification and response control of driver intention in an intelligent driving assistance system.

Techniques are described herein for determining simulated vehicle positional errors and correlating the positional errors with vehicle features. Such techniques may include receiving log data comprising trajectories and position data for a real vehicle, and executing a log-based simulated vehicle based on the log data. A simulated vehicle may be controlled to follow a simulation trajectory in a simulated environment based on the trajectory of the real vehicle. A simulation system may determine a difference between the positions of the simulated vehicle and corresponding positions of the real vehicle in the real environment. The techniques may further include determining a vehicle state features correlated to the lateral and / or longitudinal position errors of the simulated vehicle, and determining, based on the vehicle state features, position error distributions and / or models that can be used to control subsequent driving simulations.

The invention provides an anthropomorphic virtual test scene multi-background vehicle collaborative decision-making method, which comprises the following steps of: constructing a dynamic traffic map of multiple vehicles based on a graph structure, and constructing a parameter-shared generative adversarial imitation learning framework, inputting the node features optimized by the graph attention network to a reinforcement learning network to generate a serialized control instruction, and comparing the generated control instruction with a state-action pair of expert data by using a discriminator sharing scoring parameters to iteratively optimize a control instruction generator; potential factor variables are introduced to represent driving styles, and strategy personification is enhanced in combination with explicit rule punishment and implicit confrontation awards; and a highly anthropomorphic multi-background vehicle sequence cooperative control instruction is generated through multiple rounds of iteration. According to the method and the system, the adversarial imitation learning is iteratively optimized and generated by utilizing potential factor variables and reward enhanced imitation learning, and a decision with diversity, compliance and personification is generated, so that the reliability of an automatic driving simulation test is improved in multiple aspects.

The invention belongs to the technical field of automatic driving test, and provides an automatic driving confrontation test scene generation method and system based on strategy switching, and the method comprises the steps: obtaining an automatic driving simulation scene; setting positions and initial speeds of a target vehicle and an intelligent body vehicle in the acquired simulation scene; in combination with the set position and initial speed of the target vehicle, the running state of the target vehicle is optimized by adopting a multi-agent near-end strategy, and the target vehicle is controlled; determining a current traffic state according to the control driving state of the target vehicle; in combination with the dynamic quantitative index of the artificial risk potential field, sensing the traffic flow risk of the intelligent body vehicle in the determined current traffic state in real time; and according to the obtained traffic flow risk level, automatically switching a defense strategy and an attack strategy of the agent vehicle, and driving the multi-agent vehicle to cooperatively generate an automatic driving confrontation test scene.

The invention belongs to the technical field of analog simulation, and particularly relates to an intelligent simulation system with an autonomous decision-making capability, which comprises simulation management used for task scene initialization, system parameter configuration and simulation process control and operation. The display system is used for 2D / 3D visual display and playback of simulation results; the model implementation system is connected with the simulation management and display system and is used for implementing a target model and a flight mode model according to configuration parameters; the intelligent target generation system is used for automatically generating a maneuvering combination strategy, a task load control strategy and a radar control strategy according to the simulation situation information generated by the model implementation system, and feeding back the maneuvering combination strategy, the task load control strategy and the radar control strategy to the model implementation system to drive simulation deduction; wherein the system can execute a plurality of simulation modes including large sample space random task simulation, task simulation without autonomous capability level and task simulation with certain autonomous capability level according to simulation types set by the simulation management and display system.

The invention discloses a vehicle driving simulation test method and system based on digital twinning, belongs to the technical field of vehicle driving, and realizes real interaction of a driving behavior model and a control algorithm in a virtual scene by constructing a digital twinning body highly corresponding to an actual vehicle and a driving environment. Time stamps and coordinate information of all the modules are collected, time differences and space residual errors are extracted, a space-time semantic consistency index model is constructed, and the loading process is intelligently judged and optimized; when inconsistency is detected, adjustment is performed through clock synchronization and coordinate recalibration, a closed-loop optimization mechanism is formed, and high collaboration of the model and the environment is ensured, so that the accuracy, the stability and the credibility of the simulation system are improved, and the method is suitable for complex and changeable automatic driving test scenes.

The invention provides a driving behavior prediction method and device, equipment and a storage medium. Relates to the technical field of automatic driving. The method comprises the following steps: constructing a virtual human model and a driving simulation environment, configuring the virtual human model in the driving simulation environment, enabling the virtual human model to interact with a vehicle model, controlling the vehicle model to act, establishing a deep learning model, and according to input first person view angle data of a driver, carrying out deep learning on the vehicle model. And outputting a control action and outputting the control action to the virtual human model, training the deep learning model by using the training data set, maximizing accumulated rewards through two stages of imitation learning and reinforcement learning to obtain a strategy function, and continuously updating the strategy function through interaction with environment information by using near-end strategy optimization to obtain the virtual human model. Obtaining a trained deep learning model; and realizing driving behavior prediction by using the trained deep learning model. The decision-making ability of the automatic driving system is improved by simulating the decision-making process of the human driver.

The invention discloses an uncertainty perception simulation method based on a neural radiation field (NeRF), and aims to solve the problem of insufficient reality sense of a dynamic scene in an automatic driving scene. Aiming at the problems of rendering artifacts and uncertainty generated when a reflecting material and a shielding area are processed by a traditional simulation method, the invention provides a new framework fusing Bayesian uncertainty quantization and dynamic scene optimization. On the basis of an MARS simulator, the frame remarkably improves the visual quality and reliability of a simulation scene through a special rendering loss function and a physics-based rendering model. Experimental results show that the method is superior to a baseline MARS simulator in KITTI and VKITTI data sets, and particularly shows higher application value and generalization ability in the aspects of reducing artifacts and improving rendering fidelity, and provides a more reliable test environment for automatic driving simulation.

The invention relates to an automatic driving intelligent safety multi-task dynamic test system based on a Carla simulation platform, and belongs to the field of artificial intelligence safety and automatic driving simulation test. The system comprises an automatic driving perception model integration and training module which comprises a multi-task data collection module, a fine tuning perception model and a compilation perception model Carla API interface; the attack and defense algorithm integration and training module is used for finely adjusting an attack and defense algorithm, writing an attack and defense algorithm Carla API (Application Program Interface) and replacing Carla object textures with an adversarial patch; and the real-time attack and defense deduction and evaluation recording module comprises a sensor for acquiring Carla real-time data, replacing textures, starting a perception model and starting an evaluation record of the success rate and the accuracy rate of defense and attack. According to the method, the robustness of the automatic driving perception model in a complex attack scene can be comprehensively evaluated, security holes of a perception system can be found in time, and the reliability and the security of an automatic driving technology in a complex environment are improved.

The invention aims to provide a washout algorithm based on a data-driven parameter prediction model, and belongs to the technical field of driving simulation, a vehicle longitudinal acceleration signal and a motion platform state parameter are acquired and input into a pre-trained multi-layer perceptron neural network model, a washout filter parameter combination adaptive to a current working condition is calculated and output, and the washout filter parameter combination is determined. And then real-time and dynamic adjustment of parameters of the high-pass acceleration filter and parameters of the low-pass inclination coordination filter along with the state of the vehicle and the motion platform is realized, so that online real-time optimization of a control instruction of the motion platform is completed, and finally optimization of driving motion feeling simulation fidelity is realized. A data-driven parameter prediction model breaks through the limitation that a traditional washout algorithm is fixed in parameter and poor in adaptability; offline optimization and online prediction are combined, and real-time performance and fidelity are balanced; the active centering controller compensates the longitudinal acceleration by using the pitch angle, improves the space utilization rate, introduces a comprehensive somatosensory error evaluation index, and accurately evaluates the somatosensory simulation effect.

The invention relates to an automatic driving test scene simulation generalization generation method and system based on knowledge distillation. The method comprises the following steps: acquiring real trajectory data, constructing a scene-level multi-agent trajectory generation framework based on a denoising diffusion probability model, and generating diversified and vivid agent trajectories through an iterative denoising process so as to realize modeling of multi-agent interaction behaviors in a complex traffic environment; a mixed knowledge self-distillation framework is further proposed, multi-level knowledge of a teacher model is migrated in a student model, and task loss and distillation loss are dynamically balanced in combination with a simulated annealing strategy, so that the cross-scene adaptability and generation stability of the model are improved; simulation verification shows that the generated intelligent agent track can effectively reduce the collision event rate and the retrograde event rate, and interaction coordination and traffic rule constraints are ensured. According to the system, the authenticity, diversity and cross-scene adaptive capacity of an automatic driving simulation scene can be improved.

The invention provides a multi-agent-based interactive automatic driving simulation test scene generation method. The method comprises the following steps: constructing a dynamic driving model for simulating a driving decision process of a vehicle serving as a background vehicle based on image data and measurement data; based on a hierarchical training thought and the dynamic driving model, determining and training driving strategies of a plurality of interaction levels; constructing a simulation test environment comprising the tested vehicle and the vehicle as a background vehicle; and according to the dynamic driving model and the driving strategies of the multiple levels, based on the simulation test environment, configuring the driving strategies of the multiple interaction levels for the vehicle as a background vehicle, and based on a multi-agent reinforcement learning algorithm, performing joint training on the vehicle as the background vehicle and the tested vehicle. Through the method, an interactive driving strategy is designed, so that a background vehicle interacts with a tested vehicle according to a real-time simulation environment.

Provided is a method, performed by a computer system, for generating a learning model for autonomous driving of a robot. The computer system obtains driving data from the driving of the robot or a driving simulation of a robot agent, determines a plurality of candidate paths for the state of the robot or the robot agent at a first time point, ranks the candidate paths on the basis of preference information, and trains a compensation model that associates candidate paths having relatively high ranks, among the candidate paths, with higher compensation scores, thereby generating a learning model for autonomous driving of the robot.

The invention relates to the technical field of automatic driving simulation, in particular to a performance evaluation method, system and device of an automatic driving simulation platform and a medium, and the method comprises the steps: constructing a simulation environment and a simulation vehicle equipped with a sensor, an actuator and a vehicle-mounted calculation unit simulation model; establishing a multi-dimensional platform evaluation system covering security, efficiency, response time and data processing capability, defining a specific sub-index, an evaluation method and a target data item needing to be collected for each dimension, and setting a comprehensive evaluation rule; running a closed-loop simulation test in the simulation platform, and synchronously collecting all target data; calculating evaluation results of the sub-indexes one by one based on the collected data; and judging whether the overall performance of the platform reaches the standard according to comprehensive evaluation rules. According to the invention, systematization, standardization and quantitative evaluation of the performance of the automatic driving simulation platform are realized, the reliability and comparability of a test result are improved, and an effective basis is provided for optimization of the simulation platform.

Techniques are described herein for executing driving simulations where control of simulated agents is switched between different programmatic planners based on different driving scenarios encountered in the simulation. As an example, a simulation system may execute a driving simulation including a programmatic agent initially controlled using a heuristic planner. During the execution of the simulation, the simulation system may detect one or more driving scenarios for which the heuristic planner is unable to navigate the environment or may determine an unrealistic trajectory for the simulated agent. Based on detecting a driving scenario, the simulation system may determine a machine-learned planner to control the simulated agent to navigate the driving scenario. After the driving scenario has been successfully traversed by the simulated agent using the machine-learned planner, the simulation system may switch the control of the simulated agent back to the heuristic planner to continue the simulation.