398 results about "Platoon" patented technology

Systems and methods are provided herein for implementing dynamic, scalable platoon formations for traveling vehicles. Such platoons may be formed and modified on the fly by vehicles that have varying sensing or autonomy capabilities. Platoons may be negotiated among available vehicles, to designate roles including global platoon leader, local leader(s), and platoon member(s). While the platoons are in place and the vehicles traveling in coordination, platoon members may depart the platoon, and the remaining members may re-allocate roles among the remaining members.

A deep reinforcement learning-based vehicle platoon control method and system. The method comprises: on the basis of a vehicle dynamics model, constructing a motion simulation model for vehicle platoon operation; on the basis of the motion simulation model for vehicle platoon operation and vehicle operating states, by using a constant time headway strategy, obtaining a state space and an action space for vehicle platoon control; and establishing a DDPG network on the basis of the state space and the action space for vehicle platoon control, using a reward function mechanism to train the DDPG network, stopping training when the total reward obtained per episode during the training process no longer increases, so as to obtain a trained control strategy network, and by using the trained control strategy network, performing platoon control.

The invention relates to a vehicle queue cooperative control method fusing deep reinforcement learning communication time delay compensation, and belongs to the technical field of intelligent vehicle control. For the problems of control error accumulation and queue instability caused by communication time delay in the vehicle-road cloud cooperative system, a solution integrating deep reinforcement learning prediction and preset performance control is provided. According to the technical scheme, the method comprises the following steps: constructing a vehicle state prediction model based on a DDPG algorithm, and generating a time delay compensation amount in real time; establishing a vehicle dynamics model containing communication time delay, and designing a sliding mode controller based on a barrier function; and dynamically adjusting the control constraint in combination with an adaptive error boundary mechanism. According to the method, through closed-loop fusion of prediction compensation and dynamic constraint, under the scene of burst communication delay (100-400 ms), the queue spacing error is reduced by 62%, the speed tracking error is still kept to be smaller than 0.3 m / s, and the queue stability and the anti-jamming capability are remarkably improved.

Apparatus, methods, and computer program products for platoon formation are provided. An example method may include identifying a set of non-malicious vehicles based on at least one of data associated with the set of non-malicious vehicles or communication from a second vehicle or a RSU. The example method may further include transmitting a request message to the set of non-malicious vehicles. The example method may further include receiving an acceptance message from at least one vehicle of the set of non-malicious vehicles. The example method may further include configuring a platoon with the at least one vehicle of the set of non-malicious vehicles.

The invention relates to a formation driving coordination method based on vehicle-road cooperation, and the method comprises the steps: a road side unit RSU is used for releasing a traffic constraint weight value containing the information of passing restriction, path guidance, risk distribution and the like into a formation driving region, and the weight value forms a traffic environment guidance domain with a potential gradient at a vehicle end; the vehicle autonomously completes formation aggregation and position arrangement based on the own state and the weight change trend in the local sensing environment; after the formation is completed, the vehicles dynamically form a multi-level influence circle structure according to relative positions, historical cooperative behaviors and influence factors provided by the RSU, a current leading vehicle exists in each layer of influence circle, the leading vehicle has local scheduling guidance capability, and when the state of the leading vehicle is unstable or the behavior is abnormal, the control right is transferred to the auxiliary control vehicle; according to the method, the traffic environment guidance domain with the potential gradient is constructed through the traffic constraint weight value issued by the RSU, and the vehicles can autonomously perform formation aggregation and array sorting based on the local weight change trend.

The invention relates to a neural network-based adaptive control method for a vehicle formation system. Compared with the prior art, the method solves the defects that a complete target trajectory cannot be known in advance due to the influence of an actual environment and the control direction is unknown due to the unstable state of a vehicle engine. The method comprises the following steps: acquiring tracking data of a vehicle formation system; establishing a dynamic model of the vehicle formation system; establishing an error equation; designing a nusturb type function; designing a radial basis function neural network architecture; designing a GRNN training set and an evaluation index for trajectory reconstruction; designing an event trigger function of an actual controller of the system; carrying out self-adaptive control on the vehicle formation; and controlling the vehicle formation with an unknown target trajectory and an unknown control direction. According to the method, a neural network (NN)-based adaptive control architecture is adopted for a vehicle formation system (VPSs), a real-time trajectory can be predicted online by using a GRNN based on historical data of a target trajectory, and an unknown nonlinear term in the system is compensated, so that the position of a vehicle tracks the predicted target trajectory.

A method for controlling a vehicle platoon, performed by a computer device, includes: establishing a communication connection with a first vehicle, wherein the first vehicle is a free vehicle; obtaining vehicle status information of the first vehicle; obtaining at least one platoon status information of at least one vehicle platoon; matching a first target vehicle platoon of the at least one vehicle platoon with the first vehicle based on the vehicle status information and the at least one platoon status information; generating a first platoon control instruction based on: a first distance between the first vehicle and the first target vehicle platoon, the vehicle status information, and platoon status information of the first target vehicle platoon; and instructing the first vehicle to join the first target vehicle platoon based on transmitting the first platoon control instruction to at least one of the first target vehicle platoon or the first vehicle.

A vehicle platoon intersection decision-making system includes multiple vehicles. When executing the intersection decision-making process, the captain vehicle determines whether the platoon can pass through the intersection at the current speed command; if yes, the captain vehicle directs each vehicle to maintain travelling at the current speed command to pass through the intersection; if not, the captain vehicle generates a first optimized speed control information through a first speed decision-making process, making the platoon decelerate before reaching the intersection and begin to accelerate at an acceleration critical time point such that the platoon passes through the intersection. When the platoon passes through the intersection at the current speed command, no energy for accelerating or decelerating is wasted. The platoon decelerates first and then begins to accelerate at the appropriate time through the intersection, avoiding or reducing the time spent waiting for traffic lights at the intersection.

Methods and systems for a vehicle of a remote transportation system. A vehicle includes a non-transitory computer readable media and one or more processors configured by programming instructions on the non-transitory computer readable media to: coordinate a platooning operation between the first vehicle and a second vehicle; monitor an environment of the first vehicle and the second vehicle while platooning; in response to the monitoring, determine a threat level vassociated with a cut-in operation of at least one object within the environment; and selectively activate at least one visual or audio cue based on the threat level to avoid the cut-in operation.

The invention relates to the technical field of intelligent traffic control, and discloses a self-balancing two-wheeled vehicle queue formation control system which comprises a cloud scheduling platform, a formation control unit and a vehicle end execution unit. And the cloud scheduling platform generates a global avoidance path based on the accumulated gravitational potential energy change and the pavement flatness coefficient, and executes dynamic position complementing. The formation control unit constructs a communication topology and executes formation switching based on environmental perception; the cooperative control module adopts an attitude position coupling algorithm, an expected acceleration is corrected through a gain function attenuating along with an attitude angle index, and the attitude balance is maintained preferentially when a tracking error is eliminated. The vehicle end execution unit is provided with an environment sensing and composite actuating module, and a hub motor and a control moment gyroscope are used for responding to longitudinal driving and transverse balance instructions respectively, so that dynamic decoupling is achieved. According to the invention, the control conflict between two-wheeled vehicle formation trajectory tracking and attitude stability is effectively solved, and the driving safety of the system is improved.

The embodiments of the present application relate to autonomous mobile apparatuses. Provided are a multi-apparatus cooperative control method, apparatus and system, and a storage medium. The method comprises: in response to being determined as a lead vehicle of a platoon and receiving a cooperative task, planning a task trajectory on the basis of the cooperative task, wherein the platoon comprises one lead vehicle and at least one following vehicle; publishing the task trajectory and an execution starting time of the cooperative task to the at least one following vehicle, such that the at least one following vehicle plans their respective following trajectories on the basis of the task trajectory, and executes the respective following trajectories upon reaching the execution starting time of the task trajectory; and executing the task trajectory upon reaching the execution starting time of the task trajectory, such that the lead vehicle and the at least one following vehicle maintain platoon synchronization for task execution. Therefore, a cooperative operation with a plurality of apparatuses integrated into a whole is realized, thereby expanding the application scenarios of cooperative collaboration of the plurality of apparatuses.

The embodiment of the invention relates to the technical field of intelligent driving, and discloses a motorcade passing control method, device and equipment based on global planning, and the method comprises the steps: obtaining the driving related information of vehicles in a motorcade; the motorcade comprises a plurality of vehicles, and the driving related information comprises at least one of road condition information, vehicle driving information and map navigation information; according to the driving related information of at least one vehicle in the motorcade, performing global planning by taking the vehicles in the motorcade not to fall behind or the fallen vehicles to get up to the motorcade as a control target, and determining a target state of a target vehicle in the motorcade; the target state indicates driving information needing to be executed by a target vehicle, and the target vehicle is any vehicle in a motorcade; and sending the target state of the target vehicle to the target vehicle to control the target vehicle to be switched from the current state to the target state. By applying the technical scheme of the invention, the current problems that the formation vehicles are easy to fall behind and are difficult to recover because of being cut off in the complex urban road can be solved.

The invention discloses a vehicle queue control method based on an improved gap strategy and a depth deterministic strategy gradient algorithm, and the method comprises the following steps: building a vehicle-to-vehicle gap strategy considering the difference between the speed of a front vehicle and the speed of a vehicle, constructing an MPC frame through the strategy, and adding the minimum safety distance between vehicles into a constraint condition of the MPC frame; adjusting parameters in the MPC framework in real time by using a trained depth deterministic strategy gradient algorithm model to obtain an optimal parameter combination in each state, and then substituting the optimal parameter combination into the MPC framework to calculate and obtain an optimal control sequence at each moment; and finally, longitudinally controlling the vehicles in the vehicle queue according to the specified control quantity in the optimal control sequence of each control period. Compared with a traditional fixed parameter MPC method, the method has the advantages that the motorcade gap error can be remarkably reduced, the stability and safety of motorcade longitudinal control are improved, and efficient and safe automatic driving motorcade management is achieved.

Systems and methods for coordinating and controlling vehicles, for example heavy trucks, to follow closely behind each other, or linking to form a platoon. In one aspect, on-board controllers in each vehicle interact with vehicular sensors to monitor and control, for example, gear ratios on vehicles. A front vehicle can shift a gear which, via a vehicle-to-vehicle communication link, can cause a rear vehicle to shift gears. To maintain a gap, vehicles may shift gears at various relative positions based on a grade of a road.

The invention provides a heterogeneous motorcade prediction control method based on a path information protection mechanism, and relates to the technical field of network connection unmanned vehicle cooperative control and intelligent traffic. Firstly, a path information protection mechanism is provided for preventing an alien invading vehicle from tracking a motorcade and ensuring the safety of motorcade path information. In addition, a predictor model is established to improve the estimation performance of the adaptive law, and a variable gain nonlinear expansion state observer is designed to approach and compensate the total disturbance. Then, by introducing a variable-gain hyperbolic tangent tracking differentiator, the problem of'complexity explosion 'caused by repeated derivation of a virtual controller in a backstepping method is avoided; and finally, a distributed prediction cooperative controller is constructed, and stable and safe driving of the whole heterogeneous network connection fleet is ensured.

The invention discloses an intelligent electric vehicle queue optimization method based on congestion prediction and DRL. The method comprises the following steps: (1) modeling a queue position optimization problem of an electric vehicle queue into a mathematical model which takes energy balance as a target and is constrained by a traffic environment; and (2) solving the mathematical model in the step (1) by adopting a DRL method based on a TRPO algorithm to obtain an optimal queue adjustment strategy of the electric vehicle queue. In the step (2), congestion state information in an external traffic environment is obtained through an LSTM traffic prediction and FCM method, and the congestion state information, the remaining electric quantity of each vehicle in the motorcade and the accumulated driving distance are jointly used as state input of a TRPO algorithm; according to the TRPO algorithm, a strategy network and a value network are adopted to respectively obtain a strategy for adjusting the queue position, and the return expectation in the current state is evaluated. The TRPO algorithm dynamically adjusts the updating step length of the strategy through the KL divergence updated by the constraint strategy, and guarantees the stability and convergence in the strategy updating process.

The invention discloses a motorcade distributed cooperative control method under dual attacks of sensors and actuators, and relates to the technical field of motorcade safe operation control. The problems that a traditional motorcade cooperative security control method is poor in environmental adaptability, insufficient in attack compensation capability and insufficient in robustness are solved. The thought of hierarchical control is adopted, and the designed hierarchical control comprises a basic cooperative controller of each vehicle, a first cooperative feedback controller of each vehicle, an advanced cooperative controller of each vehicle and a second cooperative feedback controller; the stability of the system under the sensor attack is ensured through a first cooperative feedback controller, an advanced cooperative controller is designed to counteract the influence of the attack on a control loop, and an actuator attack forms negative value compensation through a second cooperative feedback controller and is fed back to a feedforward compensation module of a vehicle. The system disturbance caused by the attack of the actuator can be resolved in real time, and the robustness of control is ensured. The method is mainly applied to the cooperative control of the motorcade.

A method for automated vehicle driving control in a platoon includes obtaining first operational parameters of a first vehicle, including at least a first measured braking performance of the first vehicle, obtaining second operational parameters of a second vehicle, including at least a first measured braking performance of the second vehicle, determining a platoon sequence according to the operational parameters by assigning whichever of the first vehicle and the second vehicle that has a lesser measured braking performance as a lead vehicle in the platoon sequence, and assigning the other of the first vehicle and the second vehicle as a follower vehicle in the platoon sequence, initiating a platoon sequence driving route, and controlling automated driving of the follower vehicle according to tracking of the lead vehicle, wherein the automated driving includes automated steering control, automated acceleration and automated braking based on tracked movement of the lead vehicle.

The invention discloses an unmanned vehicle queue control method based on physical information reinforcement learning, and the method comprises the steps: building a reinforcement learning environment of an unmanned vehicle queue, and enabling a queue following vehicle to plan the acceleration according to the acceleration change of a leading vehicle; state information of each vehicle is obtained, a TD3 algorithm is used for carrying out training iteration on the model, in the training iteration process, the expected acceleration obtained through calculation of the CACC model is embedded into a loss function of a strategy network Actor to serve as physical information constraint, and a strategy is guided to generate an action conforming to vehicle dynamics; and after training iteration is finished, deploying a control strategy of the strategy network Actor in an unmanned motorcade simulation environment to realize cooperative control of the motorcade. According to the method, physical information constraints are introduced, so that the model training speed is increased, the stability and interpretability of a reinforcement learning control strategy are improved, and the queue operation efficiency and stability are enhanced.

The invention relates to the technical field of vehicle control, in particular to a vehicle queue optimal control method and system based on a function deviation triggering mechanism, and the method comprises the steps: 1, constructing a piloting dynamics model of a piloting vehicle and a following dynamics model of a following vehicle; 2, defining a local tracking error of the ith following vehicle, defining control input of the following dynamical model as a function of the local tracking error according to an optimal control target, further defining an optimal value function, and determining optimal control input according to the optimal value function; 3, obtaining an optimal value function estimation value through an adaptive commentator neural network; 4, designing a function deviation triggering mechanism according to the optimal value function estimation value and the local tracking error so as to dynamically adjust the optimal control input of the following dynamical model; and 5, setting a communication association relationship and an initial state of the leading vehicle and the following vehicle to obtain a queue control result. According to the invention, efficient cooperative driving in a complex dynamic environment is realized.

The invention provides a multi-pilot vehicle formation control method based on formation graph connectivity judgment, and the method comprises the steps: determining the motion state of each target vehicle in a vehicle formation when the formation operation mode of the vehicle formation is a single-pilot mode; if it is determined that a target vehicle in the vehicle formation is abnormal according to the motion state, splitting the vehicle formation into a plurality of sub-formations in a multi-navigation mode; and when each sub-formation satisfies a preset formation fusion condition, recombining the sub-formations into a vehicle formation in the single navigation mode. The method is used for overcoming the defect that in the prior art, the whole formation loses efficacy when the vehicles cannot continue to follow stably in the vehicle formation in a single-pilot mode.

The invention relates to the technical field of intelligent vehicles, in particular to an intelligent vehicle automatic driving formation obstacle avoidance control method and device, and the method comprises the steps: constructing an intelligent vehicle formation controller according to the destination data and obstacle data of a target intelligent vehicle formation, so as to control the target intelligent vehicle formation to move towards the destination; establishing an intelligent vehicle formation space-time transformation strategy based on the queue expansion coefficient according to the queue expansion coefficient of the target intelligent vehicle formation and the driving safety boundary; performing dynamic optimization on the intelligent vehicle formation controller by adopting a Levy flight random search logic based on a cuckoo algorithm to obtain an optimized intelligent vehicle formation controller; and controlling the target intelligent vehicle formation to avoid obstacles by using the optimized intelligent vehicle formation controller and the intelligent vehicle formation space-time transformation strategy based on the queue expansion coefficient. Therefore, the problems that when intelligent vehicle formation obstacle avoidance is carried out through a traditional artificial potential field method, local minimum value and obstacle avoidance track jittering are likely to happen, and complex dynamic environments cannot be rapidly adapted are solved.

The invention discloses a fleet safety reinforcement learning robust formation control method fusing deep heterogeneous features. The method comprises the following steps: step 1, establishing a heterogeneous motorcade dynamic model; step 2, isomerism feature extraction based on LSTM (Long Short Term Memory); step 3, designing a Lyapunov safety reinforcement learning vehicle following strategy; and step 4, carrying out Lyapunov-PPO training optimization and convergence guarantee. According to the invention, the dynamic time-varying features of each vehicle in the heterogeneous motorcade are accurately extracted and tracked through the LSTM network, and adaptive control of different types of vehicles is realized; a Lyapunov safety constraint mechanism is introduced, collision-free guarantee is embedded in the reinforcement learning decision process, and the driving safety is improved; robustness of the system to external disturbance and internal dynamic change is enhanced, and it is ensured that a fleet can still keep stable formation in a complex driving environment.

The invention discloses an intelligent truck formation transportation control system based on cloud side-end cooperation, and the system achieves the cooperative control through a three-stage architecture of a cloud large model cognition center, an edge-side intelligent control center and an intelligent terminal with a body. Comprising a cloud large model cognition center, an edge side intelligent control center and an emergency response module driven by integrated fuzzy logic of an intelligent terminal system with a body. The invention also discloses an intelligent truck formation transportation control method based on cloud side-end cooperation, and the method comprises the steps: firstly deploying a large model at a cloud end, achieving the domain adaptation through the LoRA fine tuning, analyzing task semantics, and outputting feature parameters; secondly, a vehicle end needs to integrate a multi-mode sensor and a fuzzy controller, a sensing-control local closed loop is established, and it is guaranteed that when communication is interrupted, local safety takeover is achieved through the fuzzy controller; and finally, cloud-edge-end strategy alignment is realized, and autonomous operation in a network disconnection scene is supported. The problems of cognitive decision separation, high communication dependency, insufficient security redundancy and the like in a traditional method are solved.

The invention relates to an airport snow sweeper cooperative formation control method, electronic equipment and a medium, and the method comprises the steps: building a vehicle transverse and longitudinal coupling kinematic model in an airport snow removal environment based on environmental parameters, the vehicle transverse and longitudinal coupling kinematic model comprises transverse and longitudinal physical quantity cross terms, enabling the longitudinal speed to affect the transverse posture change, and enabling the longitudinal speed to affect the transverse posture change; the transverse path characteristics and the control input restrict the longitudinal motion; constructing a formation constraint model based on the vehicle transverse and longitudinal coupling kinematics model; constructing a distributed communication topology model based on a directed graph and an adjacent matrix; constructing a single vehicle local optimization control problem model; and iteratively solving the single vehicle local optimization control problem model based on a path guiding type distributed model predictive control algorithm to obtain the optimal control input of each vehicle. According to the method, control input can be optimized while accurate path tracking of the snow sweeper is ensured, energy consumption and cost are reduced, and collaboration, safety and efficiency of snow removal operation of an airport can be improved.

The invention discloses a mixed traffic flow hierarchical cooperative confluence control method, which belongs to the field of automatic driving, and comprises the following steps: constructing a utility function according to mixed traffic flow vehicle interaction characteristics, and constructing a confluence sequence optimization integer programming model according to the utility function; a motorcade communication network is constructed according to the vehicle real-time state information, a vehicle distance constraint and vehicle dynamics model is constructed according to the motorcade communication network, and a consistency controller is constructed according to the vehicle dynamics model; the method comprises the steps of obtaining vehicle real-time information, optimizing the vehicle real-time information through a confluence sequence optimization integer programming model to obtain an optimal confluence sequence, and performing calculation through a consistency controller according to the optimal confluence sequence and the vehicle real-time information to obtain vehicle control information. The interaction level of an automatic driving vehicle and a manual driving vehicle can be improved, and the automatic driving safety is improved.

Platoons of vehicles are operated remotely by a teleoperator. A lead vehicle of a platoon establishes communications with a teleoperator station, which receives drive state data from the lead vehicle and generates reference instructions for the lead vehicle. When a lead vehicle is under control of a teleoperator, and a follower vehicle joins a platoon with the lead vehicle, the follower vehicle receives drive state data from the lead vehicle and reference instructions for the lead vehicle from the teleoperator station. The follower vehicle captures data regarding its own drive state, and generates instructions based on the drive state data of the lead vehicle and the reference instructions for the lead vehicle. Drive state data of a lead vehicle of a platoon may be estimated, augmented or refined for accuracy based on drive state data of other vehicles of the platoon.

The invention discloses an automobile queue control method based on pipeline distributed model predictive control, and belongs to the field of intelligent automobiles and intelligent traffic. The method comprises the following steps: constructing a vehicle discrete dynamic model; establishing a queue cooperative control framework through vehicle-vehicle communication; introducing a wheel slip rate into the queue performance index function, and setting a longitudinal slip rate as a constraint; on the basis of nominal model predictive control, a nominal optimal control input sequence and an optimal state track are generated through decision making; and then the state of the disturbed vehicle is corrected in real time through an auxiliary control law, so that the disturbed vehicle is restrained near the optimal track. In the queue car-following control process, an interference suppression mechanism and tire nonlinear modeling are introduced into the system, and the limitation that the node vehicle stability and the full-queue control performance are not sufficiently considered in a traditional method is broken through. Even under the limiting working conditions of high-speed driving, low adhesion and the like, the stability and the good all-working-condition control performance of the automobile queue can be guaranteed.

The invention provides a method for determining a motorcade driving strategy and electronic equipment, and relates to the technical field of path planning, and the method comprises the steps: firstly, determining a comprehensive operation index of a motorcade based on cooperation data and a basic operation index of the motorcade; secondly, the collaborative data and interaction data and prior data of the motorcade are fused to obtain fused data, the interaction data are data of the current running state of the vehicle and the road condition of the environment where the vehicle is located, and the prior data are used for representing historical driving data matched with the current scene; and finally, based on the fusion data, the comprehensive operation index and the path planning data of the motorcade, determining a target driving strategy of the motorcade, the path planning data being a constraint for supporting path planning. The technical problem that in the prior art, cooperative requirements of distance control, path conflict avoidance and the like of the motorcade in an off-road environment are not considered, so that the overall passing efficiency and safety of the motorcade are insufficient is solved.

A method in an On-Demand Autonomy system includes: monitoring for a trip change request from a plurality of platoon vehicles including a first leader vehicle (Lv) and a follower vehicle (Fv). When a trip termination request is received from a platoon vehicle, the method includes broadcasting information regarding the request to the other platoon vehicles, and monitoring for an acknowledgement of the request. When the trip termination request originated from the first Lv, the method includes electing a new Lv, computing a rendezvous point for the new Lv and the Fv, and signaling the Fv and new Lv regarding the rendezvous point. When a trip modification request is received from the Fv, the method includes broadcasting information regarding the request to the first Lv, electing a new Lv, computing a rendezvous point for the new Lv and the Fv, and signaling the Fv and new Lv regarding the rendezvous point.