The invention discloses an anti-collision control method based on depth reinforcement learning. A depth deterministic policy gradient method (DDPG algorithm) is adopted for depth reinforcement learning, and the anti-collision control method includes the steps that first, vehicle parameters and environmental vehicle parameters are extracted; second, a virtual environment model is constructed through the vehicle parameters and the environmental vehicle parameters; third, according to the vehicle parameters, the environmental vehicle parameters and the virtual environment model, basic parametersof the depth deterministic policy gradient method are defined; fourth, according to the basic parameters defined in the third step, a neural network in depth reinforcement learning is used for constructing an anti-collision control decision making system, and the anti-collision control decision making system comprises a strategy network and an evaluation network; and fifth, the strategy network and the evaluation network are trained, and the anti-collision control decision making system is obtained. According to the anti-collision control method based on depth reinforcement learning, the anti-collision control decision making system based on the depth neural network and the anti-collision control decision making system for constantly optimizing network control results based on a time difference reinforcement learning method are constructed, and the control performance of the anti-collision control decision making system is improved effectively.

Anti-collision control method based on depth reinforcement learning

The invention relates to the field of vehicle cruise control, in particular to a self-adaptive cruise control method and system. A lateral control remind function is added on the basis of the longitudinal control of the vehicle adaptive cruise. When a lane change is required in adaptive cruising, by judging the distance between the vehicle in front of the adjacent lane and the vehicle, it is determined whether lane change reminder is needed, and the reminder of lane change timing is realized through different control strategies, which can help users accurately control lane change timing, reduce the loss caused by lane change timing misalignment, and ensure driving safety.

Self-adaptive cruise control method and system

The invention discloses a self-adaptive kinetic energy recovery method and system based on road and road condition information. The self-adaptive kinetic energy recovery method comprises the followingsteps that a data acquisition module acquires map data and vehicle surrounding road condition information and comprehensively determines vehicle and vehicle surrounding situations; when a driver releases an accelerator pedal and does not depress a brake pedal, a prediction module predicts a path P along which the vehicle is going to travel in the future T time according to the current vehicle steering input; a judging module judges whether an event requiring vehicle deceleration exists or not in the future T time in real time in combination with the vehicle surrounding situations and the pathalong which the vehicle is going to travel; and a processing module determines an optimal deceleration strategy and updates the strategy in real time; and a kinetic energy recovery module performs kinetic energy recovery according to the determined optimal deceleration strategy. The self-adaptive kinetic energy recovery method and system have the beneficial effects that the operating pressure ofthe driver is reduced, the riding comfort of the vehicle is improved, the energy use efficiency is improved, and the endurance mileage of the vehicle is increased.

Self-adaptive kinetic energy recovery method and system based on road and road condition information

The embodiment of the invention discloses a vehicle danger early warning method and a related product which are applied to a vehicle-mounted device The vehicle-mounted device comprises a plurality ofultraviolet light modules arranged on a vehicle The method comprises the steps of: detecting whether a target object exists in a preset range of the vehicle or not by a plurality of ultraviolet light modules, and if yes, obtaining motion parameters of the target object; acquiring the first driving parameter of the vehicle; estimating whether a collision risk exists between the vehicle and the target object or not according to the first driving parameter and the motion parameters; and if yes, sending alarm prompt information Therefore, by arranging the ultraviolet light modules arranged on the vehicle, the target object near the vehicle in the preset range can be detected, the possible collision danger between the vehicle and the target object is estimated, and therefore, vehicle dangerearly warning is achieved

Vehicle danger early warning method and related product

The invention provides a system and a method for emergency collision avoidance, and relates to the field of vehicle safety control. The emergency collision avoidance system comprises a trajectory prediction unit, a determining unit, a calculating unit, and a control unit. The trajectory prediction unit is used to continuously predict movement trajectory of a vehicle and at least one target objectaround the vehicle in future preset time. The determining unit is used to continuously determine whether the vehicle and the target object have collision risk according to the movement trajectory of the target object and the movement trajectory of the vehicle. The calculating unit is used to continuously calculate at least one collision avoidance path of the vehicle according to the movement trajectory of the vehicle and the movement trajectory of the target object. The control unit is used to change a travelling state of the vehicle to make the vehicle travel along the collision avoidance path according to a result calculated by the calculating unit. Using the system and the method for emergency collision avoidance can accurately and rationally schedule a collision avoidance path in realtime, so as to avoid collision to the maximum extent under the condition of ensuring safety of the vehicle.

Huo Ke

Papers

System and method for emergency collision avoidance