Implementations a method using a collision detection device associated with a user to detect a moving object in an environment and provide an alert to the user are provided. In some implementations the environment comprises at least one transmitter of opportunity. In some implementations, the collision detection device comprises a receiver and a processor. In some implementations, the method comprises receiving at the collision detection device Wi-Fi signals reflected from the moving object where the Wi-Fi signals originate from a Wi-Fi source not associated with the moving object. The method further comprises detecting, measuring, and tracking the Doppler effect of the Wi-Fi signals at the collision detection device to track velocity vector relative to the collision detection device. The method further comprises calculating the time of arrival of the moving object based on the velocity vector relative to the location of the collision detection device. The method further comprises tracking the relative angle between the moving object and the collision detection device based on the velocity vector. The method further comprises predicting the occurrence of a collision between the moving object and the collision detection device based on the relative angle. The method further comprises providing a notification based on the predicting step.

A method for determining the start of movement of a motor vehicle equipped with a system for monitoring tire pressure of a motor vehicle. Communication between the receiver and each pressure monitoring system emitter being subjected to a Doppler effect so that a periodic component is inserted by the emitter into the signal emitted to the receiver. The method includes: acquiring the intermediate-frequency signal before demodulation by a processor to extract data carried by the radiofrequency signal, determining the FFT of the IF signal, determining the average value of the FFT of the IF signal over a preset duration, and determining whether there is a frequency deviation by comparing the instantaneous value of the fast Fourier transform to the average value of the fast Fourier transform, if so, determining whether the emitter for monitoring the pressure of a tire is moving and that the vehicle is moving.

Embodiments of the invention are directed to a computer-implemented method that includes determining, by a vehicle controller associated with a vehicle, a typical driving behavior of a driver of the vehicle. The method also includes detecting, by the vehicle controller associated with the vehicle, that the driver has deviated from the typical driving behavior. The method also includes transmitting a notification that indicates that the driver has deviated from the typical driving behavior.

Vehicles can be operated according to an artificial intelligence model contained in an on-board processor. The AI model can analyze sensor data, such as visible or infrared images of traffic, and determine when a collision is possible, whether it has become imminent, and whether the collision is avoidable or unavoidable using sequences of accelerations, braking, and steering. The AI model can also select the most appropriate sequence of actions from a large plurality of calculated sequences to avoid the collision if avoidable, and to minimize the harm if unavoidable. The AI model can also cause a processor to actuate linkages connected to the throttle (or electric power control), brakes (or regenerative braking), and steering to implement the selected sequence of actions. Thus the collision can be avoided or mitigated by an ADAS system or a fully autonomous vehicle.

Disclosed are systems and methods for autonomous vehicles and vehicles with automatic driver-assistance systems (ADAS) to automatically detect an imminent collision, determine whether the collision is avoidable or unavoidable, and plot a course minimizing the hazard using an artificial intelligence (AI) model. For example, a collision is avoidable if the vehicle can avoid it by steering, braking, and/or accelerating in a particular sequence. The AI model finds the best sequence for collision avoidance, and if that is not possible, it finds the best sequence for minimizing the harm. The harm is based on an estimated number of fatalities, injuries, and property damage predicted to be caused in the collision. The AI-based situation analysis and sequence selection are directly applicable to human-driven vehicles with an emergency-intervention ADAS system, as well as fully autonomous vehicles. With fast electronic reflexes and multi-sensor situation awareness, the AI model can save lives on the highway.

A first phantom vehicle is projected into one of a branch and a circle lane of a roundabout in association with a first autonomous vehicle. The first autonomous vehicle is caused to enter the circle lane upon predicting no collision with oncoming vehicles. The first autonomous vehicle is caused to exit from the roundabout.

A traveling control apparatus performs a target-following control process on a target to be followed detected by a target detecting unit. Further, the traveling control apparatus calculates a probability that the target to be followed is within an own lane, and determines whether a degree of recognition by the target detecting unit of the target to be followed is in a weakly recognized state where the degree of recognition is weaker than a predetermined degree. The apparatus sets a reliability of the target to be followed on the basis of the probability calculated by a probability calculating process and a determination result by a determining process, and controls acceleration of an own vehicle so that a jerk which is a differential value of the acceleration becomes smaller as the reliability of the target to be followed is lower while the target-following control process is performed.

Human drivers generally cannot plan a collision evasion maneuver in the brief interval before impact, other than simply slamming on the brakes and hoping for the best. Often the collision could have been avoided by swerving or other sequence of actions. Therefore, improved collision avoidance and mitigation procedures are disclosed, based on a well-trained artificial intelligence (AI) model that takes over the accelerator, brake, and steering in an emergency. With fast electronic reflexes and AI-based computational power, the AI model can find a more effective avoidance maneuver, or at least an action that would minimize the harm (for example, by swerving to miss the passenger compartment). The AI model can then implement the sequence instantly, without fear or hesitation. The resultfewer collisions and less fatality on our highways.

The present invention provides a method and an apparatus for dynamically controlling the luminance of a tail light of a vehicle tail lamp in response to a change in the difference of speed between a vehicle and a vehicle therebehind, and for preventing a collision between the traveling vehicles. In addition, the apparatus comprises: a tail light operating unit, which slowly or rapidly becomes brighter up to a predetermined brightness as the speed difference between the vehicle and the vehicle behind gradually becomes larger, and slowly or rapidly becomes darker down to a predetermined brightness as the speed difference between the vehicle and the vehicle behind gradually becomes smaller; a speed sensing unit for measuring the speed of the vehicle; a rear speed sensing unit for measuring the speed of the vehicle therebehind; and a control unit for automatically adjusting the luminance of the tail light by controlling the tail light operating unit when the vehicle therebehind is traveling faster than the vehicle.

A first vehicle in traffic can use machine learning and artificial intelligence to detect an imminent collision with a second vehicle or other object. A well-trained AI algorithm can select a sequence of actions (braking, swerving, or acceleratingdepending on the specific kinetics) to avoid the collision if possible, and to reduce or minimize the harm if unavoidable. With proper training, the AI model may also infer the intent and future actions of the second vehicle, as well as potential interference of other traffic agents. A good algorithm can also infer the intent of the driver of the first vehicle, for example based on prior driving habits. The AI algorithm may be implemented in a processor on the subject vehicle, potentially in communication with another processor at a fixed site such as a local access point or a central supercomputer. With super-fast AI solutions, lives will be saved!