Early warning and collision avoidance

Abstract

Among other things, equipment is located at an intersection of a transportation network. The equipment includes an input to receive data from a sensor oriented to monitor ground transportation entities at or near the intersection. A wireless communication device sends to a device of one of the ground transportation entities, a warning about a dangerous situation at or near the intersection, there is a processor and a storage for instructions executable by the processor to perform actions including the following. A machine learning model is stored that can predict behavior of ground transportation entities at or near the intersection at a current time. The machine learning model is based on training data about previous motion and related behavior of ground transportation entities at or near the intersection. Current motion data received from the sensor about ground transportation entities at or near the intersection is applied to the machine learning model to predict imminent behaviors of the ground transportation entities. An imminent dangerous situation for one or more of the ground transportation entities at or near the intersection is inferred from the predicted imminent behaviors. The wireless communication device sends the warning about the dangerous situation to the device of one of the ground transportation entities.

1 . A method comprising
 using electronic sensors located in a vicinity of an intersection of a ground transportation network to monitor the intersection and approaches to the intersection, the electronic sensors generating motion data about ground transportation entities moving on the approaches or in the intersections,   defining distinct virtual zones in the intersection and the approaches to the intersection,   segmenting the motion data according to corresponding virtual zones to which the generated motion data relates,   applying the generated motion data for each of the respective segments to a machine learning model running in equipment located in the vicinity of the intersection to predict an imminent dangerous situation in the intersection or one of the approaches involving one or more of the ground transportation entities,   before the imminent dangerous situation becomes an actual dangerous situation, wirelessly transmitting a warning to a device associated with at least one of the involved ground transportation entities.   
     
     
         2 . The method of  claim 1  in which the device associated with each of the ground transportation entities comprises a wearable, a smart phone, or another mobile device. 
     
     
         3 . The method of  claim 1  in which at least one of the ground transportation entities comprises a motorized vehicle. 
     
     
         4 . The method of  claim 1  in which the machine learning model is provided to the equipment located in the vicinity of the intersection by a remote server through the Internet. 
     
     
         5 . The method of  claim 1  in which the machine learning model is generated at the equipment located in the vicinity of the intersection. 
     
     
         6 . The method of  claim 1  comprising training the machine learning model using motion data generated by the sensors located in the vicinity of the intersection. 
     
     
         7 . The method of  claim 1  comprising sending motion data generated by the sensors located in the vicinity of the intersection to a server for use in training the machine learning model. 
     
     
         8 . The method of  claim 1  comprising using the electronic sensors to monitor an area in or nearby a crosswalk that crosses one of the approaches to the intersection. 
     
     
         9 . The method of  claim 1  comprising using the electronic sensors to generate motion related data representing physical properties of a vulnerable road user in the vicinity of the crosswalk. 
     
     
         10 . The method of  claim 1  comprising deriving trajectory information about the vulnerable road user from motion data generated by the sensor. 
     
     
         11 . The method of  claim 1  in which there is a machine learning model for each of the approaches to the intersection. 
     
     
         12 . The method of  claim 1  comprising determining whether to transmit the warning based also on motion data generated by sensors with respect to another nearby intersection. 
     
     
         13 . The method of  claim 1  comprising determining whether to transmit the warning based also on information received from ground transportation entities moving on the approaches or in the intersection. 
     
     
         14 . The method of  claim 1  in which the intersection is signalized and information about the state of the signals is received. 
     
     
         15 . The method of  claim 1  in which the intersection is not signalized and is controlled by one or more signs. 
     
     
         16 . The method of  claim 15  in which the defined virtual zones include one or more approaches controlled by the signs. 
     
     
         17 . The method of  claim 15  in which the signs comprise a stop sign or a yield sign. 
     
     
         18 . The method of  claim 15  in which one of the ground transportation entities comprises a rail vehicle.