Method and system for analyzing the control of a vehicle
View Patent ↗A method and a system analyze the control of a vehicle having an autonomous driving unit. A change in the driving mode from autonomous driving to manual driving is detected, and at least one driving parameter before and/or after detecting the change is monitored. Based on driving values obtained by the monitoring with respect to the detected change in driving mode, at least one driving quantity quantifying the quality of interplay between the autonomous driving unit and a human driver is determined.
1. A method for improving a processor assessing a control of a vehicle having an autonomous driving unit, which comprises the steps of:
generating driving value data by:
detecting a change in a driving mode from autonomous driving to manual driving;
monitoring at least one driving parameter before and after detecting the change in the driving mode;
determining at least one driving quantity quantifying a quality of interplay between the autonomous driving unit and a human driver based on driving values obtained by the monitoring with respect to the change detected in the driving mode and a length of a time interval between the autonomous driving unit outputting a control takeover request and the human driver taking over control, wherein the length of the time interval is weighted by a vehicle dynamic variable obtained during the time interval and the at least one driving quantity being based on a product of the time interval and the vehicle dynamic variable during the time interval, wherein the product reaches or exceeds a threshold, and
the at least one driving quantity being further determined based on a quantity distribution, the quantity distribution being further determined based on driving value data obtained from at least one vehicle during a previous driving period of the at least one vehicle;
rating the control of the vehicle based on the at least one driving quantity;
training the autonomous driving unit by providing the driving value data corresponding to an above average rating to a neural network; and
performing at least two of:
using the rating for indicating usage-based product liability for vehicle insurance of autonomous vehicles;
determining responsibility of either the autonomous driving unit or the human driver in a case of an accident;
determining a capability of the autonomous driving unit to assess traffic scenarios and recognize potentially overtaxing driving situations to determine an insurance premium; and
calculating an insurance premium for the human driver of the vehicle based on the rating.
2. The method according to claim 1 , which further comprises storing the driving values obtained by the monitoring for a predetermined storage time interval spanning at least from a point in time before a control takeover request is outputted by the autonomous driving unit to a point in time the autonomous driving unit outputs the control takeover request.
3. The method according to claim 1 , wherein the at least one driving quantity is a composite quantity.
4. The method according to claim 1 , which further comprises determining the at least one driving quantity based on an autonomous driving quantity quantifying a quality of a driving of the autonomous driving unit before the change in the driving mode and on a manual driving quantity quantifying a quality of a driving of the human driver after the change in the driving mode.
5. The method according to claim 4 , wherein the at least one driving quantity is further based on mileage accumulated in a respective driving mode.
6. The method according to claim 1 , which further comprises determining the at least one driving quantity based on an autonomous driving quantity quantifying a quality of a driving of the autonomous driving unit after a control takeover request is outputted by the autonomous driving unit and on a manual driving quantity quantifying a quality of a driving of the human driver subsequently to the human driver taking over control.
7. The method according to claim 6 , wherein the at least one driving quantity is further based on accident rate values for autonomous driving or manual driving after a takeover control request is outputted by the autonomous driving unit and subsequently to the human driver taking over control, respectively.
8. The method according to claim 1 , which further comprises determining the at least one driving quantity based on the driving values obtained by the monitoring during a predetermined first time interval prior to the autonomous driving unit outputting a control takeover request.
9. The method according to claim 1 , wherein the at least one driving quantity is interrelated to a quantity distribution of the driving quantity.
10. The method according to claim 1 , which further comprises determining the quantity distribution based on the driving value data provided by a plurality of vehicles.
11. The method according to claim 10 , which further comprises generating the driving value data by driving value statistic processors provided in each of the plurality of vehicles, the driving value statistic processors monitoring at least one driving parameter of each of the plurality of vehicles and transmitting corresponding driving values to a server.
12. The method according to claim 1 , wherein the monitoring of at least one driving parameter includes monitoring at least the following: vehicle speed; vehicle acceleration; and vehicle deceleration.
13. A system for analyzing a control of a vehicle having an autonomous driving unit, the system comprising:
a detector configured to detect a change in a driving mode from autonomous driving to manual driving;
a sensor configured to monitor at least one driving parameter before and after the change in the driving mode was detected; and
a processor configured to:
determine at least one driving quantity quantifying a quality of interplay between the autonomous driving unit and a human driver based on driving values obtained by said sensor with respect to the change in the driving mode and a length of a time interval between the autonomous driving unit outputting a control takeover request and the human driver taking over control, wherein the length of the time interval is weighted by a vehicle dynamic variable obtained during the time interval and the at least one driving quantity further based on a product of the time interval and the vehicle dynamic variable during the time interval, wherein the product reaches or exceeds a threshold;
the at least one driving quantity being determined further based on a quantity distribution, the quantity distribution being determined based on driving value data obtained from at least one vehicle during a previous driving period of the at least one vehicle;
rate the control of the vehicle based on the at least one driving quantity; and
calculate an insurance premium for the human driver of the vehicle based on the rating and determine a responsibility of either the autonomous driving unit or the human driver in a case of an accident;
wherein the autonomous driving unit is trained by providing the driving values corresponding to an above average rating to a neural network.