Route prediction system

Patent metadata

Field	Value
Publication number	US-2018182245-A1
Application number	US-201615739650-A
Country	US
Kind code	A1
Filing date	Apr 27, 2016
Priority date	Jul 2, 2015
Publication date	Jun 28, 2018
Grant date	—

Abstract

The route prediction system according to the invention includes a measurement unit to measure an area including a host vehicle and other moving vehicles, a vehicle detection unit to detect the host vehicle and at least two of the surrounding vehicles having collision possibilities on the basis of observation results observed by the observation unit, a hypothesis generation unit to generate plural hypotheses for the at least two of the surrounding vehicles detected by the vehicle detection unit to avoid collision, a likelihood calculation unit to calculate a likelihood indicating probability of occurrence of each of the plural hypotheses generated by the hypothesis generation unit, and a predicted route analysis unit to analyze, on the basis of the likelihood calculated by the likelihood calculation unit, predicted routes of the at least two of the surrounding vehicles, and output the analysis result. With such a configuration, in a case where plural vehicles may collide in future, predicted routes of the plural surrounding vehicles can be calculated without contradiction, improving performance on predicting the routes of the surrounding vehicles.

First claim

1 - 10 . (canceled)

11 . A route prediction system comprising:
a processor to execute a program; and a memory to store the program which, when executed by the processor, performs processes of
observing a position of a host vehicle and positions and speeds of vehicles surrounding the host vehicle,
detecting the host vehicle and at least two of the surrounding vehicles having collision possibilities on a basis of the observation results,
generating a plurality of hypotheses for the at least two of the surrounding vehicles to avoid collision,
calculating a likelihood indicating probability of occurrence of each of the plurality of hypotheses,
analyzing predicted routes of the at least two of the surrounding vehicles on a basis of the likelihood, and
outputting the analysis result, wherein
the program performs, in the process of calculation the likelihood, a route prediction process, that is a process of predicting future positions of the at least two of the surrounding vehicles for each of the plurality of hypotheses, and
a hypothesis likelihood calculation process, that is a process of calculating the likelihood indicating the probability of occurrence of each of the plurality of hypotheses, on a basis of the future positions of the at least two of the surrounding vehicles.

12 . The route prediction system according to claim 11 , wherein the program performs, in the process of detection, processes of
detecting a lane where the host vehicle is located, on a basis of the observation results, tracking the surrounding vehicles on a basis of the observation results, and detecting, among the tracked surrounding vehicles, the at least two of the surrounding vehicles having collision possibilities.

13 . The route prediction system according to claim 11 , wherein the program performs, in the hypothesis likelihood calculation process, a process of calculating, on a basis of estimated speeds and estimated speed errors at a current time of the at least two surrounding vehicles, the likelihood indicating the probability of occurrence of each of the plurality of hypotheses.

14 . The route prediction system according to claim 11 , wherein the program performs, in the hypothesis likelihood calculation process, a process of calculating, on a basis of estimated accelerations and estimated acceleration errors at a current time of the at least two surrounding vehicles, the likelihood indicating the probability of occurrence of each of the plurality of hypotheses.

15 . The route prediction system according to claim 11 , wherein the program performs, in the process of analyzing predicted routes, processes of selecting and outputting the predicted routes of the at least two of the surrounding vehicles on a basis of the likelihood.

16 . The route prediction system according to claim 11 , wherein the program performs, in the process of analyzing predicted routes, a predicted route confidence level process, that is a process of calculating, on a basis of the likelihood, a predicted route confidence level indicating probability of occurrence of each of the predicted routes of the at least two of the surrounding vehicles for each of the predicted routes.

17 . The route prediction system according to claim 11 , wherein the program performs, in the process of analyzing predicted routes, a predicted route confidence level process, that is a process of calculating, on a basis of the likelihood, a confidence level of each of the plurality of hypotheses including the predicted routes of the at least two of the surrounding vehicles.

18 . The route prediction system according to claim 16 , wherein the program performs, in the predicted route confidence level process, a process of calculating the predicted route confidence level for each of the predicted routes, on a basis of a confidence level of each of the plurality of hypotheses including the predicted routes of the at least two of the surrounding vehicles calculated at a preceding time.

19 . The route prediction system according to claim 17 , wherein the program performs, in the predicted route confidence level process, a process of calculating a predicted route confidence level for each of the predicted routes, on a basis of a confidence level of each of the plurality of hypotheses including the predicted routes of the at least two of the surrounding vehicles calculated at a preceding time.

20 . A route prediction system comprising:
a processor to execute a program; and a memory to store the program which, when executed by the processor, performs processes of
observing a position of a host vehicle and positions and speeds of vehicles surrounding the host vehicle,
generating, on a basis of the observation results, a plurality of hypotheses expressing collision avoidance models for at least two of the detected surrounding vehicles having collision possibilities,
calculating predicted route confidence levels of predicted routes of the at least two of the surrounding vehicles corresponding to each of the plurality of hypotheses, and
displaying, on a basis of the predicted route confidence levels, the predicted routes and the predicted route confidence levels of the at least two of the surrounding vehicles.

21 . A route prediction system comprising:
a sensor to observe a position of a host vehicle and positions and speeds of vehicles surrounding the host vehicle; a processor to execute a program; a memory to store the program which, when executed by the processor, performs processes of
generating, on a basis of the observation results observed by the sensor, a plurality of hypotheses expressing collision avoidance models for at least two of the detected surrounding vehicles having collision possibilities, and
calculating predicted route confidence levels of predicted routes of the at least two of the surrounding vehicles corresponding to each of the plurality of hypotheses; and
a display to display, on a basis of the predicted route confidence levels, the predicted routes and the predicted route confidence levels of the at least two of the surrounding vehicles.

22 . A route prediction system comprising processing circuitry
to observe a position of a host vehicle and positions and speeds of vehicles surrounding the host vehicle, to detect the host vehicle and at least two of the surrounding vehicles having collision possibilities on a basis of the observation results, to generate a plurality of hypotheses for the at least two of the surrounding vehicles to avoid collision, to calculate a likelihood indicating probability of occurrence of each of the plurality of hypotheses, to analyze predicted routes of the at least two of the surrounding vehicles on a basis of the likelihood, and to output the analysis result, wherein the processing circuitry, in the calculation of the likelihood, predicts future positions of the at least two of the surrounding vehicles for each of the plurality of hypotheses, and
calculates hypothesis likelihood indicating the probability of occurrence of each of the plurality of hypotheses, on a basis of the future positions of the at least two of the surrounding vehicles.

23 . The route prediction system according to claim 22 , wherein the processing circuitry, in detection of the vehicles,
detects a lane where the host vehicle is located, on a basis of the observation results, tracks the surrounding vehicles on a basis of the observation results, and detects, among the tracked surrounding vehicles, the at least two of the surrounding vehicles having collision possibilities.

24 . The route prediction system according t

Assignees

• Mitsubishi Electric Corp

Inventors

• Takabayashi Yuki
• Obata Yasushi
• Konishi Kyosuke

Classifications

• G08G1/164

  Centralised systems, e.g. external to vehicles · CPC title

• G08G1/133

  within the vehicle {; Indicators inside the vehicles or at stops} · CPC title

• H04W4/44

  for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H] · CPC title

• G08G1/166 Primary

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• B60W60/00276

  for two or more other traffic participants · CPC title