FIELD: vehicles.
SUBSTANCE: invention relates to operational vehicle control and driving, including autonomous operational vehicle control and autonomous driving. The method for moving in a vehicle transport network comprises determination of the operational information of the vehicle for the vehicle, including measuring the global position of the vehicle, wherein the vehicle constitutes an autonomous vehicle or a semi-autonomous vehicle, then the determining the estimate of the metric location of the vehicle using the operational information of the vehicle, including determining the estimate of the metric location using the measured global position as the input data in a nonlinear loss function with filtering by means of a Kalman filter in order to alleviate the effects from an unmodelled sensor error. The information on the operating environment of a part of the vehicle transport network is then determined, wherein the information on the operating environment includes the data from the sensors of the part of the vehicle transport network available for observation on the vehicle, wherein the data from the sensors comprises the data on the location of the remote vehicle, then determining the estimate of the topological location of the vehicle in the vehicle transport network using the estimate of the metric location and the information on the operating environment, and moving by means of the vehicle in the vehicle transport network based on the estimate of the topological location of the vehicle. In order to determine the estimate of the metric location, a nonlinear loss function with a Kalman filter can alleviate the effects from unmodelled sensor errors. Also described are methods using hidden Markov models and the distance of a ground moving object for determining the estimate of the topological location.
EFFECT: increase in the accuracy of determining the location of the vehicle.
20 cl, 9 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD FOR VISUAL LOCALIZATION OF URBAN RAIL TRANSPORT BASED ON KALMAN PARTICLE FILTERS AND MAPPING DATA | 2023 |
|
RU2807978C1 |
| SYSTEM AND METHOD FOR DETERMINING TRAJECTORY FOR VEHICLE | 2016 |
|
RU2681984C1 |
| OPERATIONAL CONTROL OF AUTONOMOUS VEHICLE, INCLUDING OPERATION OF MODEL INSTANCE OF PARTIALLY OBSERVED MARKOV PROCESS OF DECISION MAKING | 2017 |
|
RU2734744C1 |
| TRAFFIC NETWORK BLOCKING TRACKING DURING OPERATIONAL CONTROL OF AUTONOMOUS VEHICLE | 2017 |
|
RU2734732C1 |
| CONTROL OF AUTONOMOUS VEHICLE OPERATIONAL CONTROL | 2017 |
|
RU2725920C1 |
| REAL-TIME VEHICLE CONTROL | 2017 |
|
RU2733015C1 |
| STRUCTURE OF PROBABILISTIC OBJECT TRACKING AND FORECASTING | 2018 |
|
RU2756872C1 |
| METHOD AND SYSTEM FOR PREDICTING A MANOEUVRE OF THE OBJECT | 2021 |
|
RU2778300C1 |
| OPTIONS FOR AUTONOMOUS VEHICLE OPERATION | 2017 |
|
RU2744640C1 |
| OPERATION OF VEHICLE IN QUESTION USING PREDICTION OF INTENTIONS OF REMOTE VEHICLES | 2016 |
|
RU2714056C2 |
