Aspects of the invention relate generally to autonomous vehicles. Specifically, the features described may be used alone or in combination in order to improve the safety, use, driver experience, and performance of these vehicles.

System and method for predicting behaviors of detected objects

Systems and methods are provided for controlling a vehicle A safe envelope driving pattern is determined to control the vehicle in an autonomous mode User identification data and sensor data are received from one or more sensors associated with the vehicle A driver-specific driving pattern is determined based on the received sensor data and the user identification data Operation of the vehicle is controlled in the autonomous mode based on the identification of the user in the driver's seat, the safe envelope driving pattern, and the user-specific driving pattern

Driving pattern recognition and safety control

Aspects of the disclosure relate generally to determining whether an autonomous vehicle should be driven in an autonomous or semiautonomous mode (where steering, acceleration, and braking are controlled by the vehicle's computer). For example, a computer may maneuver a vehicle in an autonomous or a semiautonomous mode. The computer may continuously receive data from one or more sensors. This data may be processed to identify objects and the characteristics of the objects. The detected objects and their respective characteristics may be compared to a traffic pattern model and detailed map information. If the characteristics of the objects deviate from the traffic pattern model or detailed map information by more than some acceptable deviation threshold value, the computer may generate an alert to inform the driver of the need to take control of the vehicle or the computer may maneuver the vehicle in order to avoid any problems.

Determining when to drive autonomously

Aspects of the disclosure relate to detecting and responding to objects in a vehicle's environment. For example, an object may be identified in a vehicle's environment, the object having a heading and location. A set of possible actions for the object may be generated using map information describing the vehicle's environment and the heading and location of the object. A set of possible future trajectories of the object may be generated based on the set of possible actions. A likelihood value of each trajectory of the set of possible future trajectories may be determined based on contextual information including a status of the detected object. A final future trajectory is determined based on the determined likelihood value for each trajectory of the set of possible future trajectories. The vehicle is then maneuvered in order to avoid the final future trajectory and the object.

Predicting trajectories of objects based on contextual information

A method and apparatus are provided for determining whether a driving environment has changed relative to previously stored information about the driving environment. The apparatus may include an autonomous driving computer system configured to detect one or more vehicles in the driving environment, and determine corresponding trajectories for those detected vehicles. The autonomous driving computer system may then compare the determined trajectories to an expected trajectory of a hypothetical vehicle in the driving environment. Based on the comparison, the autonomous driving computer system may determine whether the driving environment has changed and/or a probability that the driving environment has changed, relative to the previously stored information about the driving environment.

Determining changes in a driving environment based on vehicle behavior

A system for determination of kinematics of a moving object comprising: a sensor producing angular data for the object at a number of observation times, a state initialization unit, receiving angular data from the sensor and on basis thereof determining a first kinematic state of the object, and a tracking filter having a prediction unit, arranged to determine a predicted kinematics state of the object on bases of a kinematic model of the object, wherein the kinematic model comprises a guidance law locked on a known position, and at least one previously determined kinematic state of the object, and a state updating unit, receiving angular data from the sensor and the predicted kinematic state of the object, and on basis thereof determining an updated kinematic state of the object.

Tracking of a moving object

An avionics system including a radar system being capable of automatically tracking a radar target, an optical image producing system, a radar monitor, an optical image monitor, a decision support unit having a connection to the radar system and to the optical image producing system, and an input/output unit for entering one or more decision parameters. The decision support unit is connected to the input/output unit. During a flight mission the decision support unit receives one or more automatic radar tracking parameters from the radar system, uses the decision parameters on the radar tracking parameters to decide upon which radar target(s) to be subjected to observation by the optical image producing system.

Multi-sensor system

The present invention relates to a method suitable for, within a platform, merging data from different sensors of different platforms, comprising the steps of: generating a first information entity; receiving a second information entity; processing the first and second information entities. The invention is characterized by the steps of analysing said processed first and second information entities; and performing an action event in response to the analysis.

Method and arrangement for data fusion

Present invention relates to an arrangement, suitable for increasing data association accuracy, comprising means for generating a first data entity comprising a first information set and a second information set about at least one object; and means for generating a second data entity comprising a first information set and second information set about at least one object. The invention is characterized by means for generating at least one distance matrix depending upon the first information sets or the second information sets; means for gating said at least one generated distance matrix, and means for performing an association process depending upon the gated distance matrix.

Method and arrangement for processing data

A system for determination of kinematics of a moving object comprising: a sensor (1) producing angular data for the object at a number of observation times, a state initialization unit (7), receiving angular data from the sensor and on basis thereof determining a first kinematic state of the object, and a tracking filter (11) having a prediction unit, arranged to determine a predicted kinematics state of the object on bases of a kinematic model of the object, wherein the kinematic model comprises a guidance law locked on a known position, and at least one previously determined kinematic state of the object, and a state updating unit, receiving angular data from the sensor and the predicted kinematic state of the object, and on basis thereof determining an updated kinematic state of the object.

Leif Axelsson

Papers

Tracking of a moving object

Multi-sensor system

Method and arrangement for data fusion

Method and arrangement for processing data

Tracking of a moving object for a self-defence system