Driver assistance system with vehicle states, environment and driver intention

A driver assistance system, the system comprising:

• a first interface for sensing external signals coming from an environment of a vehicle and generating a first interface output signal, the first interface comprising projective sensors and non-projective sensors,
• a second interface for sensing internal signals of the vehicle and generating a second interface output signal,
• a first subsystem comprising
• an information fusion module, a vehicle environment representation module, a vehicle environment interpretation module, and a knowledge base for storing representations of detectable object associated attributes,
• wherein the information fusion module identifies an object based on the first interface output signals and provides the identity of the object to the knowledge base,
• wherein the knowledge base receives said identity of the object and provides attribute signals representing at least one attribute of the identified object to the vehicle environment representation module, and
• wherein the vehicle environment representation module generates a central model of the vehicle environment comprising at least one representation of an object, wherein each representation of an object comprises the identity of the object and at least one object attribute,
• wherein the vehicle environment interpretation module sends data to the vehicle environment representation module to guide a filtering process that filters identified objects from the central model of the vehicle environment based on relevance,
• a second subsystem for modeling a current internal state of the vehicle based on the second interface output signal,
• a third subsystem for modeling a driver intention,
• a fourth subsystem for analyzing the central model of the vehicle environment represented by the first subsystem, for ranking a hierarchy of action signals, the action signals generated based on the output signals of the second and the third subsystems, wherein the ranking is based on the modeled driver intention, and for generating stimuli for an actuator of the vehicle or the driver based on a highest ranked action signal in the hierarchy.

A method for assisting a driver of a vehicle, comprising the following steps:

• sensing external signals of the vehicle using projective sensors and non-projective sensors,
• sensing internal signals of the vehicle,
• identifying an object based on the external signals of the vehicle and providing the identity of the object to a knowledge base for storing representations of detectable object associated attributes, which in response provides attribute signals representing at least one attribute of the identified object,
• generating a central model of the vehicle environment comprising at least one representation of an object, wherein each representation of an object comprises the identity of the object and at least one object attribute,
• filtering identified objects from the central model of the vehicle environment based relevance,
• modeling a driver intention,
• analyzing the central model of the vehicle environment in order to distinguish external environmental conditions relevant to the vehicle, and
• combining the analyzed central model of the vehicle environment and the behavior of the driver in order to generate rank a hierarchy of action signals, the action signals based on the relevant identified objects, wherein the ranking is based on the modeled driver intention, and in order to output a stimulus for an actuator of the vehicle or the driver based on a highest ranked action signal in the hierarchy.

A computer software program product embodied on a computer readable medium which when executed by a computer performs the method steps of:

• sensing external signals of a vehicle using projective sensors and non-projective sensors,
• sensing internal signals of the vehicle,
• identifying an object based on the external signals of the vehicle and providing the identity of the object to a knowledge base for storing representations of detectable object associated attributes, which in response provides attribute signals representing at least one attribute of the identified object,
• generating a central model of the vehicle environment comprising at least one representation of an object, wherein each representation of an object comprises the identity of the object and at least one object attribute,
• filtering identified objects from the central model of the vehicle environment based on relevance,
• modeling a driver intention,
• analyzing the central model of the vehicle environment in order to distinguish external environmental conditions relevant to the vehicle, and
• combining the analyzed central model of the vehicle environment and the behavior of the driver in order to generate rank a hierarchy of action signals, the action signals based on the relevant identified objects, wherein the ranking is based on the modeled driver intention, and in order to output a stimulus for an actuator of the vehicle or the driver based on a highest ranked action signal in the hierarchy.

A method for assisting a driver of a vehicle, comprising the following steps:

• sensing external signals of the vehicle using projective sensors and non-projective sensors,
• sensing internal signals of the vehicle,
• identifying an object based on the external signals of the vehicle and providing the identity of the object to a knowledge base for storing representations of detectable object associated attributes, which in response provides attribute signals representing at least one attribute of the identified object,
• generating a central model of the vehicle environment comprising at least one representation of an object, wherein each representation of an object comprises the identity of the object and at least one object attribute,
• filtering identified objects from the central model of the vehicle environment based on relevance,
• modeling a driver intention, and
• analyzing the central model of the vehicle environment, ranking a hierarchy of action signals, the action signals based on the relevant identified objects, wherein the ranking is based on the modeled driver intention, and generating a stimulus for at least one of an actuator of the vehicle or the driver based on a highest ranked action signal in the hierarchy.

A computer software program product embodied on a computer readable medium which when executed by a computer performs the method steps of:

• sensing external signals of the vehicle using projective sensors and non-projective sensors,
• sensing internal signals of the vehicle,
• identifying an object based on the external signals of the vehicle and providing the identity of the object to a knowledge base for storing representations of detectable object associated attributes, which in response provides attribute signals representing at least one attribute of the identified object,
• generating a central model of the vehicle environment comprising at least one representation of an object, wherein each representation of an object comprises the identity of the object and at least one object attribute,
• filtering identified objects from the central model of the vehicle environment based on relevance,
• modeling a driver intention, and
• analyzing the central model of the vehicle environment, ranking a hierarchy of action signals, the action signals based on the relevant identified objects, wherein the ranking is based on the modeled driver intention, and generating a stimulus for at least one of an actuator of the vehicle or the driver based on a highest ranked action signal in the hierarchy.

A driver assistance system comprising:

• a first interface for sensing external signals received from an environment of a vehicle and generating a first interface output signal,
• a second interface for sensing internal signals of the vehicle and generating a second interface output signal,
• a first subsystem comprising
• an information fusion module, a vehicle environment representation module, and a knowledge base for storing representations of detectable object associated attributes,
• wherein the information fusion module identifies an object based on the first interface output signal and provides the identity of the object to the knowledge base,
• wherein the knowledge base receives said identity of the object and provides attribute signals representing at least one object attribute of the identified object to the vehicle environment representation module, and
• wherein the vehicle environment representation module generates a central model of the vehicle environment comprising at least one representation of an object, wherein each representation of an object comprises the identity of the object and at least one object attribute, and
• a second subsystem for modeling a current internal state of the vehicle based on the second interface output signal,
• a third subsystem for modeling a driver intention,
• a fourth subsystem for analyzing the central model of the vehicle environment represented by the first subsystem in order to distinguish external environmental conditions relevant to the vehicle, and
• a fifth subsystem for ranking a hierarchy of action signals, the action signals generated based on the output signals of the second, the third and the fourth subsystems, wherein the ranking is based on the modeled driver intention, and for generating stimuli for an actuator of the vehicle or the driver based on a highest ranked action signal in the hierarchy.