Systems and methods for generating simulated LiDAR data using RADAR and image data are provided. An algorithm is trained using deep-learning techniques such as loss functions to generate simulated LiDAR data using RADAR and image data. Once trained, the algorithm can be implemented in a system, such as a vehicle, equipped with RADAR and image sensors in order to generate simulated LiDAR data describing the system's environment. The simulated LiDAR data may be used by a vehicle control system to determine, generate, and implement modified driving operations.

Original sensor data is received from one or more sensors of a vehicle. Free space around the vehicle is identified according to the sensor data, such as by identifying regions where data points have a height below a threshold. A location for an object model is selected from the free space. A plane is fitted to sensor data around the location and the object model is oriented according to an orientation of the plane. Sensing of the object model by a sensor of the vehicle is simulated to obtain simulated data, which is then added to the original sensor data. Sensor data corresponding to objects that would have been obscured by the object model is removed from the original sensor data. Augmented sensor data may be used to validate a control algorithm or train a machine learning model.

Example methods and systems for detecting weather conditions using vehicle onboard sensors are provided. An example method includes receiving laser data collected for an environment of a vehicle, and the laser data includes a plurality of laser data points. The method also includes associating, by a computing device, laser data points of the plurality of laser data points with one or more objects in the environment, and determining given laser data points of the plurality of laser data points that are unassociated with the one or more objects in the environment as being representative of an untracked object. The method also includes based on one or more untracked objects being determined, identifying by the computing device an indication of a weather condition of the environment.

Implementations of the disclosed subject matter provide a device of a mobile robot may include a motor to drive a drive system to move the mobile robot in an area, and a light source to output ultraviolet light. The device may include at least one first sensor to determine at least one of an orientation of the mobile robot, a location of the mobile robot, and/or when the light source is within a predetermined distance of an object in the area. The device may include a controller, communicatively coupled to the drive system, the light source, and the at least one first sensor to control the drive system so as to stop or move the mobile robot before the light source is within the predetermined distance of the object based on at least a signal received from the at least one first sensor.

Some radar sensors may provide a Doppler measurement indicating a relative velocity of an object to a velocity of the radar sensor. Techniques for determining a two-or-more-dimensional velocity from one or more radar measurements associated with an object may comprise determining a data structure that comprises a yaw assumption and a set of weights to tune the influence of the yaw assumption. Determining the two-or-more-dimensional velocity may further comprise using the data structure as part of regression algorithm to determine a velocity and/or yaw rate associated with the object.

A method, system, apparatus, and architecture are provided for generating a sound-enhanced sensing envelope. A plurality of sensors and one or more passive sound sensors of a vehicle are used to collect and process sensor data signals characterizing an exterior environment of the vehicle, thereby generating a sensing envelope around the vehicle using direct sensing data signals and a sound-enhanced sensing envelope around the vehicle using indirect sensing data signals. The sound-enhanced sensing envelope is used to evaluate advanced driver assistance system commands for the vehicle with respect to safety-related events identified by the indirect sensing data signals.

A method of sensing a three-dimensional (3D) space using at least one sensor is proposed. The method can include acquiring spatial information over time for the sensed 3D space, applying a neural network based object classification model to the acquired spatial information over time to identify at least one object in the sensed 3D space. The method can also include tracking the sensed 3D space including the identified at least one object, and using information related to the tracked 3D space.

A method for controlling a vehicle (100) includes reading-in measurement data about a surface (6) of a substrate (2) lying ahead of the vehicle (100) in its travel direction (F), where the surface contains a ground-level obstacle (4) and recognizing the ground-level obstacle (4) from the measurement data. The method also includes determining a movement vector (V4) of the recognized ground-level obstacle (4) in a vehicle-associated coordinate system on the basis of the measurement data read in and determining a movement vector (V1) of the vehicle (100) in a coordinate system superordinate relative to the vehicle-associated coordinate system. The method further includes checking whether the ground-level obstacle (4) is a dynamic ground-level obstacle (4) in the superordinate coordinate system and emitting a control signal for controlling an operational safety system (30) of the vehicle (100) as a function of the result of the check. Also disclosed is a control unit (200) for carrying out a method of that type and a vehicle (100) with a control unit (200) of that type.

A method includes determining a current state of an environment of an autonomous agent, such as a vehicle. The method also includes determining, via a first neural network, a set of actions based on the current state. The method further includes determining whether further analysis of the set of actions is desired. The method selects an action from the set of actions using a model-based solution based on a reward and a risk of the action when further analysis is desired. The method also includes selecting the action from the set of actions according to a metric when further analysis is not desired. The method controls the autonomous agent to perform the selected action.

A scenario aware perception system (10) suitable for use on an automated vehicle includes a traffic-scenario detector (14), an object-detection device (24), and a controller (32). The traffic-scenario detector (14) is used to detect a present-scenario (16) experienced by a host-vehicle (12). The object-detection device (24) is used to detect an object (26) proximate to the host-vehicle (12). The controller (32) is in communication with the traffic-scenario detector (14) and the object-detection device (24). The controller (32) configured to determine a preferred-algorithm (36) used to identify the object (26). The preferred-algorithm (36) is determined based on the present-scenario (16).