Abstract:
Various systems and methods for providing assistance at the end of an autonomous system journey are provided. A system can include an autonomous system configured to transport the user, a first sensor coupled to the autonomous system and configured to provide a sensor stream of an environment between the autonomous system and a terminus, and a terminus assistance processor mechanically coupled to the autonomous system. In an example, the terminus assistance processor can receive and process the sensor stream, detect and can track the user in the environment in response to the sensor stream, and can provide status information to a first mobile device based on the sensor stream.
Abstract:
A system for a distributed in-vehicle real-time sensor data processing can be adapted to receive a request for sensor data from vehicles. The system may be further adapted to generate an application for collection of the sensor data. The application may have sensor requirements for performing the collection of sensor data. The system may be further adapted to identify a set of vehicles for distribution of the application based on available sensors in each vehicle corresponding to the sensor requirements. The system may be further adapted to transmit the application to the set of vehicles and receive sensor data results from respective instances of the application executing on the set of vehicles. The system may be further adapted to transmit a command to remove the respective instances of the application from the set of vehicles.
Abstract:
A system, including: a communication interface operable to receive sensor data related to a state of an object; object state estimation processor circuitry operable to estimate, based on the sensor data, a prospective probability of a degradation of the state of the object; and cobot fleet control processor circuitry operable to generate a command for either a transport cobot operable to transport the object, or another actor, to take proactive action to mitigate the prospective probability of the degradation of the state of the object.
Abstract:
A mechanism is described for facilitating depth and motion estimation in machine learning environments, according to one embodiment. A method of embodiments, as described herein, includes receiving a frame associated with a scene captured by one or more cameras of a computing device; processing the frame using a deep recurrent neural network architecture, wherein processing includes simultaneously predicating values associated with multiple loss functions corresponding to the frame; and estimating depth and motion based the predicted values.
Abstract:
A device including a processor configured to: receive sensor measurements; determine a viewer position based on the received sensor measurements; generate a control signal based on the viewer position; and determine a view based on the viewer position.
Abstract:
According to various examples, a vehicle controller is described comprising a determiner configured to determine information about surroundings of a vehicle, the information about the surroundings comprising information about velocities of objects in the surroundings of the vehicle and a velocity controller configured to input the information about the surroundings of the vehicle and a specification of a path of the vehicle to a convolutional neural network, to determine a target velocity of the vehicle along the path based on an output of the convolutional neural network and to control the vehicle according to the determined target velocity.
Abstract:
A system for a vehicle may be configured to, for each combination including a driving behavior of one or more driving behaviors, a traffic situation of one or more traffic situations in which to implement the one or more driving behaviors, and an object hypothesis of one or more object hypotheses for each of the one or more traffic situations obtain, for the respective combination, one or more driving model parameters associated with the driving behavior and object hypothesis for the respective combination obtain, for the respective combination, a probability indicating a likelihood of an accident or collision for the respective combination determine, for the respective combination, a risk value based on the obtained safety driving parameters and the obtained probability for the respective combination; and select a driving behavior for each traffic situation based at least in part on the one or more determined risk values.
Abstract:
Methods, apparatuses, and systems may provide for using the motion of a vehicle to estimate the orientation of a camera system of a vehicle relative to the vehicle. Image data may be received from a plurality of cameras positioned on the vehicle, and a first constraint set may be determined for the plurality of cameras based on a plurality of feature points in a ground plane proximate to the vehicle. A second constraint set may be determined based on one or more borders of the vehicle. One or more of the cameras may be automatically calibrated based on the first constraint set and the second constraint set.
Abstract:
Mobility-as-a-Service (MaaS) provides technical solutions for technical problems facing this shift toward public and private vehicles for hire, including providing a platform for users to identify and select public transportation and private vehicles for hire. Users may plan and book transportation services through a MaaS platform, such as a smartphone application. Technical solutions described herein include improved identification and selection of a vehicle based on wireless communication, such as using Near-Field Communication (NFC), Bluetooth, Wi-Fi, and other wireless communication.
Abstract:
Aspects concern a method for controlling a braking of a vehicle. The method including detecting a braking situation, determining a classification of the braking situation, selecting a braking profile based on the determined classification, and applying a deceleration based on the selected braking profile to maintain a safety distance based on the selected braking profile.