Abstract: A computer-implemented method is provided that involves determining, based on map data, an approaching merge region comprising an on-ramp merging with a road comprising one or more lanes, wherein a truck is traveling on an initial lane of the road according to a navigation plan. The method involves an indication of movement of a vehicle on the on-ramp, wherein the indication of movement is based on data collected by one or more sensors configured to capture sensor data from an environment surrounding the truck. The method involves determining, for the on-ramp and the one or more lanes, respective avoidance scores indicative of a likelihood of an interaction between the truck and the vehicle based on the approaching merge region. The method involves updating the navigation plan based on the respective avoidance scores. The method also involves controlling the truck to execute a driving strategy based on the updated navigation plan.

Abstract: Example embodiments relate to lane adjustment techniques for slow lead agents. A vehicle computing system may use sensor data depicting the surrounding environment to detect when another vehicle is traveling in front of the vehicle at a speed that is less than a threshold minimum speed. If the other vehicle fails to increase speed above the minimum speed, the computing system may determine whether to change lanes to avoid the other vehicle based on speed data for other lanes. In some implementations, the computing system assigns penalties to lane segments surrounding the vehicle based on speed data for the different lane segments. For instance, the path finding system for the vehicle can use penalties and speed data to determine efficient routes that safely circumvent slow agents.

Abstract: A method and a system include a first inertial measurement unit (IMU) is positioned on a first member of a joint and a second IMU is positioned on a second member of the joint, where the first IMU and the second IMU each lack a magnetometer unit. A processing device receives first IMU sensor data and second IMU sensor data. The first IMU sensor data is inputted into a quaternion computation algorithm (QCA) to compute a first quaternion. The first quaternion and the second IMU sensor data are inputted into the QCA to compute a one second quaternion, where the inputting of the first quaternion imposes yaw constraints. A calibration parameter algorithm determines a mobility metric of the joint based on the first and the second quaternions, and an orientation and position of the first IMU on the first member and of the second IMU on the second member.

Abstract: Systems and methods for calculating mobility metrics associated to a plurality of wearable sensors in various arrangements comprising a plurality of communicatively-connected sensors comprising inertial measurement units (IMU) attached to connected bodies of a hinge or ball joint in communication with a computing device. Systems and methods for quaternion calculations comprising a first sensor's quaternion output as estimate into another sensor's quaternion calculation to improve the other sensor's quaternion estimate and vice versa. Systems and methods for data synchronization of a plurality of sensors involving building an external reference time vector and interpolating the sensor's data based on the reference time vector. Systems and methods for calculating a sensor's orientation and position based on the inertial measurements captured by the wearable sensors during hinge or ball joint movements to, at least, calculate a joint angle.

Abstract: Example embodiments relate to a method for cut-in identification and classification. An example embodiment includes a obtaining operational data about one or more vehicles; based on the operational data, identifying the presence of one or more cut-ins within the operational data; extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data; and, based on the extracted cut-in data, training a model for controlling an autonomous vehicle. Identifying the presence of a given cut-in includes: determining that at least one vertex of a bounding box surrounding a vehicle was located more than a threshold distance within a lane being navigated by a given vehicle; and determining that the ability of the given vehicle to maintain its course and speed was impeded by the presence of the particular additional vehicle within the lane.

Abstract: A computer-implemented method is provided that involves determining, based on map data, an approaching merge region comprising an on-ramp merging with a road comprising one or more lanes, wherein a truck is traveling on an initial lane of the road according to a navigation plan. The method involves an indication of movement of a vehicle on the on-ramp, wherein the indication of movement is based on data collected by one or more sensors configured to capture sensor data from an environment surrounding the truck. The method involves determining, for the on-ramp and the one or more lanes, respective avoidance scores indicative of a likelihood of an interaction between the truck and the vehicle based on the approaching merge region. The method involves updating the navigation plan based on the respective avoidance scores. The method also involves controlling the truck to execute a driving strategy based on the updated navigation plan.

Abstract: Systems and methods for calculating mobility metrics associated to a plurality of wearable sensors in various arrangements comprising a plurality of communicatively-connected sensors comprising inertial measurement units (IMU) attached to connected bodies of a hinge or ball joint in communication with a computing device. Systems and methods for quaternion calculations comprising a first sensor's quaternion output as estimate into another sensor's quaternion calculation to improve the other sensor's quaternion estimate and vice versa. Systems and methods for data synchronization of a plurality of sensors involving building an external reference time vector and interpolating the sensor's data based on the reference time vector. Systems and methods for calculating a sensor's orientation and position based on the inertial measurements captured by the wearable sensors during hinge or ball joint movements to, at least, calculate a joint angle.

Abstract: A method, system and computer program product for detecting an object within a frame, the method comprising: receiving calibration parameters of a camera; obtaining four or more salient points of an object model, wherein a plane containing the salient points is at an arbitrary position relatively to a frame view of the camera; determining a projection of each of the at least four salient feature points onto the frame view of the camera, thus determining a quadrilateral in frame coordinates; determining a transformation for transforming the quadrilateral into a rectangle having edges parallel to edges of frames captured by the camera; receiving at least a part of the frame captured by the camera; applying the transformation to the at least part of the frame to obtain a rectangular search area having edges parallel to edges of the frame; and detecting an object within the rectangular search area.

Abstract: Apparatus and method for extracting a background model from a video stream of frames. Each frame is divided into a rectangular array of blocks, and a block descriptor of each block is compared with the previous frame's corresponding block descriptor. When a block descriptor is substantially the same as the corresponding block descriptor of the preceding frame for at least a predetermined number of frames, then the background model is updated according to the block descriptor.

Abstract: The invention provides methods and systems for reliably detecting objects in a received video stream from a camera. Objects are selected and a bound around selected objects is calculated and displayed. Bounded objects can be tracked. Bounding is performed by using Histogram of Oriented Gradients and linear Support Vector Machine classifiers.

Abstract: A robotic two-wheeled vehicle comprising a connection body interposed between the two wheels are described. A drum can be coaxially located in a central region of the connection body and can support a hollow arm projecting radially from the drum. A tether can be inserted in the arm and connected to a second drum. Instruments and sensors can be accommodated in a case housed inside each wheel.

Abstract: A robotic two-wheeled vehicle comprising a connection body interposed between the two wheels are described. A drum can be coaxially located in a central region of the connection body and can support a hollow arm projecting radially from the drum. A tether can be inserted in the arm and connected to a second drum. Instruments and sensors can be accommodated in a case housed inside each wheel.

Abstract: A robotic two-wheeled vehicle comprising a connection body interposed between the two wheels are described. A drum can be coaxially located in a central region of the connection body and can support a hollow arm projecting radially from the drum. A tether can be inserted in the arm and connected to a second drum. Instruments and sensors can be accommodated in a case housed inside each wheel.

Abstract: A robotic two-wheeled vehicle comprising a connection body interposed between the two wheels are described. A drum can be coaxially located in a central region of the connection body and can support a hollow arm projecting radially from the drum. A tether can be inserted in the arm and connected to a second drum. Instruments and sensors can be accommodated in a case housed inside each wheel.