Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.

Abstract: Surgical systems and methods involve manipulation of a bone. A robotic manipulator supports and moves a surgical tool that has a cutting bur rotatable about a cutting axis. Controller(s) control the manipulator to align the cutting axis to a target axis associated with the bone and advance the cutting bur along the target axis towards a cortical region of the bone. The controller(s) control the surgical tool to rotate the cutting bur about the cutting axis and contact the cortical region. The controller(s) detect, from sensor(s), forces applied to the cutting bur by the cortical region and compare the sensed forces to a threshold indicative of skiving of the cutting bur relative the cortical region. In response to the sensed forces exceeding the threshold, the controller(s) adjust control of the manipulator and/or surgical tool to reduce forces applied to the cutting bur by the cortical region.

Abstract: Surgical systems and methods for utilizing virtual boundaries having different constraint parameters. A robotic manipulator supports and moves a surgical tool for treating a bone structure. A navigation system tracks the surgical tool and the bone structure. Controller(s) obtain a virtual model of the bone structure and define first and second virtual boundaries relative to the virtual model. The first virtual boundary has a first constraint parameter and the second virtual boundary has a second constraint parameter that is different than the first constraint parameter. The virtual model and virtual boundaries are registered to the bone structure. The manipulator moves the surgical tool relative to the bone structure and the first and second virtual boundaries. The surgical tool is constrained relative to the first virtual boundary in accordance with the first constraint parameter and constrained relative to the second virtual boundary in accordance with the second constraint parameter.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.

Abstract: A load balancing method is disclosed, the method includes establishing a processing network including a plurality of task-processing processors interconnected therewith, each processor of the plurality having a queue of tasks to be processed, establishing a k-regular graph including nodes and branches connecting the nodes, where k is the degree of the graph, assigning d walkers to the k-regular graph, where each walker is randomly assigned to a node, receiving a new task to be processed, walking from the assigned nodes to new nodes by randomly choosing a new node from one or more available nodes, without backtracking from each of the assigned nodes to a node from which each of the d walkers immediately walked, comparing the queues of the new nodes, determining which queue of the new nodes has the least number of tasks; and assigning the new task to the node with the least number of tasks.

Abstract: Systems and methods for autonomous vehicle motion planning are provided. Sensor data describing an environment of an autonomous vehicle and an initial travel path for the autonomous vehicle through the environment can be obtained. A number of trajectories for the autonomous vehicle are generated based on the sensor data and the initial travel path. The trajectories can be evaluated by generating a number of costs for each trajectory. The costs can include a safety cost and a total cost. Each cost is generated by a cost function created in accordance with a number of relational propositions defining desired relationships between the number of costs. A subset of trajectories can be determined from the trajectories based on the safety cost and an optimal trajectory can be determined from the subset of trajectories based on the total cost. The autonomous vehicle can control its motion in accordance with the optimal trajectory.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.

Abstract: Strengthened glass-based substrates having a first outer region compressive stress and a first side having first coating thereon are disclosed. The first coating comprising a material selected to have a first coating Young's modulus value, a first coating thickness, and a first coating stress that is either neutral or compressive, such that the absolute value of first outer region compressive stress is greater than the absolute value of the first coating stress. Methods of making glass-based articles are provided, and glass-based articles having coatings that provide different strength values and/or reliability on different sides of the glass-based articles are also disclosed.

Abstract: Laminated glass-based articles and methods of manufacture are disclosed. A glass-based article includes a glass-based substrate having a first surface and a second surface opposing the first surface defining a substrate thickness (t) in a range of about 0.1 millimeters to 3 millimeters, the glass-based substrate having a compressive region having a first compressive stress CS maximum at the first surface of the glass-based article extending to a depth of compression (DOC) and second local CS maximum at a depth of at least 25 ?m from the first surface, wherein the glass-based substrate comprises a glass-based core substrate having a first side and a second side, the glass-based core substrate sandwiched between a glass-based first cladding substrate and a glass-based second cladding substrate, the first cladding substrate and second cladding substrate directly bonded to the first side and the second cladding substrate directly bonded to the second side.

Abstract: Surgical systems and methods for utilizing virtual boundaries having different constraint parameters. A robotic manipulator supports and moves a surgical tool for treating a bone structure. A navigation system tracks the surgical tool and the bone structure. Controller(s) obtain a virtual model of the bone structure and define first and second virtual boundaries relative to the virtual model. The first virtual boundary has a first constraint parameter and the second virtual boundary has a second constraint parameter that is different than the first constraint parameter. The virtual model and virtual boundaries are registered to the bone structure. The manipulator moves the surgical tool relative to the bone structure and the first and second virtual boundaries. The surgical tool is constrained relative to the first virtual boundary in accordance with the first constraint parameter and constrained relative to the second virtual boundary in accordance with the second constraint parameter.

Abstract: Systems and methods for autonomous vehicle motion planning are provided. Sensor data describing an environment of an autonomous vehicle and an initial travel path for the autonomous vehicle through the environment can be obtained. A number of trajectories for the autonomous vehicle are generated based on the sensor data and the initial travel path. The trajectories can be evaluated by generating a number of costs for each trajectory. The costs can include a safety cost and a total cost. Each cost is generated by a cost function created in accordance with a number of relational propositions defining desired relationships between the number of costs. A subset of trajectories can be determined from the trajectories based on the safety cost and an optimal trajectory can be determined from the subset of trajectories based on the total cost. The autonomous vehicle can control its motion in accordance with the optimal trajectory.

Abstract: Disclosed herein are techniques for preparation of a bone structure wherein a robotically controlled cutting bur is utilized for both milling the entry point at the outer cortical region and cannulation of the cancellous bone region for receipt of an implant. A robotic manipulator supports and moves the cutting bur and one or more controllers analyze measurements from sensors and, in response, control the robotic manipulator and/or the cutting bur for purposes such as landmark detection to determine entry point, avoiding tool skiving at entry point, and avoidance of cortical wall breach during cannulation. Also described are techniques for managing feed rate, rotational cutting speed, or mode of operation depending on operational conditions surrounding various stages of cannulation. A control interface is also provided to enable the user to manage or adjust cutting bur operation and feed rate.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.

Abstract: Coated glass-based articles and methods of manufacture disclosed. An article comprises a chemically strengthened glass-based core substrate having a first surface and a second surface, a chemically strengthened glass-based first cladding substrate having a third surface directly bonded to the first surface to provide a first core-cladding interface and a chemically strengthened glass-based second cladding substrate having a fourth surface directly bonded to the second surface to provide a second core-cladding interface, wherein the core substrate is bonded to the first cladding substrate and the second cladding substrate, and there is a coating on the first cladding substrate.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.

Abstract: A glass article (100) includes a core layer (102) formed from a core glass composition with a core coefficient of thermal expansion (CTE) and first (104) and second (106) cladding layers fused to first and second major surfaces of the core layer (102) and formed from a clad glass composition comprising a clad CTE. An aperture (120) extends through each of the core layer (102), the first cladding layer (104), and the second cladding layer (106). The clad CTE is less than the core CTE such that each of the first (104) and second (106) cladding layers is under a compressive stress and the core layer (102) is under a tensile stress. A flexural strength of the glass article (100) can be at least about 75 MPa. A peak load sustainable by the glass article (100) in a modified ring-on-ring test can be at most 96.5% less than a peak load sustainable by a reference glass article in the modified ring-on-ring test.

Abstract: A load balancing method is disclosed, the method includes establishing a processing network including a plurality of task-processing processors interconnected therewith, each processor of the plurality having a queue of tasks to be processed, establishing a k-regular graph including nodes and branches connecting the nodes, where k is the degree of the graph, assigning d walkers to the k-regular graph, where each walker is randomly assigned to a node, receiving a new task to be processed, walking from the assigned nodes to new nodes by randomly choosing a new node from one or more available nodes, without backtracking from each of the assigned nodes to a node from which each of the d walkers immediately walked, comparing the queues of the new nodes, determining which queue of the new nodes has the least number of tasks; and assigning the new task to the node with the least number of tasks.

Abstract: Methods and systems are provided for automatically adjusting a position of a table configured to be positioned in a bore of a medical imaging device. The table may be adjusted according to one or more of a table elevation, an anatomical reference, and a start scan location. The table elevation, anatomical reference, and start scan location may be obtained from a selected imaging protocol.

Abstract: A strengthened article (and methods for making it) is provided that includes a glass, glass-ceramic or ceramic, having a plurality of primary surfaces, side edges, and a thickness. The article also includes a compressive stress region extending from one of the primary surfaces to a first selected depth in the article; a central region extending from a boundary located at a depth of 200 ?m from the primary surfaces and the edges to the centroid of the article; and an outer region extending between the primary surfaces and edges to the boundary. Further, the maximum principal stress within the outer region is no more than two times the maximum principal stress within the central region. The primary surfaces and side edges may define a plurality of corners, and the corners may be defined by a chamfer, a fillet, or a curved shape.

Abstract: A load balancing method is disclosed, the method includes establishing a processing network including a plurality of task-processing processors interconnected therewith, each processor of the plurality having a queue of tasks to be processed, establishing a k-regular graph including nodes and branches connecting the nodes, where k is the degree of the graph, assigning d walkers to the k-regular graph, where each walker is randomly assigned to a node, receiving a new task to be processed, walking from the assigned nodes to new nodes by randomly choosing a new node from one or more available nodes, without backtracking from each of the assigned nodes to a node from which each of the d walkers immediately walked, comparing the queues of the new nodes, determining which queue of the new nodes has the least number of tasks; and assigning the new task to the node with the least number of tasks.