Abstract: A track chain member includes a shoe member, and a first rail member extending from the shoe member. The first rail member includes a first lug defining a first bore defining a first longitudinal axis and including a first bushing retention shelf disposed in the first bore, as well as a second lug including a second bushing retention shelf disposed in the second bore. A third lug extends in a direction opposite that of the first lug and second lug and is disposed axially between the first lug and the second lug.

Abstract: Swimming pool or spa gas heaters, cabinets, water header manifolds, and heat exchangers include: gas heaters having an air gap between a cabinet and combustion chamber to reduce heat transfer to sides of the cabinet; gas heaters having a user interface that is repositionable on a top panel; gas heater cabinets including a removable top panel that can be hung on a side panel; gas heaters having a built-in dual junction box; gas heaters having a top-accessible igniter and burner that are interlocked to maintain positioning thereof; adaptable water manifolds including connectable inlet and outlet fittings that adjust effective inlet and outlet positions; heat exchangers having a plurality of tube-and-fin subassemblies arranged in a semi-circular configuration; and water manifolds including internal cartridges that divide the water manifold into a plurality of chambers for improved circulation through a heat exchanger.

Abstract: Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

Abstract: Techniques to predict object behavior in an environment are discussed herein. For example, such techniques may include determining a trajectory of the object, determining an intent of the trajectory, and sending the trajectory and the intent to a vehicle computing system to control an autonomous vehicle. The vehicle computing system may implement a machine learned model to process data such as sensor data and map data. The machine learned model can associate different intentions of an object in an environment with different trajectories. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on object's intentions and trajectories.

Abstract: A track chain assembly comprises a plurality of interlocking track chain members wherein each track chain member defines a track chain traveling direction, a lateral direction perpendicular to the track chain traveling direction, and includes a shoe member defining a shoe width along the lateral direction; and a first track pad member defining a first track pad maximum width along the lateral direction, and a second track pad member defining a second maximum track pad width along the lateral direction, wherein a ratio of either track pad maximum widths to the shoe member width ranges from 1:4 to 3:4. The first and the second track pad members each include a first projection disposed at one lateral extremity of the first track pad member and a second projection disposed at another lateral extremity of the second track pad member.

Abstract: Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

Abstract: Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

Abstract: Techniques for detecting and tracking objects in an environment are discussed herein. For example, techniques can include detecting a center point of a block of pixels associated with an object. Unimodal (e.g., Gaussian) confidence values may be determined for a group of pixels associated with an object. Proposed detection box center points may be determined based on the Gaussian confidence values of the pixels and an output detection box may be determined using filtering and/or suppression techniques. Further, a machine-learned model can be trained by determining parameters of a center pixel of the detection box and a focal loss based on the unimodal confidence value which can then be backpropagated to the other pixels of the detection.

Abstract: Tracking a current and/or previous position, velocity, acceleration, and/or heading of an object using sensor data may comprise determining whether to associate a current object detection generated from recently received (e.g., current) sensor data with a previous object detection generated from formerly received sensor data. In other words, a track may identify that an object detected in former sensor data is the same object detected in current sensor data. However, multiple types of sensor data may be used to detect objects and some objects may not be detected by different sensor types or may be detected differently, which may confound attempts to track an object. An ML model may be trained to receive outputs associated with different sensor types and/or a track associated with an object, and determine a data structure comprising a region of interest, object classification, and/or a pose associated with the object.

Abstract: A gas heater for a swimming pool or spa includes a cabinet defining an interior, a combustion chamber enclosure, a heat exchanger positioned within the combustion chamber enclosure, a burner, a combustion blower configured to provide combustible gas to the burner, and electrical components positioned within the cabinet. The cabinet has a plurality of side panels and a top panel covering a top opening to the interior of the cabinet. The combustion chamber enclosure defines a combustion chamber, and is positioned within the interior of the cabinet. The combustion chamber enclosure also includes a burner opening in which the burner is positioned such that the burner is configured to dissipate combustible gas into the combustion chamber. At least one of the electrical components is configured to control the gas heater. The electrical components are accessible through the top opening when the top panel is removed.

Abstract: Techniques are disclosed for a combined machine learned (ML) model that may generate a track confidence metric associated with a track and/or a classification of an object. Techniques may include obtaining a track. The track, which may include object detections from one or more sensor data types and/or pipelines, may be input into a machine-learning (ML) model. The model may output a track confidence metric and a classification. In some examples, if the track confidence metric does not satisfy a threshold, the ML model may cause the suppression of the output of the track to a planning component of an autonomous vehicle.

Abstract: A modulating heater system for a pool or spa includes a pool/spa heater capable of variably modulating energy output thereof and a controller communicatively coupled to the heater. The controller determines a current mode of operation for the heater, and establishes temperature overshoot and target temperature setpoints for pool/spa water for the current mode of operation. The controller determines a current temperature of the water, an optimized modulation rate for the heater for the current mode of operation, and a maximum modulation rate for the heater for the current mode of operation. The controller controls the heater to operate at one of the optimized and maximum modulation rates based on the temperature overshoot setpoint for the current mode of operation, the target water temperature setpoint for the current mode of operation, and the current water temperature. A corresponding method for controlling a pool/spa modulating heater is also provided.

Abstract: Techniques relating to training a model for detecting that a vehicle is likely to perform a cut-in maneuver are described. Computing device(s) can receive log data associated with vehicles in an environment and can detect an event in the log data, wherein an event corresponds to a cut-in maneuver performed by a vehicle. In an example, the computing device(s) can generate training data based at least in part on converting a portion of the log data that corresponds to the event into a top-down representation of the environment and inputting the training data into a model, wherein the model is trained to output an indication of whether another vehicle is likely to perform another cut-in maneuver.

Abstract: Systems and methods for high-bandwidth, minimally invasive brain-computer interfaces (BCIs) are disclosed. The BCIs are configured for deployment and operation in conjunction with a comprehensive interventional electrophysiology procedural suite. Three primary methods of minimally invasive electrode array delivery are disclosed: (1) cortical surface delivery, (2) ventricular delivery, and (3) endovascular delivery. Additionally, systems and methods for interacting with such high-bandwidth electrode arrays are discussed, including real-time imaging, signal processing, and neural decoding. Systems and methods for architectures for accelerating the underlying computational processes (such as graphics processing units or tensor processing units) are also discussed. Multiple applications of BCIs are discussed, with emphasis on restoration, rehabilitation, and augmentation of neurologic function.

Abstract: Embodiments of the disclosure are drawn to implantable stimulator with machine learning based classifier. An implantable system includes sensors which provide sensor information to an implantable unit. The implantable unit uses a classifier on the sensor information to select a stimulation procedure which is applied via a stimulation electrode. The classifier may be generated by a trained machine learning model. The classifier may be trained on an external unit which is not implanted in the subject. The classifier may be trained based on sensor information from the implanted sensors as well as symptom information.

Abstract: Techniques are discussed for controlling a vehicle, such as an autonomous vehicle, based on occluded areas in an environment. An occluded area can represent areas where sensors of the vehicle are unable to sense portions of the environment due to obstruction by another object. An occlusion grid representing the occluded area can be stored as map data or can be dynamically generated. An occlusion grid can include occlusion fields, which represent discrete two- or three-dimensional areas of driveable environment. An occlusion field can indicate an occlusion state and an occupancy state, determined using LIDAR data and/or image data captured by the vehicle. An occupancy state of an occlusion field can be determined by ray casting LIDAR data or by projecting an occlusion field into segmented image data. The vehicle can be controlled to traverse the environment when a sufficient portion of the occlusion grid is visible and unoccupied.

Abstract: A track pad includes a shoe member that has two bottom voids extending upwardly from the ground engaging surface of the shoe member, and which form a central support pillar having a serpentine surface laterally on side of the central support pillar, and another serpentine surface laterally on the other side of the central support pillar. The two bottom voids form oval perimeters at the ground engaging surface.

Abstract: An onboard track machine wear measurement system has an ultra-sonic probe that is attached to an undercarriage of the machine that is disposed adjacent a track chain assembly, and a controller that is in communication with the ultra-sonic probe. The controller is configured to determine the thickness of a load bearing wall of a track component of the track chain assembly.

Abstract: A machine track includes a track shoe having a first outboard edge and a second outboard edge, and a first set of pin lugs and a second set of pin lugs. A roller pad is positioned between the sets of pin lugs and includes a roller contact surface extending between a first roller pad end and a second roller pad end. The first roller pad end includes a relatively softer material, and the second roller pad end includes a relatively harder material that forms a trimming edge for trimming off interfering material of an adjacent track shoe in a machine track that is plastically deformed by way of roller contact with the adjacent track shoe during service.

Abstract: A track chain assembly includes a first track pad including a first pair of lugs defining a gap therebetween, and a second track pad including an intermediate lug disposed in the gap. The first pair of lugs and the intermediate lug each define a concentric bore, defining an axis of rotation for a pinned joint of the track chain assembly, and the concentric bore of one of the first pair of lugs is in communication with the gap with a first blend disposed axially between the gap and the concentric bore.