Abstract: Systems and methods for training and executing machine learning models to generate lane index values are disclosed. A method includes identifying a set of image data captured by at least one autonomous vehicle when the at least autonomous vehicle is positioned in a lane of a roadway and respective ground truth localization data; determining a plurality of lane index values for the set of image data based on the ground truth localization data; labeling the set of image data with the plurality of lane index values, the lane index values representing a number of lanes from a leftmost or rightmost lane to the lane in which the at least one autonomous vehicle was positioned; and training, using the labeled set of image data, a plurality of machine learning models that generate a left lane index value and a right lane index value as output.

Abstract: Systems and methods for training and executing machine learning models to generate lane index values are disclosed. A method includes identifying a set of image data captured by at least one autonomous vehicle when the at least autonomous vehicle is positioned in a lane of a roadway and respective ground truth localization data; determining a plurality of lane index values for the set of image data based on the ground truth localization data; labeling the set of image data with the plurality of lane index values, the lane index values representing a number of lanes from a leftmost or rightmost lane to the lane in which the at least one autonomous vehicle was positioned; and training, using the labeled set of image data, a plurality of machine learning models that generate a left lane index value and a right lane index value as output.

Abstract: Systems and methods for training and executing machine learning models to generate lane index values are disclosed. A method includes identifying a set of image data captured by at least one autonomous vehicle when the at least autonomous vehicle is positioned in a lane of a roadway and respective ground truth localization data; determining a plurality of lane index values for the set of image data based on the ground truth localization data; labeling the set of image data with the plurality of lane index values, the lane index values representing a number of lanes from a leftmost or rightmost lane to the lane in which the at least one autonomous vehicle was positioned; and training, using the labeled set of image data, a plurality of machine learning models that generate a left lane index value and a right lane index value as output.

Abstract: A safety module having a plurality of microcontrollers receives an analog input and determines a value of the analog input. The microcontrollers each determine a respective ternary state of the device by identifying, from three candidate ranges of values, a range of values in which the value falls, wherein at least two of the plurality of microcontrollers uses different candidate ranges of values, determining, based on the identified range, a ternary state corresponding to the range, and assigning the determined ternary state as the respective ternary state. The safety module determines whether the ternary states from the two microcontrollers map to a fault state, and, where they do, cause a command a command to be output to the device to enter a safe state.

Abstract: A method includes obtaining, by the treatment system configured to implement a machine learning (ML) algorithm, one or more images of a region of an agricultural environment near the treatment system, wherein the one or more images are captured from the region of a real-world where agricultural target objects are expected to be present, determining one or more parameters for use with the ML algorithm, wherein at least one of the one or more parameters is based on one or more ML models related to identification of an agricultural object, determining a real-world target in the one or more images using the ML algorithm, wherein the ML algorithm is at least partly implemented using the one or more processors of the treatment system, and applying a treatment to the target by selectively activating the treatment mechanism based on a result of the determining the target.

Abstract: Data is received that includes a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system. Within each image, it is detected whether an object is present within the image. Instance identifiers are assigned to each object. A single image is identified in which the object is optimally represented for each object using the corresponding instance identifier. These identified images are provided to a consuming application or process for quality assurance analysis.

Abstract: A method includes: compiling lower-resolution images, captured during a global scan cycle executed over a workpiece, into a virtual model; defining a nominal toolpath and a nominal target force for the workpiece based on a the virtual model; detecting a defect indicator on the workpiece based on the lower-resolution images; accessing a higher-resolution image captured during a local scan cycle over the defect indicator; characterizing the defect indicator as a defect reparable via material removal based on the higher-resolution image; defining a repair toolpath for the defect based on the virtual model; navigating a sanding head over the workpiece according to the repair toolpath to repair the defect; and, during a processing cycle: navigating the sanding head across the workpiece according to the nominal toolpath and deviating the sanding head from the nominal toolpath to maintain forces of the sanding head on the workpiece proximal the nominal target force.

Abstract: Disclosed is an adjustment mechanism for an electric power-driven shoe, the mechanism comprising a shoe sole (1), wherein a plurality of rolling wheels (2) are arranged below the shoe sole (1); a foot-positioning mechanism is arranged above the shoe sole (1) and is provided with an angle-adjusting mechanism for adjusting an angle between the foot-positioning mechanism and a lengthwise direction of the shoe sole (1).

Abstract: A robotic order fulfilment system for picking inventory. The system includes a piece picking robot configured to pick inventory from a plurality of containers arranged on shelving. The robot includes a base moveable relative to the shelving in a horizontal direction, a vertical post extending from the base, a platform linearly moveable along the vertical post, a suction system arranged to secure and move a select one of the containers from the shelving to expose an open top of the select one of the containers, and a picking arm configured to pick an item from the select one of the containers after the open top has been exposed. An order fulfilment method using the piece picking robot is also provided.

Abstract: Systems and methods for safety-enabled control by: establishing a wireless communication channel with a plurality of remote control units via the wireless interface device; in response to establishing the wireless communication channels, operating a system-under-control in a supervised mode based on input received from at least one of the plurality of remote control units; in response to a mode switch command received from a first remote control unit of the plurality of remote control units, providing the other remote control units with a request for a mode switch confirmation; and, in response to confirming receipt of a safety-rated input from an autonomous control system and receipt of a mode switch confirmation from each of the other remote control units, operating the system-under-control in an autonomous mode based on input received from the autonomous control system.

Abstract: A waste collection bag may be used by an autonomous cleaning robot (e.g., an autonomous vacuum) to store waste during a plurality of cleaning processes. The waste bag comprises a waste bag, a waste collection sachet, and an absorbent. The waste bag has a first side and a second side, where the first side has an opening for waste to enter, and is composed of filtering material. The waste collection enclosed sachet has a first side and a second side that connect to form a cavity. The waste collection enclosed sachet is tethered to the second side of the waste bag and is composed of dissolvable paper. The absorbent may absorb liquid waste and is located inside the cavity of the waste collection enclosed sachet.

Abstract: A mobile manipulator robot having a pneumatic charging system. The mobile robot includes an energy source and a charging system to charge the energy source. The charging system includes a coupler having a mating end configured to mate with an external pneumatic supply system to access a pneumatic supply and a pneumatic actuator disposed downstream of the coupler. The pneumatic actuator is configured to convert energy from the pneumatic supply to charge the energy source. The pneumatic actuator may be an air motor or a piezo.

Abstract: Each of a plurality of co-located inspection camera modules captures raw images of objects passing in front of the co-located inspection camera modules which form part of a quality assurance inspection system. The inspection camera modules have either a different image sensor or lens focal properties and generate different feeds of raw images. The co-located inspection camera modules can be selectively switched amongst to activate the corresponding feed of raw images. The activated feed of raw images is provided to a consuming application or process for quality assurance analysis.

Abstract: Systems, methods and apparatuses for inspecting a tank containing a flammable fluid are provided. The system includes a vehicle having a propeller, a latch mechanism, a pressure switch, and an inspection device. The system includes a control unit in communication with the propeller, the latch mechanism, and the inspection device, and electrically connected to the pressure switch. The control unit powers on responsive to the pressure switch detecting an ambient pressure greater than a minimum threshold. The control unit receives, from the latch mechanism, an indication of a state of the latch mechanism. The control unit determines that the cable used to lower the vehicle into the tank containing the flammable fluid is detached from the vehicle. The control unit commands the propeller to move the vehicle through the flammable fluid. The control unit determines a quality metric of a portion of the tank.

Abstract: A method of operating an exoskeleton system that includes obtaining a first set of sensor data from one or more sensors associated with one or more leg actuator units of an exoskeleton system during a user activity, the first set of sensor data indicating a first configuration state of the one or more actuator units; determining, based at least in part on the first set of obtained sensor data, to change configuration of the one or more leg actuator units to a second configuration state to support a user during the user activity; and introducing fluid to one or more fluidic actuators of the one or more leg actuator units to generate the second configuration state by causing the one or more fluidic actuators to apply force at the one or more actuator units.

Abstract: A mobile inventory transportation unit (MITU) in a communication network is disclosed. The communication network may comprise the MITU, a transportation system, a first and a second central system, in communication with each other, the MITU comprising a housing, an inventory storage device, a power device, a drive device, a navigation device, a sensing device, and a control device. The MITU may be configured to receive inventory demands and handle them based on analyzing its own inventory, the transportation system may be configured to physically receive and transport the MITU, the second central system may be configured to determine an inventory demand at a second or more location and transmit the same to the first central system or the MITU, and the first central system or the MITU may be configured to schedule the movement of the MITU and control the delivery of the MITU to a final destination.

Abstract: A method for controlling a robot is provided. The method includes the steps of: acquiring information on a sound associated with a robot call in a serving place; determining a call target robot associated with the sound, among a plurality of robots in the serving place, on the basis of the acquired information; and providing feedback associated with the sound by the call target robot.

Abstract: Systems and methods are provided for providing redundant pulse-width modulation (PWM) throttle control. The system includes a manual throttle controller configured to generate a manual PWM throttle control signal, and an automated throttle control system. The automated throttle control system includes a plurality of automated throttle controllers, each of which being configured to independently control a throttle of a vehicle, and each including a processor configured to generate and output an automated PWM throttle control signal, a first double pole double throw (DPDT) relay that, when engaged, is configured to receive and output the manual PWM throttle control signal, and a second DPDT relay, configured to receive and output the automated PWM throttle control signal to an engine, when the second DPDT relay is engaged; and receive and output the manual PWM throttle control signal to the engine, when the DPDT relay is disengaged.

Abstract: Provided is a robotic retrieval system that adapts robot operations to different densities with which containers are stored. The system determines a position of a particular container in a slot. The system selects a first side of the slot from which to gain access to the particular container based on the particular container being blocked from the first side by a first number of containers and from an opposite second side by a larger second number of containers. The system uses robots to advance the particular container to the frontmost position at the first side of the particular slot by removing the first number of containers from the first side, and by inserting the first number of containers into the second side, and to transfer the particular container to a target destination after advancing the particular container to the frontmost position at the first side.

Abstract: Systems for reprogrammable inspection robots are described. An example system may include an inspection robot having a housing, a payload interface, a drive module interface, and a tether interface. The system may further include a first electronic board having a primary functionality circuit communicatively coupled to a base station and a second electronic board operationally coupled to the payload interface, the second electronic board having a payload functionality circuit coupled to a selected payload through the payload interface. The example system may further include a third electronic board operationally coupled to the drive module interface, the third electronic board having a drive module functionality circuit communicatively coupled to a selected drive module through the drive module interface.