Abstract: A force transmission system for a robotically controlled medical device can include a pushing actuator configured to be pushed by a robotic instrument controller and a wire. The wire can include a first end attached to an end of the pushing actuator to be pushed distally by the pushing actuator, and a second end attached to a distal location of the medical device. The system can include a reverse motion device that can be interfaced with the wire between the first end and the second end. The reverse motion device can be configured to cause a proximal pulling action on the second end in response to pushing of the first end distally by the pushing actuator or other actuation by the pushing actuator. The reverse motion device can be configured to maintain a point of contact with the wire in the same spatial location to prevent wire motion due to actuation.

Abstract: Exemplary embodiments provide enhancements for soft robotic actuators. In some embodiments, angular adjustment systems are provided for varying an angle between an actuator and the hub, or between two actuators. The angular adjustment system may also be used to vary a relative distance or spacing between actuators. According to further embodiments, rigidizing layers are provided for reinforcing one or more portions of an actuator at one or more locations of relatively high strain. According to further embodiments, force amplification structures are provided for increasing an amount of force applied by an actuator to a target. The force amplification structures may serve to shorten the length of the actuator that is subject to bending upon inflation. According to still further embodiments, gripping pads are provided for customizing an actuator's gripping profile to better conform to the surfaces of items to be gripped.

Abstract: Methods and systems are described herein for hosting and arbitrating algorithms for the generation of structured frames of data from one or more sources of unstructured input frames. A plurality of frames may be received from a recording device and a plurality of object types to be recognized in the plurality of frames may be determined. A determination may be made of multiple machine learning models for recognizing the object types. The frames may be sequentially input into the machine learning models to obtain a plurality of sets of objects from the plurality of machine learning models and object indicators may be received from those machine learning models. A set of composite frames with the plurality of indicators corresponding to the plurality of objects may be generated, and an output stream may be generated including the set of composite frames to be played back in chronological order.

Abstract: A patient cart for a robot surgical system can include a mobile base having a frame adapted and configured to support a medical robot, one or more motive devices operatively connected to the frame, and one or more motors connected to the motive devices to drive the motive devices to move the frame. The patient cart can include a drive control interface connected to the frame and configured to sense a user input and to operate the one or more motors to move the one or more motive devices as a function of the user input.

Abstract: A vehicle comprises a sensor configured to capture images and one or more processors. The one or more processors can be configured to receive a single image from the sensor, the single image captured by the sensor as the autonomous vehicle was moving; execute a machine learning model using the single image as input to generate a change in pose of the autonomous vehicle, the machine learning model trained to output changes in pose of autonomous vehicles based on blurring in individual images; determine a global position of the autonomous vehicle based on the generated change in pose of the autonomous vehicle; and transmit the global position to an autonomous vehicle controller configured to control the autonomous vehicle.

Abstract: A patient console for a robotic surgical system can include a base, a vertical lift attached to a top of the base and configured to provide up and down motion in a vertical axis, a yaw rotation device attached to the top of the vertical lift and configured to provide a yaw rotation about the vertical axis, a pitch rotation device attached to the top of the yaw rotation device and configured to provide a pitch rotation about a pitch axis orthogonal to the vertical axis, a translation device attached to the top of the pitch rotation device and configured to provide sliding translation along a translation axis, and a roll rotation device attached to the translation device to roll relative to the translation device about a roll axis to provide a roll to an instrument controller assembly. An angle of the translation axis and the roll axis relative to horizontal can be a function of the pitch rotation provided by the pitch rotation device.

Abstract: A method performed by a treatment system disposed on a moving platform, the treatment system having one or more processors, a storage and a treatment mechanism, comprising: receiving one or more images of an environment in which the moving platform is operating; identifying, in real-time, a pose of the moving platform using sensor inputs; identifying one or more target objects by processing the one or more images using a machine learning (ML) algorithm; and controlling the treatment mechanism to treat the one or more target objects by orienting the treatment mechanism towards the one or more target objects at least partially based on the pose.

Abstract: The present invention relates to an image processing system for a catheter operation. One embodiment comprises: a storage unit for at least temporarily storing a plurality of candidate routes on which a guide wire can proceed on a changing route caused by vascular bifurcations while proceeding from a first point by using a blood vessel image; and a processor for selecting, from an image inputted while an operation proceeds, at least one route corresponding to the current shape of the guide wire on the basis of a similarity comparison between the current shape of the guide wire and each of the plurality of candidate routes.

Abstract: Systems and methods of determining distance bounds for adaptive cruise control. An autonomous vehicle system can identify a second vehicle on the roadway that is traveling in front of the autonomous vehicle; determine a speed of the second vehicle while the second vehicle travels along the roadway; generate a distance bound between the autonomous vehicle and the second vehicle based on the speed of the second vehicle and a speed of the autonomous vehicle; and control the speed of the autonomous vehicle to implement adaptive cruise control according to the distance bound.

Abstract: A method comprises periodically monitoring, by a processor, lateral position and velocity of vehicle within a predetermined distance from an autonomous vehicle, the vehicle moving in a direction having at least one common attribute with the autonomous vehicle; executing, by the processor, a computer model using the monitored lateral position and velocity of the vehicle, to predict whether a trajectory for the vehicle; and when a current trajectory of the autonomous has a likelihood of collision with the predicted trajectory of the vehicle that satisfies a threshold, determining, by the processor, an alternative trajectory for the autonomous vehicle.

Abstract: A gripping system for grabbing and releasing an object using a robotic arm includes a gripper body for operably engaging the robotic arm. The gripper body includes a vacuum pathway, a vacuum source connector operably coupled to the vacuum pathway, and a compressed air source connector. A plurality of compensators are configured to extend and retract relative to the gripper body. Each one of the compensators is configured for being placed in communication with the vacuum pathway when the compensator is in the extended position and for being isolated from the vacuum pathway when the compensator is in the retracted position.

Abstract: Embodiments include systems and methods for determining states of traffic lights and managing behavior of an automated vehicle approaching an intersection. An autonomy system applies an object recognition engine trained to recognize a traffic light, and identify and confirm the state of the traffic light. A first neural network trained for object detection recognizes a traffic light and defines a bounding box around the recognized traffic light. A second neural network receives the region of the image bounded by the box as constituting the traffic light and “reads” the light. The automated vehicle uses other information, such as states of pedestrian traffic lights, detection of objects in and near the intersection, and glare on one or more cameras, to supplement its determination of the right of way through the intersection. The autonomy system generates a driving instruction based on the traffic light combined.

Abstract: A vehicle comprises one or more sensors, and a processor coupled with the one or more sensors and stored inside a housing of the vehicle. The processor can be configured to collect data regarding the environment surrounding the vehicle from the one or more sensors; detect a second vehicle and an observed trajectory of the second vehicle from the collected data, the observed trajectory indicating a position or speed of the second vehicle over a time period; compare the observed trajectory with one or more expected trajectories of the second vehicle; responsive to determining a deviation between the observed trajectory and at least one of the one or more expected trajectories satisfies a condition, generate a record indicating the deviation and including a video of the second vehicle that corresponds to the observed trajectory; and transmit the record to a remote processor.

Abstract: The present disclosure is for a system and a method for computer vision based object detection. The invention uses images of objects from multiple perspectives and for each image identifies planes belonging to different objects. The planes are then analyzed to determine planes belonging to the same physical object. This is accomplished by comparing characteristics of the identified planes with each other and/or expected criteria. Planes identified as belonging to the same object can be grouped and used to provide pick instructions to a robot.

Abstract: An earth moving vehicle (EMV) autonomously performs an earth moving operation within a dig site. If the EMV determines that a state of the EMV or the dig site triggers a triggering condition associated with a pause in the autonomous behavior of the EMV, the EMV determines a risk associated with the state or triggering condition. If the risk is greater than a first threshold, the EMV continues the autonomous performance and notifies a remote operator that the triggering condition was triggered. If the risk is greater than the first threshold risk but less than a second threshold risk, the EMV is configured to operate in a default state before continuing and notifying the remote operator. If the risk is greater than the second threshold risk, the EMV notifies the remote operator of the state pauses the performance until feedback is received from the remote operator.

Abstract: A transportable kitchen workcell includes a prefabricated enclosure, a robotic arm secured within the enclosure, one or more food appliances, a food prep area and storage, a sensor assembly, and a processor operable to command the robotic arm to autonomously prepare a completed entree from a wide variety of raw ingredients. A dispensing unit is arranged in the enclosure for dispensing the raw ingredients onto a target surface according to a selected flowrate and based on real time feedback measured during dispensing. The workcell is self-contained and is adapted to be conveniently moved (e.g., towed) to a new location. A wide range of entrees may be completed without rearranging or retooling the equipment in the workcell. New food items may be prepared by the workcell by simply selecting the applicable program, or by downloading an update corresponding to the new food item.

Abstract: A soft robotic gripper having component parts capable of being assembled in the field at the terminus of an industrial robot arm for providing adaptive gripping of a product. A hub includes a pneumatic inlet leading to outlets. Finger mounts with pneumatic passages hold inflatable fingers, and tension fastener(s) secure and compress the finger mounts toward the hub by passing through the pneumatic passages and fastening under tension in a direction of the hub.

Abstract: A method for autonomously grinding a workpiece includes: accessing a virtual model defining a geometry of the workpiece; identifying a grinding region on the workpiece; and projecting a target grinding profile onto the grinding region on the workpiece. The method also includes: based a geometry of the workpiece and the target grinding profile, generating a tool path for removal of material from the grinding region to the target grinding profile; and assigning a target force to the target region. The method also includes, during a processing cycle: accessing a sequence of force values output by a force sensor coupled to a grinding head; navigating the grinding head across the grinding region according to the tool path; and, based on the sequence of force values, deviating the grinding head from the tool path to maintain forces of the grinding head on the grinding region proximal the target force.

Abstract: An automated kitchen assistant system inspects a food preparation area in the kitchen environment using a plurality of sensors or cameras. A trained model computes the identity and the location of the food item. In embodiments, the food items are on a grill, and the automated kitchen assistant system is operable to compute the time remaining to remove or flip each of the food items. The output may further be utilized to command a robotic arm, kitchen worker, or otherwise assist in food preparation. Related methods are also described.

Abstract: Aspects of this technical solution can include identifying, by a processor coupled to non-transitory memory, a plurality of bounding boxes for one or more objects depicted in each image of a sequence of images captured during operation of an autonomous vehicle, allocating, by the processor and based on corresponding positions of the bounding boxes in each image and corresponding time stamps, one or more of the bounding boxes to one or more tracking identifiers each indicating trajectories of corresponding objects, generating, by the processor and based on the time stamps and the bounding boxes allocated to each of the tracking identifiers, one or more tracking images for each of the tracking identifiers, each of the tracking images including visual indications of the time stamps, and training, by the processor and based on the tracking images, an artificial intelligence model to output an indication of a type of trajectory.