Abstract: A system and method for providing in hand robotics dexterous manipulation of an object that include determining a geometry of an object, a position of the object, and a placement of at least one robotic finger of a robot upon the object. The system and method also include computing a direction of rolling or rotation of the object by the at least one robotic finger. The system and method additionally include updating a position of the object that is manipulated by the robot. The system and method further include updating contact points of the at least one robotic finger with respect to contacting the object in a manner that ensures that a viable grasp is enforced to have force closure to retain the object.

Abstract: A system and method for providing tactile sensor calibration that include receiving force data from a force/torque sensor and tactile data from a plurality of taxels of a tactile sensor pad. The system and method also include interpolating the force data and the tactile data and pre-processing the interpolated data to align the force data and the tactile data to match data points. The system and method additionally include dividing the matched data points into individual interactions and computing a linear regression for each segment that is associated with each interaction. The system and method further include determining an amount of force that is absorbed by the tactile sensor pad based on a conversion of tactile measurements sensed by the plurality of taxels into Newtons based on the linear regression computed for each segment.

Abstract: Systems and techniques for grasp selection may include receiving one or more candidate object trajectories and a current grasp of a robotic hand on an object, sampling random candidate grasps for the one or more candidate object trajectories based on the current grasp, generating one or more grasps to be optimized for each of the one or more candidate object trajectories based on the sampled candidate grasps, and optimizing one or more of the grasps to be optimized for each of the one or more candidate object trajectories based on a cost function.

Abstract: Systems and methods for online iterative re-planning are provided herein. In one embodiment, a method includes receiving, at a first time step, a first grasp and an initial object pose of an agent. The method also includes generating a first set of candidate object trajectories based on the first grasp and the initial object pose. Candidate object trajectories of the first set of candidate object trajectories provide a number object poses from the initial object pose to a goal for a number of future time steps after the first time step. The method further includes calculating contact points for grasps associated with each candidate object trajectory of the first set of candidate object trajectories. The method further includes selecting a first candidate object trajectory from the first set of candidate object trajectories. The method includes causing the agent to execute the first candidate object trajectory at a second time step.

Abstract: Systems and methods for online augmentation for learned grasping are provided. In one embodiment, a method is provided that includes identifying an action from a discrete action space. The method includes identifying a second set of grasps of the agent utilizing a transition model based on the action and at least one contact parameter. The at least one contact parameter defines allowed states of contact for the agent. The method includes applying a reward function to evaluate each grasp of the second set of grasps based on a set of contact forces within a friction cone that minimizes a difference between an actual net wrench on the object and a predetermined net wrench. The reward function is optimized online using a lookahead tree. The method includes selecting a next grasp from the second set. The method includes causing the agent to execute the next grasp.

Abstract: A system and method for providing accelerated reinforcement training that include receiving training data associated with a plurality of atomic actions. The system and method also include inputting the training data associated with the plurality of atomic actions to a neural network. The system and method additionally include completing dynamic programming to generate an optimal policy. The system and method further include inputting the optimal policy through a behavior cloning pipeline to output an expert policy for behavior cloning that is associated with the plurality of atomic actions.

Abstract: A robot for object manipulation may include sensors, a robot appendage, actuators configured to drive joints of the robot appendage, a planner, and a controller. Object path planning may include determining poses. Object trajectory optimization may include assigning a set of timestamps to the poses, optimizing a cost function based on an inverse kinematic (IK) error, a difference between an estimated required wrench and an actual wrench, and a grasp efficiency, and generating a reference object trajectory based on the optimized cost function. Grasp sequence planning may be model-based or deep reinforcement learning (DRL) policy based. The controller may implement the reference object trajectory and the grasp sequence via the robot appendage and actuators.

Abstract: A robot for object manipulation may include sensors, a robot appendage, actuators configured to drive joints of the robot appendage, a planner, and a controller. Object path planning may include determining poses. Object trajectory optimization may include assigning a set of timestamps to the poses, optimizing a cost function which may be a cost function for finger sliding based on a penalty for a sliding distance, a change in desired normal direction, and a wrench error associated with sliding a robot finger, and generating an object trajectory based on the optimized cost function. Grasp sequence planning may be model-based or deep reinforcement learning (DRL) policy based. The controller may execute the object trajectory and the grasp sequence via the robot appendage and actuators.

Abstract: The robotic upper limb rehabilitation device assists in rehabilitation of an upper limb of a human patient recovering from a stroke or the like. The device is an exoskeleton having an articulated shoulder assembly having five degrees of freedom, including at least two degrees of freedom simulating inner shoulder movement. An upper arm member is pivotally attached to the shoulder assembly, and a forearm assembly is pivotally attached to the upper arm member. An inflatable handgrip is pivotally attached to the forearm assembly. A robotic control unit receives signals from sensors and is configured to activate actuators attached to the exoskeleton to assist upper limb movement when required, or to permit the exoskeleton to conform to upper limb movement when no assistance is required.