A method for controlling a robot includes applying a setpoint force to a contact point; measuring a contact stiffness at the contact point; and slowing down the moving robot using its drives and/or braking the robot to apply the setpoint force to the contact point by the slowing down and/or slowed down robot depending on the measured contact stiffness, wherein the robot is slowed down before the setpoint force is reached.

A disclosed system includes a physically plausible virtual runtime environment to simulate a real-life environment for a simulated robot and a test planning and testing component to define a robotic task and generate virtual test cases for the robotic task. The test planning and testing component is further operable to generate virtual test cases for the robotic task, determine a control strategy for executing the virtual test cases, and create the physics-based simulated environment. The system further includes a robot controller operable to execute the virtual test cases in parallel in the physics-based simulated environment, measure a success of the execution, and store training and validation data to a historical database to train a machine learning algorithm. The robot controller may continuously execute the virtual test cases and use the machine learning algorithm to adjust parameters of the control strategy until optimal test cases are determined.

This disclosure relates generally to a method and system that provides personalized neuro motor rehabilitation therapy using a musculoskeletal arm model. The arm model is personalized using anthropometric measures and further adapted to operate using an optimized set of muscle actuators considering associated redundancy. The method generates trajectories associated with reach motion profiles for each motion task utilizing joint kinematics and inverse dynamics by integrating forward dynamics and muscle synergy concepts to select the optimized set of muscle actuators. The generated trajectories are further ranked based on muscle synergy, minimum energy consumption and optimized trajectory to select rehabilitation therapy best suited for effective recovery. Conventional methods that work with neural dynamics in deriving muscle synergy are dependent on single tasks, leaving synergy variation with task variability unexplored. The present disclosure provides understanding of work space, task variability and synergy paradigm to derive conclusive control actions for aiding rehabilitation effectively.

A simulation apparatus includes: a robot model arranging unit that arranges a robot model on a virtual space; a configuration information storage unit that stores configuration information of a robot system; a transport device arrangement position calculating unit that calculates a transport device arrangement position based on a follow-up operation reference coordinate system related to a follow-up operation of a robot, included in the configuration information; and a detection unit arrangement position calculating unit that calculates a detection unit arrangement position based on the follow-up operation reference coordinate system.

A computer-implemented method for determining a control trajectory for a robotic device. The method includes: performing an information theoretic model predictive control applying a control trajectory sample prior in each time step to obtain a control trajectory for a given time horizon; determining the control trajectory sample prior depending on a data-driven trajectory prediction model which is trained to output a control trajectory sample as the control trajectory sample prior based on an actual state of the robotic device.

Described is system for tele-robotic operations over time-delayed communication links. Sensor data is acquired from at least one sensor for sensing surroundings of a robot having at least one robotic arm for manipulating an object. A three-dimensional model of the sensed surroundings is generated, and the sensor data is fit to the three-dimensional model. Using the three-dimensional model, a user demonstrates a movement path for the at least one robotic arm. A flow field representing the movement path is generated and combined with obstacle-repellent forces to provide force feedback to the user through a haptic device. The flow field comprises a set of parameters, and the set of parameters are transmitted to the robot to execute a movement of the at least one robotic arm for manipulating the object.

A lab automation system receives an instruction from a user to perform a protocol within a lab via an interface including a graphical representation of the lab. The lab includes a robot and set of equipment rendered within the graphical representation of the lab. The lab automation system identifies an ambiguous term of the instruction and pieces of equipment corresponding to the ambiguous term and modifies the interface to include a predictive text interface element listing the pieces of equipment. Upon a mouseover of a listed piece of equipment within the predictive text interface element, the lab automation system modifies the graphical representation of the lab to highlight the listed piece of equipment corresponding to the mouseover. Upon a selection of the listed piece of equipment within the predictive text interface element, the lab automation system modifies the instruction to include the listed piece of equipment.

A soft joint gripper based on 4D printing comprises a palm body and five soft finger units connected with the palm body; each soft finger unit is provided with two soft finger joints and two finger bones; the finger bones are made of 3D printing resin; the soft finger joints are two symmetrical double-layer thin-film soft finger joint actuators; the double-layer thin-film soft finger joint actuator is made of a 4D printing liquid crystal elastomer and a polyimide electrothermal film, and the bending angle of each double-layer thin-film soft finger joint actuator is changed by energization or heating stimulation; and the double-layer film soft finger joint actuator is used to control the soft finger unit to perform reversible bending motion. Accurate control of the soft joint gripper can be realized.

A virtualization system implemented within a cloud server enables the simulation of robot structure and behavior in a virtual environment. The simulated robots are controlled by clients remote from the cloud server, enabling human operators or autonomous robot control programs running on the clients to control the movement and behavior of the simulated robots within the virtual environment. Data describing interactions between robots, the virtual environment, and objects can be recorded for use in future robot design. The virtualization system can include robot templates, enabling users to quickly select and customize a robot to be simulated, and further enabling users to update and re-customize the robot in real-time during the simulation. The virtualization system can re-simulate a portion of the robot simulation when an intervention by a human operator is detected, positioning robots, people, and objects within the virtual environment based on the detected intervention.

A biomimetics based robot is disclosed. The robot may include filament driven and fluid pumped elastomer based artificial muscles coordinated for slow twitch/fast twitch contraction and movement of the robot by one or more microcontrollers. A process may provide physics based simulation for movement of a robot in a virtual setting. Embodiments include artificial skin and sensor systems in the artificial muscles and artificial skin whose feedback is used to control the muscles and movement of the robot.