Here is an actuator that allows robots to perform high-speed grasping motions. MagLinkage is a low friction and high torque actuator with 1ms torque control and high-backdrivability motion. Robot hands that use MagLinkage can slide and grasp thin objects on a table.
In the past few years, we have covered a bunch of tasks the ANYmal robot is capable of performing and learning. Robotic Systems Lab has shared a new video that shows ANYmal with actuated wheels performing dynamic hybrid walking driving motions.
Snake robots are capable of entering narrow spaces and climbing obstacles with their long, thin bodies. Controlling their precise movements is not easy when you are dealing with so many actuators. Motoyasu Tanaka and colleagues at the University of Electrocommunications Tokyo have come up with methods to control snake-like robots for 3-dimensional steering, climbing, and manipulating things.
Meet the LittleBot Buddy: a cute little social robot with Arduino that can teach kids a thing or two about technology and education. It uses the Meped Arduino board and has 8 digital outputs to run servos, buzzers and LEDs. The robot maps its surroundings all the time, so it will notice when you move objects.
Robots are getting better at handling fragile objects all the time. This 2-fingered robotic gripper can adjust the stiffness of its grasp. UB engineers developed it to mimic the adjustable grip of a human hand and avoid breaking things it is holding. Here is how it works:
each of the gripper’s fingers has a magnetic base that sits between two neodymium magnets that repulse, or push against, the finger. The air gap between the magnets acts like a spring, creating a little give when the hand picks up an object or collides with an external force. The stiffness of the grip can also be adjusted by increasing or decreasing the space between magnets.
The gripper also absorbs energy from collisions. The above video shows it in action.
[HT]
Here is a wearable interface that can be used for teleoperation of whole-body-controlled humanoid robots. The idea is to use two Vive motion trackers and two Myo bracelets. Thanks to this approach, a wide variety of every day tasks can be done by a robot, guided by a human operator.
Meet the Delta X: an open source delta robot based on Arduino that can be used for 3D printing, laser engraving, drawing, and testing touchscreen devices. It can be used with many end effectors. The Delta X robot can be controlled from computers and smartphones.
Soft robots are getting smarter all the time. This stretchable optical lace material developed by Ph.D. student Patricia Xu can gift soft robots the ability to sense how they interact with their environment. A flexible, porous lattice structure manufactured from 3D-printed polyurethane was used for this project.
Meet MARS: a mobile arm robotic system that uses an autonomous mobile platform with 2D/3D sensors, flexible robotic arm, and AI vision to take on indoor tasks. MARS (Mobile Arm Robot System) has high efficiency wheel drive modules. It has obstacle avoidance, adaptable gripper, and a ROS compatible platform.
Here is an artificial hand that merges user and robotic control to make life easier for amputees. EPFL scientists developed it using an algorithm that learns how to decode user intention and translates it into finger movement of the prosthetic hand:
The amputee must perform a series of hand movements in order to train the algorithm that uses machine learning. Sensors placed on the amputee’s stump detect muscular activity, and the algorithm learns which hand movements correspond to which patterns of muscular activity. Once the user’s intended finger movements are understood, this information can be used to control individual fingers of the prosthetic hand.
The algorithm developed kicks in as soon as the user tries to grasp an object. It tells the hand to close its fingers when the object comes in contact with the sensors. The above video shows this artificial robotic hand in action.
[HT]
