Tag Archives: technology

Rethinking Trust in Social Robotics

How soon do you think you will encounter an autonomous robot in your day-to-day life?  The question of trust between robots and humans will have to become the basis of the entire social robotics. Image credit: epSos.de via Wikimedia (CC BY 2.0) If your answer was not “never”, you probably expect human-robot interaction to start happening soon & its frequency ...

Read More »

NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping

Mapping the 3D volume of an environment during online operation is necessary for tasks like autonomous navigation or mobile manipulation. However, these measurements are affected by sensor noise and pose estimation errors. Volumetric Mapping technique is used in different fields, where image segmentation or other types of image processing are required. Image credit: Toorumer via Wikimedia, CC-BY-SA-4.0 A recent study ...

Read More »

How Boston Dynamics Is Building Its Robot Empire

The name of Boston Dynamics has been already well-established in the world of companies that develop and manufacture robots. In fact, Boston Dynamics is also one of the most innovative engineering ventures relentlessly improving their existing designs while also pursuing new and more radical innovative ideas. Spot – one of the most famous creations from Boston Dynamics. Image credit: CNBC ...

Read More »

This Robot Walks, Flies, Skateboards, Slacklines

This robot is unusual. There are many robotic models that are capable of traversing different and difficult types of terrain. This one, however, aptly combines several skills: walking, flying, skateboarding and even slacklining. LEONARDO robot in a flight mode. Image credit: Veritasium (screen from YouTube video) Seeing robots around is not surprising anymore – just think about drones or robotic ...

Read More »

New fibers can make breath-regulating garments

“Robotic” textiles could help performers and athletes train their breathing, and potentially help patients recovering from postsurgery breathing changes. The key features of the new fiber architecture include its extremely narrow size and use of inexpensive materials, which make it relatively easy to structure the fibers into a variety of fabric forms. Credits: Courtesy of the researchers / MIT A ...

Read More »

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes

Lots of learning algorithms have been created to solve robot manipulation problems (such as robotic stacking) with a large and diverse set of objects. However, most of them focused on tasks like grasping that do not typically require complex inter-object contact dynamics. An industrial robot. Machines like this are used to perform robotic stacking operations in a variety of industrial ...

Read More »

OPEn: An Open-ended Physics Environment for Learning Without a Task

Reinforcement learning algorithms are commonly used for narrowly defined tasks. In contrast, humans plan their actions using a mental model of the world’s physical structure. Inspired by human intelligence, a recent paper proposes an environment that is designed as a sandbox where the agent has to learn about how a physical world works. Illustration of the problem setup for modeling ...

Read More »

These neural networks know what they’re doing

A certain type of artificial intelligence agent can learn the cause-and-effect basis of a navigation task during training. Neural networks can learn to solve all sorts of problems, from identifying cats in photographs to steering a self-driving car. But whether these powerful, pattern-recognizing algorithms actually understand the tasks they are performing remains an open question. Image credit: Free-Photos cia Pixabay (Free ...

Read More »

Power walk

Stan Schaar, who lost his left leg in an accident while helping a neighbor, never thought he would again feel the sensation of effortlessly walking with two healthy legs. Then he slipped on a new experimental exoskeleton developed by mechanical engineers at the University of Utah’s Bionic Engineering Lab. “It just felt like a big wind was behind me, pushing me ...

Read More »

Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation

Deep reinforcement learning is successfully applied in many real-world robotic tasks. However, it is limited to domains in which a simulator is available or environments that have been tailored and instrumented for the agent’s training. Interactive learning approach is useful in training not just industrial robotic systems. Image credit: Auledas via Wikimedia, CC-BY-SA-4.0 Therefore, a recent paper proposes an interactive ...

Read More »