News

In this blog, you'll learn about these two lens types with key insights into their attributes and best-use scenarios in the world of embedded vision.

The quadrupedal robot ANYmal went back to school and has learned a lot. Researchers used machine learning to teach it new skills: the robot can now climb over obstacles and successfully negotiate pitfalls.

The robot known as ANYmal has, for some time, had no problem coping with the stony terrain of Swiss hiking trails. Now researchers at ETH Zurich have taught this quadrupedal robot some new skills: It is proving rather adept at parkour, a sport based on using athletic maneuvers to smoothly negotiate obstacles in an urban environment, which has become very popular. ANYmal is also proficient at dealing with the tricky terrain commonly found on building sites or in disaster areas.

Recreating the action of opening doors in the virtual world requires engineering ways in which to provide the equivalent haptic feedback and steer users away from walls in the real world. A research group has done just this; developing RedirectedDoors+, which employs door robots and rotation to create a more realistic experience.

A new tool will help orthodontists correctly fit braces onto teeth. Using artificial intelligence and virtual patients, the tool predicts how teeth will move, so as to ensure that braces are neither too loose nor too tight.

Is there a way to stick hard and soft materials together without any tape, glue or epoxy? A new study shows that applying a small voltage to certain objects forms chemical bonds that securely link the objects together. Reversing the direction of electron flow easily separates the two materials. This electro-adhesion effect could help create biohybrid robots, improve biomedical implants and enable new battery technologies.

A new University of Michigan study on how humans and robots work together on tasks with conflicting objectives is the first to demonstrate that trust and team performance improve when the robot actively adapts to the human's strategy.

When lower limb exoskeletons—mechanical structures worn on the leg—do not operate properly, some people adjust quickly while others compensate with their ankle or hip, expending more energy than necessary, according to a new study by University of Michigan researchers.

Introducing SIMA, a Scalable Instructable Multiworld Agent

Introducing SIMA, a Scalable Instructable Multiworld Agent

Introducing SIMA, a Scalable Instructable Multiworld Agent

Introducing SIMA, a Scalable Instructable Multiworld Agent

Introducing SIMA, a Scalable Instructable Multiworld Agent

Introducing SIMA, a Scalable Instructable Multiworld Agent

Introducing SIMA, a Scalable Instructable Multiworld Agent