Goto

Collaborating Authors

 difficult terrain


How Robots Learn To Hike - AI Summary

#artificialintelligence

ETH Zurich researchers led by Marco Hutter developed a new control approach that enables a legged robot, called ANYmal, to move quickly and robustly over difficult terrain. Steep sections on slippery ground, high steps, scree and forest trails full of roots: the path up the 1,098-meter-high Mount Etzel at the southern end of Lake Zurich is peppered with numerous obstacles. "The reason is that the information about the immediate environment recorded by laser sensors and cameras is often incomplete and ambiguous," explains Takahiro Miki, a doctoral student in Hutter's group and lead author of the study. Before the robot could put its capabilities to the test in the real world, the scientists exposed the system to numerous obstacles and sources of error in a virtual training camp. The ETH Zurich robot automatically and quickly overcame numerous obstacles and difficult terrain while autonomously exploring an underground system of narrow tunnels, caves, and urban infrastructure.


How robots learn to hike

#artificialintelligence

Steep sections on slippery ground, high steps, scree and forest trails full of roots: the path up the 1,098-metre-high Mount Etzel at the southern end of Lake Zurich is peppered with numerous obstacles. But ANYmal, the quadrupedal robot from the Robotic Systems Lab at ETH Zurich, overcomes the 120 vertical metres effortlessly in a 31-minute hike. That's 4 minutes faster than the estimated duration for human hikers -- and with no falls or missteps. This is made possible by a new control technology, which researchers at ETH Zurich led by robotics professor Marco Hutter recently presented in the journal Science Robotics. "The robot has learned to combine visual perception of its environment with proprioception -- its sense of touch -- based on direct leg contact. This allows it to tackle rough terrain faster, more efficiently and, above all, more robustly," Hutter says.


How robots learn to hike

#artificialintelligence

ETH Zurich researchers led by Marco Hutter developed a new control approach that enables a legged robot, called ANYmal, to move quickly and robustly over difficult terrain. Thanks to machine learning, the robot can combine its visual perception of the environment with its sense of touch for the first time. Steep sections on slippery ground, high steps, scree and forest trails full of roots: the path up the 1,098-meter-high Mount Etzel at the southern end of Lake Zurich is peppered with numerous obstacles. But ANYmal, the quadrupedal robot from the Robotic Systems Lab at ETH Zurich, overcomes the 120 vertical meters effortlessly in a 31-minute hike. That's 4 minutes faster than the estimated duration for human hikers--and with no falls or missteps.


How robots learn to hike

Robohub

The legged robot ANYmal on the rocky path to the summit of Mount Etzel, which stands 1,098 metres above sea level. Steep sections on slippery ground, high steps, scree and forest trails full of roots: the path up the 1,098-metre-high Mount Etzel at the southern end of Lake Zurich is peppered with numerous obstacles. But ANYmal, the quadrupedal robot from the Robotic Systems Lab at ETH Zurich, overcomes the 120 vertical metres effortlessly in a 31-minute hike. That's 4 minutes faster than the estimated duration for human hikers – and with no falls or missteps. This is made possible by a new control technology, which researchers at ETH Zurich led by robotics professor Marco Hutter recently presented in the journal Science Robotics.


China deploys armed robotic vehicles during standoff with India to deal with cold, difficult terrain: reports

FOX News

Fox News national security correspondent Jennifer Griffin discusses a report alleging China is developing'brain control weapons' on'Fox Report.' Reports from India claim that China has started to deploy armed robotic vehicles to handle the altitude and terrain that has proven too difficult for its troops. China and India clashed in Sept. 2020 during a border dispute along the southern coast of Pangong Lake in an area known in China as Shenpaoshan and in India as Chushul, but the armies continued their standoff along the two nations' borders throughout 2021. China has now reportedly deployed unmanned ground vehicles (UGV) to the region of Tibet to strengthen its position. People's Liberation Army (PLA) soldiers march next to the entrance to the Forbidden City during the opening ceremony of the Chinese People's Political Consultative Conference (CPPCC) in Beijing on May 21, 2020.


Lockheed Martin and GM are building an electric Moon buggy that greatly differs from the Apollo-era

Daily Mail - Science & tech

As NASA attempts to return to the moon in 2024, the U.S. space agency has tasked Lockheed Martin and General Motors to create a new electric, autonomous lunar rover. The rover will use GM's autonomous driving technology and allow it to go'significantly farther' than the ones the auto maker worked on during the Apollo program, some 50 years ago. Though the rover is still in the planning stages, both companies highlighted that it is imperative it allows astronauts to traverse difficult terrains of the lunar south pole, which could hold a number of interesting discoveries, including water. A concept of what the Lockheed Martin-GM rover might look like on the moon's south pole The lunar south pole is a site of interest for scientists and agencies planning crewed missions to the Moon. This is because water ice has been found in shadowed areas in that region with craters that never get sunlight.


This Birdlike Robot Uses Thrusters to Float on Two Legs

WIRED

We humans envy birds for their seemingly effortless ability to fly, and for their ability to extract endless amounts of bread from old people in parks. But there's a middle ground between those two states--soaring and ambling around on two feet in pursuit of crumbs--that we tend to overlook: Birds are a kind of hybrid. To walk over difficult terrain, they can flap to stabilize, while we humans trip over ourselves. When roboticists look to nature for inspiration, they overlook this middle-ground state, developing robots that either walk or fly--but not both. "Everyone is working on drones or bipedal locomotion," says Caltech roboticist Soon-Jo Chung. "We want to lay the groundwork for combining these two different types."


This artificial intelligence teaches robots to walk--by creating custom obstacle courses

#artificialintelligence

Before you run hurdles, you have to learn to crawl, and before you read William Shakespeare, you need to know the alphabet. Any educator knows the importance of a step-by-step lesson plan for mastering a task. Now, researchers at Uber AI Labs have designed an algorithm that comes up with its own curriculum for teaching simulated robots to cross difficult terrain, without falling flat on their faceless bodies. The algorithm might one day even help autonomous vehicles react in emergency situations. The new program, called Paired Open-Ended Trailblazer (POET) first comes up with a set of unique terrains, each inhabited by a computer-controlled character.


Hyundai is set to unveil a car that WALKS

Daily Mail - Science & tech

Hyundai is set to take the covers off what might be the craziest concept of 2019 when it unveils the Elevate on Monday. Being shown for the first time at the Consumer Electronics Show in Las Vegas on Monday, it's the first UMV - or Ultimate Mobility Vehicle - fitted with legs so it can walk over difficult terrains. And it's not the only wacky offroader that will be shown to the public for the first time in the next week - Suzuki set to preview two modified versions of its latest Jimny SUV. Strolling into 2019: Hyundai is due to unveil one of the craziest concept vehicles we're likely to see all year when it takes the wraps off the Elevate in Las Vegas on January 7 Hyundai has teased what's in store for January 7 with the early release of a preview image of the incredible vehicle in question. Elevate looks set to become one of the most bonkers concepts of the year.


Leg over wheels: Ghost robotics' Minitaur proves legged capabilities over difficult terrain

Robohub

Ghost Robotics--a leader in fast and lightweight direct-drive legged robots--announced recently that its Minitaur model has been updated with advanced reactive behaviors for navigating grass, rock, sand, snow and ice fields, urban objects and debris, and vertical terrain. The latest gaits adapt reactively to unstructured environments to maintain balance, ascend steep inclines up to 35º, climb up to 15cm curb-sized steps, crouch to fit under crawl spaces as low as 27cm, and operate at variable speeds and turning rates. Minitaur's high-force capabilities enable it to leap up to 40cm onto ledges and across gaps of up to 80cm. Its high control bandwidth allows it to actively balance on two legs, and its high speed operation allows its legs to navigate challenging environments rapidly, whilst reacting to unexpected contact. "Our primary focus since releasing the Minitaur late last year has been expanding its behaviors to traverse a wide range of terrains and real-world operating scenarios," said Gavin Kenneally, and Avik De, Co-founders of Ghost Robotics.