Skip to main content

Four-legged walking robot uses a drone sidekick to map and avoid difficult terrain

It’s no secret that walking robots are capable of navigating difficult and technical terrain more effectively than their their wheeled counterparts, but they also have a major limitation — they can’t look ahead very far to plan the best travel route based on the current status of their surroundings. To remedy this problem, researchers at the Autonomous Systems Lab at ETH Zurich have developed a brilliant solution that uses a drone to give a walking robotic quadruped a pair of long distance eyes.

When they venture out, the current generation of walking robots are provided with existing map data, which can be months and even years old depending on the source. Any new terrain information is gathered in real-time using onboard cameras, which are capable of detecting items in the robot’s immediate surroundings. As a result, a walking robot must scan its local environment and make changes on the fly. It cannot plan its route of travel too far in advance because it cannot detect potential obstacles.

The system designed by Autonomous Systems Lab takes the burden of terrain detection off the robot and places it onto a drone, which acts as scout. In their experiments, a camera-equipped hexacopter drone would fly ahead of the walking robot, mapping the terrain, recording landmarks and calculating the elevation as it goes along. This up-to-date information then was sent to the robot, which combined this local data with its global map to choose the best path for traveling across its terrain. This information is continuously updated by the drone, allowing the robot to receive a steady stream of navigational data that it can use to make course adjustments as necessary.

In the experimental course, the walking robot was able to successfully navigate previously unknown terrain using the map data provided by the drone. It walked without incident from its starting point to the goal position, traversing narrow pathways, scaffolding and even a ramp along the way. These experiments are part of a broader initiative to develop the next generation robotic quadrupeds that will be energy efficient well as capable of dynamic motions including a fast walk, trot, bound, and gallop.

Editors' Recommendations

Kelly Hodgkins
Kelly's been writing online for ten years, working at Gizmodo, TUAW, and BGR among others. Living near the White Mountains of…
Notre Dame fire: How drones and a robot called Colossus helped limit the damage
notre dame fire how drones and a robot helped to prevent worse damage colossus

As the people of France begin to come to terms with Monday's devastating fire at the Notre Dame Cathedral in Paris, stories are beginning to emerge of how the blaze was tackled.

Around 500 firefighters made their way to the 850-year-old Gothic structure when the alarm sounded at around 6.30 p.m. local time on April 15, but when they arrived, the enormity of the challenge that confronted them was immediately apparent.

Read more
This very talented robotic leg learned to walk all by itself
robot limb

A team of researchers at the USC Viterbi School of Engineering believe they have become the first to create an AI-controlled robotic limb driven by animal-like tendons that can even be tripped up and then recover within the time of the next footfall, a task for which the robot was never explicitly programmed to do. Photo by Matthew Lin. Matthew Lin

Robots suck at walking. Even the most advanced of their kind, like those developed by engineers at Boston Dynamics, have taken years to evolve beyond the sure-footedness of a toddler stumbling on an ice rink. And that’s when they’re programmed ahead of time to perform the task. But what if robots were created without the innate ability to walk? How might they find their footing?

Read more
Meet the game-changing pitching robot that can perfectly mimic any human throw
baseball hitter swings and misses

Who’s your favorite baseball pitcher? Shane McClanahan? Sandy Alcantara? Justin Verlander? Whoever you said, two of the top sports-tech companies in the U.S. -- Rapsodo and Trajekt Sports -- have teamed up to build a robot version of them, and the results are reportedly uncannily accurate.

Okay, so we’re not talking about walking-talking-pitching standalone robots, as great a sci-fi-tinged MLB ad as that would be. However, Rapsodo and Trajekt have combined their considerable powers to throw a slew of different technologies at the problem of building a machine that's able to accurately simulate the pitching style of whichever player you want to practice batting against -- and they may just have pulled it off, too.

Read more