A four-legged robot has learned to change the way it runs while navigating forests, staircases and obstacle courses. — seamlessly switching between a steady trot and a faster bounding gait without instructions from a human operator.
The 100-pound (45 kilograms) robot, called KAIST HOUND, uses cameras and lidar to scan the ground ahead, then selects an appropriate gait and adjusts its movements in real time. In outdoor tests, it crossed a 0.7-mile (1.1- kilometers) university campus route and a 0.2-mile (0.3 km) forest trail strewn with roots, logs and slippery leaves.
The researchers described the robotic framework on July 15 in the journal Science Robotics.
Changing gait
Animals naturally change their gait depending on their speed and surroundings. A dog might trot carefully across uneven ground, for example, before bounding over a fallen branch. Reproducing this adaptability in robots is tricky because different movements are often controlled by separate, highly specialized coding systems, and transitions between them can cause a lag that drives the robot to stumble.
To overcome this issue, researchers developed a special training framework called action pretrained transformer–based reinforcement learning (APT-RL). This is an artificial intelligence (AI) training system that first studies many examples of actions, uses a transformer to understand patterns across those actions, and then improves through rewards and penalties.
The training began with a simple, two-dimensional computer model of the robot. Using trajectory optimization — a technique that calculates physically workable movements for the robot — the team generated 180,000 short trotting and bounding sequences, including the joint forces the robot’s legs need to perform. The dataset represented about 15.5 hours of movement but took only around eight minutes to produce.
During reinforcement learning — a machine learning technique where AI learns to make the best decisions by engaging with a particular environment through trial and error — an AI system then learned how to select and modify those skills while negotiating simulated stairs, stepping stones, hurdles, gaps and rough ground.
Get the world’s most fascinating discoveries delivered straight to your inbox.
In digital simulations, the robot dog was not limited to copying its prerecorded movements. It could also make corrections for three-dimensional terrain and unexpected situations, such as jumping over a log — a behavior that wasn’t included in the original, flat-ground training data.
The KAIST HOUND quadrupedal robot navigates a forested terrain
(Image credit: Jun-Gill Kang, Jaehyun Park)
Finally, the researchers configured the system to include the robot’s depth camera and lidar scanner in the simulation.
In one indoor test, HOUND bounded across an obstacle 2 feet (60 centimeters) high while briefly achieving 9.5 mph (15 km/h). It also jumped down a three-step staircase. The robot generally chose trotting at lower speeds on irregular ground, while bounding became more common at higher speeds or when it encountered larger steps, hurdles or gaps. The AI system that could select either gait performed more consistently across the different simulated environments than the version restricted to trotting or bounding alone.
The researchers suggest the technology could eventually help robots navigate disaster zones or other places inaccessible for wheeled machines. However, the current framework only allows two gait choices and mainly handles forward movement. Rapid turning, sideways motion and other behaviors like crawling remain future goals for the research team.
Key Takeaways for What is Ozempic Breath? Ozempic breath is on the rise as GLP-1 drugs have been linked to a surge in bad-breath complaints. Dry mouth and acid reflux may be driving “Ozempic breath.” Persistent bad breath could signal a larger dental problem that should not be ignored. Executives at The Hershey Company shared…
In an interview with BBC Jersey, external, Chief Minister Lyndon Farnham was asked whether his government would consider buying the site. “I fancy that coming into public ownership somehow,” he said. Farnham said he was keen to speak to the National Trust about it. “There’s a great opportunity, if you look at the Simon Sand…
As the title says, I've spent the last 3.5 years working on Anukari, a 3D physics simulation much like a video game engine, except that instead of running at 60 steps per second, it runs at 48,000 (or more) steps per second, so that the physics systems can vibrate at audio frequencies. It's commercial software;…
Since physicist Freeman Dyson first proposed the idea in 1960, the hypothetical “Dyson sphere” has become one of the most intriguing concepts in the search for extraterrestrial intelligence. Rather than a single solid shell, scientists now envision a Dyson “swarm” made up of countless orbiting structures that capture nearly all of a star’s energy. While…
The first person has been treated with a highly anticipated new gene therapy that aims to turn back the clock on ageing cells. The trial is aimed at retinal cells, with the hope that encouraging them to behave as if they were young again could improve sight in the affected patients. If it proves to…
Researchers at the City College of New York are charting a fast-growing area of quantum science centered on materials only a few atoms thick. In these systems, light, electric charge, and magnetism are closely connected rather than behaving independently. The work comes from physicist Vinod M. Menon’s Laboratory for Nano and Micro Photonics (LaNMP). Researchers…
