FALCON from Carnegie Mellon doubled the accuracy of humanoid robot control

Post Thumbnail

Scientists from the Adaptive Robotics Laboratory at Carnegie Mellon University created a system called FALCON, which significantly improves the ability of humanoid robots to perform complex tasks with high force loads. This is a real breakthrough in the field of robotics, opening new possibilities for robot applications in real-world conditions.

The main feature of FALCON lies in its architecture, consisting of 2 separate artificial intelligence agents that work as a single unit. The first agent is responsible for stable walking and balance, while the second controls precise hand movements considering applied force. Thanks to such function division, robots can learn in a virtual environment to perform real physical tasks requiring not only precision but also significant force.

After training in simulation, robots are capable of performing actions such as moving heavy objects, opening massive doors, or maintaining balance under external influences, for example, when they are pushed. This is a significant step forward compared to previous control systems.

One of the main advantages of FALCON is its versatility. The system does not require complex configuration for each new robot model. Researchers tested it on 2 completely different platforms — Unitree G1 and Booster T1. And in both cases, the results turned out to be impressive. Hand control accuracy increased by 100%, and stability when performing force tasks reached the level of industrial requirements.

The FALCON system can withstand loads up to 100 newtons, which is almost a third of the robot’s own weight.

I am really surprised! FALCON for the first time offers an effective solution to the problem of simultaneous control of balance and force impact. Which historically has been one of the main obstacles for applying humanoid robots in real force tasks.

AIvengo > Reviews > FALCON from Carnegie Mellon doubled the accuracy of humanoid robot control
Почитать из последнего
UBTech will send Walker S2 robots to serve on China's border for $37 million
Chinese company UBTech won a contract for $37 million. And will send humanoid robots Walker S2 to serve on China's border with Vietnam. South China Morning Post reports that the robots will interact with tourists and staff, perform logistics operations, inspect cargo and patrol the area. And characteristically — they can independently change their battery.
Anthropic accidentally revealed an internal document about Claude's "soul"
Anthropic accidentally revealed the "soul" of artificial intelligence to a user. And this is not a metaphor. This is a quite specific internal document.
Jensen Huang ordered Nvidia employees to use AI everywhere
Jensen Huang announced total mobilization under the banner of artificial intelligence inside Nvidia. And this is no longer a recommendation. This is a requirement.
AI chatbots generate content that exacerbates eating disorders
A joint study by Stanford University and the Center for Democracy and Technology showed a disturbing picture. Chatbots with artificial intelligence pose a serious risk to people with eating disorders. Scientists warn that neural networks hand out harmful advice about diets. They suggest ways to hide the disorder and generate "inspiring weight loss content" that worsens the problem.
OpenAGI released the Lux model that overtakes Google and OpenAI
Startup OpenAGI released the Lux model for computer control and claims this is a breakthrough. According to benchmarks, the model overtakes analogues from Google, OpenAI and Anthropic by a whole generation. Moreover, it works faster. About 1 second per step instead of 3 seconds for competitors. And 10 times cheaper in cost per processing 1 token.