Robotics startup MagicLab introduced a team of humanoid robots in a factory to train for diverse jobs.
MagicLab’s MagicBot robot performs many tasks such as production monitoring, material handling, parts picking and sorting, inventory review and management. Humanoid robots also demonstrated the ability to operate cooperatively on a small scale, demonstrating that they can work effectively together, Interesting Engineering reported on December 9.
In January, MagicLab introduced a third-generation humanoid robot called MagicBot, designed to compete with Boston Dynamics’ Atlas robot. In February, they shared videos of the robot roasting marshmallows, performing magic tricks, and dancing. MagicLab joins a wave of companies deploying robots in the industrial landscape as China aims to mass produce humanoid robots by 2025 and dominate the market by 2027. Founded in December 2023, MagicLab (Magic Atom Robotics Technology) focuses on revolutionizing research and rescue, logistics, and manufacturing with humanoid robots.
In the new video, several MagicBot humanoid robots work together. A robot transfers a material tray to another robot at the work station after lifting it from the assembly point. Their effective collaboration is demonstrated when the second robot takes the object out of the box and transfers it to processing machinery.
“Compared with traditional composite robots, humanoid robots are more adaptable to complex environments thanks to their human-like characteristics and can be adjusted to different jobs and production line layouts. It Especially suitable for the fields of computers, communications, consumer electronics, home appliances and many other factories that need to regularly change production lines,” said Wu Changzheng, director of Magic Atom company.
Currently, the humanoid robot MagicBot used in factories can rotate freely 42 degrees. Its arms can lift objects weighing up to 20 kg while its entire body can transport 40 kg of goods. Made from ultra-light, highly durable materials to increase efficiency, MagicBot has a battery life of up to 5 hours when traveling and operating continuously. In addition to roasting marshmallows on a tray, folding children’s clothes and placing them in a basket, the remote-controlled robot can also water plants and dance to exciting music. It also possesses impressive dexterity when grasping small objects and performing diverse tasks with smooth agility.
MagicBot achieves these advanced skills using miniature high-torque servo actuators combined with extremely sensitive multi-dimensional pressure sensors, allowing for exceptionally smooth hand movements. The developer emphasizes that the six servo actuators play a key role in allowing it to flexibly control objects, ensuring users have precise and intuitive control. The robot’s hands excel at grasping objects of various shapes, sizes, weights and materials, including soft, slippery or malleable objects.
According to its manufacturers, MagicBot can simulate about 70% of human hand movements, meeting the requirements for a wide range of applications, from household work and public services to specialized industrial operations and Handling hazardous materials. MagicBot is also equipped with many sensors. Data from the sensor is aggregated by an algorithm to create a meta-cognitive sensor, allowing the robot to observe the environment 360 degrees and recognize semantics.
According to Sango Automation, cognitive capabilities allow MagicBot to plan a safe path, avoid obstacles, and reach the operating point efficiently using a self-developed navigation algorithm. Through data-augmented training, MagicBot continuously improves its ability to perceive the environment, make decisions and perform tasks. MagicBot uses four types of training data: synthetic data, remote operation data, imitation learning data, and real-time field data. To optimize data usage, the team developed the MagicData AI engine for data annotation, processing, and simulation training.
The new MagicBot robot, expected to launch in early 2025, will enter small-scale production and can be deployed in industrial and commercial sectors.