Thursday, February 22, 2024

New AI system allows robots to manipulate thousands of objects with ease

Humans have long been masters of dexterity; however, robots are still catching up. In an effort to get machines to replicate human abilities, a team of scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a new AI system that could give robots that same kind of dexterity.

The new model-free framework can learn to reorient objects with the robotic hand facing both upwards and downwards, in a step towards more human-like manipulation. It can manipulate over 2000 geometrically different objects in both cases. This new ability to manipulate anything could help the hand quickly pick-and-place objects in specific ways and locations and even generalize to unseen objects.

The MIT CSAIL team used a simulated, anthropomorphic hand with 24 degrees of freedom and showed evidence that the system could be transferred to a real robotic system in the future.

The system uses a model-free reinforcement learning algorithm with deep learning and something called a “teacher-student” training method. The “teacher” network is trained on information about the object and robot that’s easily available in simulation but not in the real world. The knowledge of the “teacher” is then distilled into observations that can be acquired in the real world, such as depth images captured by cameras, object pose, and the robot’s joint positions.

The robot could reorient a large number of objects it had never seen before and with no knowledge of shape. It can manipulate small, circular-shaped objects such as apples, tennis balls, marbles, with a nearly 100% success rate. However, when it comes to more complex objects, like a spoon, a screwdriver, or scissors, its success rate falls closer to 30%. Since success rates varied with object shape, in the future, the team notes that training the model based on object shapes could improve performance.

Still, the system has great potential; it could be an asset in speeding up logistics and manufacturing, helping with common demands such as packing objects into slots for kitting or dexterously manipulating a wider range of tools.