Deep learning for deformable object manipulation

For humans, working with deformable objects is not significantly more difficult than handling rigid objects. We learn naturally to shape them, fold them, and manipulate them in different ways and still recognize them.

But for robots and artificial intelligence systems, manipulating deformable objects present a huge challenge. Consider the series of steps that a robot must take to shape a ball of dough into pizza crusts. It must keep track of the dough as it changes shape, and at the same time, it must choose the right tool for each step of the work. These are challenging tasks for current AI systems, which are more stable in handling rigid-body objects, which have more predictable states.

Now, a new deep learning technique developed by researchers at MIT, Carnegie Mellon University, and the University of California at San Diego, shows promise to make robotics systems more stable in handling deformable objects. Called DiffSkill, the technique uses deep neural networks to learn simple skills and a planning module for combining the skills to solve tasks that require multiple steps and tools.

Read the full article on TechTalks.

For more on AI research:

• DALL-E 2, the future of AI research, and OpenAI’s business model

• New RL technique achieves superior performance in control tasks

• Meta’s Yann LeCun on his vision for human-level AI

• What DeepMind’s AlphaCode is and isn’t