MIT researchers have developed a new AI technique called smoothing, which simplifies contact-rich manipulation planning for robots. The technique summarizes multiple contact events into a smaller number of decisions, enabling a simple algorithm to quickly identify effective manipulation plans. This method could lead to the use of smaller, mobile robots in factories, reducing energy consumption and costs. It could also be useful for robots sent on exploration missions. The researchers combined their model with an efficient algorithm to search through the decisions, significantly reducing computation time. The approach achieved the same performance as reinforcement learning in a fraction of the time. However, the model is limited to slower manipulation tasks and cannot handle highly dynamic motions. Future enhancements are planned to address this limitation. The research was funded by Amazon, MIT Lincoln Laboratory, the National Science Foundation, and the Ocado Group.