A Learning Based Approach for Planning with Safe Actions

Given a configuration involving some objects in an environment, the planning problem, considered in this paper, is to find a plan that rearranges these objects so as to place a new object. The challenging aspect here involves deciding when an object can be placed on top of another object. Here only defining standard planning operators would not suffice. For instance, using these operators we can come up with actions that may be performed at a state but it should not be performed. So we introduce the notion of safe actions whose outcomes are consistent with the laws of physics, commonsense, and common practice. A safe action can be performed if a robot performing the action knows the knowledge of the situation. We developed a knowledge engine using a supervised learning technique. However, unlike the common task of learning functions, our approach is to learn predicates–that evaluate to binary values. By learning such a predicate a robot would be able to decide whether or not an object A can be placed on top of another object B. We give a method to handle new objects for which the predicates have not been learned. We suggest a nondeterministic planning algorithm to synthesize plans that contain only safe actions. Experimental results show the efficacy of our approach.