How can we build autonomous robots that operate in unstructured and dynamic environments such as homes or hospitals? This problem has been investigated under several disciplines, including planning (motion planning, task planning, etc.), and reinforcement learning. While both of these fields have witnessed tremendous progress, each have fundamental drawbacks: planning approaches require substantial manual engineering in mapping perception to a formal planning problem, while RL, which can operate directly on raw percepts, is data hungry, cannot generalize to new tasks, and is ‘black box’ in nature.
In this talk, we present several studies that aim to mitigate these shortcomings by combining ideas from both planning and learning. We start by introducing value iteration networks, a type of differentiable planner that can be used within model-free RL to obtain better generalization. Next, we consider a practical robotic assembly problem, and show that motion planning, based on readily available CAD data, can be combined with RL to quickly learn policies for assembling tight fitting objects. We conclude with our recent work on learning to imagine goal-directed visual plans. Motivated by humans’ remarkable capability to predict and plan complex manipulations of objects, and recent advances such as GANs in imagining images, we present Visual Plan Imagination (VPI) — a new computational problem that combines image imagination and planning. In VPI, given off-policy image data from a dynamical system, the task is to ‘imagine’ image sequences that transition the system from start to goal. Key to our method is Causal InfoGAN, a deep generative model that can learn features that are compatible with strong planning algorithms. We demonstrate our approach on learning to imagine and execute robotic rope manipulation from image data.