Sequential Topological Representations for Predictive Models of Deformable Objects
This work provides a method for robots to better understand and predict the behavior of highly deformable objects, which is a significant problem for robotic manipulation.
This paper addresses the challenge of robotic manipulation of deformable objects by creating compact topological representations to capture their state and track its evolution over time. The authors developed predictive models that take past point cloud observations and predict future topological states conditioned on control actions, achieving more precise results than computational topology libraries in simulation.
Deformable objects present a formidable challenge for robotic manipulation due to the lack of canonical low-dimensional representations and the difficulty of capturing, predicting, and controlling such objects. We construct compact topological representations to capture the state of highly deformable objects that are topologically nontrivial. We develop an approach that tracks the evolution of this topological state through time. Under several mild assumptions, we prove that the topology of the scene and its evolution can be recovered from point clouds representing the scene. Our further contribution is a method to learn predictive models that take a sequence of past point cloud observations as input and predict a sequence of topological states, conditioned on target/future control actions. Our experiments with highly deformable objects in simulation show that the proposed multistep predictive models yield more precise results than those obtained from computational topology libraries. These models can leverage patterns inferred across various objects and offer fast multistep predictions suitable for real-time applications.