Sequential Manipulation Planning on Scene Graph
This work addresses the challenge of specifying and planning sequential manipulation tasks for robots, though it appears incremental as it builds on existing graph-based representations.
The paper tackled the problem of sequential robot task planning for object rearrangement by introducing a 3D scene graph representation (contact graph+) that abstracts scene layouts and interactions, enabling robots to successfully complete complex tasks that are difficult with conventional methods like PDDL.
We devise a 3D scene graph representation, contact graph+ (cg+), for efficient sequential task planning. Augmented with predicate-like attributes, this contact graph-based representation abstracts scene layouts with succinct geometric information and valid robot-scene interactions. Goal configurations, naturally specified on contact graphs, can be produced by a genetic algorithm with a stochastic optimization method. A task plan is then initialized by computing the Graph Editing Distance (GED) between the initial contact graphs and the goal configurations, which generates graph edit operations corresponding to possible robot actions. We finalize the task plan by imposing constraints to regulate the temporal feasibility of graph edit operations, ensuring valid task and motion correspondences. In a series of simulations and experiments, robots successfully complete complex sequential object rearrangement tasks that are difficult to specify using conventional planning language like Planning Domain Definition Language (PDDL), demonstrating the high feasibility and potential of robot sequential task planning on contact graph.