PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning
This addresses robotic manipulation planning with constraints like kinematics and collisions, representing an incremental advance in integrating symbolic and sampling-based methods.
The authors tackled the problem of planning with complex constraints in high-dimensional continuous spaces by extending PDDL to support blackbox samplers, developing algorithms that reduce these problems to finite PDDL sequences and balance exploration-exploitation. They demonstrated effectiveness on simulated robotic domains and real-world tasks, achieving improved solution times and cost optimization.
Many planning applications involve complex relationships defined on high-dimensional, continuous variables. For example, robotic manipulation requires planning with kinematic, collision, visibility, and motion constraints involving robot configurations, object poses, and robot trajectories. These constraints typically require specialized procedures to sample satisfying values. We extend PDDL to support a generic, declarative specification for these procedures that treats their implementation as black boxes. We provide domain-independent algorithms that reduce PDDLStream problems to a sequence of finite PDDL problems. We also introduce an algorithm that dynamically balances exploring new candidate plans and exploiting existing ones. This enables the algorithm to greedily search the space of parameter bindings to more quickly solve tightly-constrained problems as well as locally optimize to produce low-cost solutions. We evaluate our algorithms on three simulated robotic planning domains as well as several real-world robotic tasks.