LDHP: Library-Driven Hierarchical Planning for Non-prehensile Dexterous Manipulation

Abstract

Non-prehensile manipulation is essential for handling thin, large, or otherwise ungraspable objects in unstructured settings. Prior planning and search-based methods often rely on ad-hoc manual designs or generate physically unrealizable motions by ignoring critical gripper properties, while training-based approaches are data-intensive and struggle to generalize to novel, out-of-distribution tasks. We propose a library-driven hierarchical planner (LDHP) that makes executability a first-class design goal: a top-tier contact-state planner proposes object-pose paths using MoveObject primitives, and a bottom-tier grasp planner synthesizes feasible grasp sequences with AdjustGrasp primitives; feasibility is certified by collision checks and quasi-static mechanics, and contact-sensitive segments are recovered via a bounded dichotomy refinement. This gripper-aware decomposition decouples object motion from grasp realizability, yields a task-agnostic pipeline that transfers across manipulation tasks and geometric variations without re-design, and exposes clean hooks for optional learned priors. Real-robot studies on zero-mobility lifting and slot insertion demonstrate consistent execution and robustness to shape and environment changes.

Figures (7)

• Figure 1: (a) A representative non-prehensile scenario where a block must be lifted from the table edge with no finger clearance; (b) LDHP synthesize an executable plan; example snapshots illustrate the primitive sequence.
• Figure 2: Problem formulation. A rigid object $\mathcal{O}$ with initial pose $T_0$ is placed inside a static environment $\mathcal{E}$ and manipulated by a parallel-jaw gripper $\mathcal{G}$. The task is to compute a feasible sequence of non-prehensile motion primitives that moves the object to the goal pose $T_g$.
• Figure 3: System overview. From left to right: inputs (environment $\mathcal{E}$, gripper $\mathcal{G}$, object model $\mathcal{O}$, and initial/goal poses $T_0,T_g$); the hierarchical framework that (top tier) generates an object-pose plan using MoveObject primitives and (bottom tier) generates a grasp plan using AdjustGrasp primitives; and execution of the resulting plan on the robot.
• Figure 4: Gripper configurations used in this work. (a--b) Configuration I: two-finger gripper with cylindrical flanks, modeled as a two-point contact abstraction with fixed inter-finger distance. (c--d) Configuration II: cuboid fingertips represented by polyline contours. A grasp is valid only if a collision-free gripper pose exists for approach/retreat and for any required regrasp under opening-width limits.
• Figure 5: Visualization of MoveObject and AdjustGrasp primitives.