Optimizing Robotic Placement via Grasp-Dependent Feasibility Prediction

TL;DR

This paper introduces a physics-free, learning-based method to efficiently prioritize grasp and placement candidates in robotic pick-and-place tasks, reducing planning time while maintaining success rates.

Contribution

It proposes a dual-output neural network that predicts grasp feasibility and collision likelihood from inexpensive labels, improving planning efficiency in robotic manipulation.

Findings

Scores transfer effectively to physics-enabled trajectories.

The method reduces planner calls and speeds up successful path finding.

Maintains or improves final success rates with fewer computational resources.

Abstract

In this paper, we study whether inexpensive, physics-free supervision can reliably prioritize grasp-place candidates for budget-aware pick-and-place. From an object's initial pose, target pose, and a candidate grasp, we generate two path-aware geometric labels: path-wise inverse kinematics (IK) feasibility across a fixed approach-grasp-lift waypoint template, and a transit collision flag from mesh sweeps along the same template. A compact dual-output MLP learns these signals from pose encodings, and at test time its scores rank precomputed candidates for a rank-then-plan policy under the same IK gate and planner as the baseline. Although learned from cheap labels only, the scores transfer to physics-enabled executed trajectories: at a fixed planning budget the policy finds successful paths sooner with fewer planner calls while keeping final success on par or better. This work targets a single rigid cuboid with side-face grasps and a fixed waypoint template, and we outline extensions to varied objects and richer waypoint schemes.