Robotic Pick-and-Place With Uncertain Object Instance Segmentation and Shape Completion

TL;DR

This paper presents a robotic pick-and-place method that models uncertain object geometries using shape completion and incorporates this uncertainty into a regrasp planner, improving packing success rates.

Contribution

It introduces a novel cost function for regrasp planning that accounts for perceptual uncertainty using neural networks, outperforming traditional methods.

Findings

Neural network-based cost outperforms uncertainty-unaware costs.

Incorporating uncertainty improves packing success by 7.8%.

Method is faster than Monte Carlo sampling.

Abstract

We consider robotic pick-and-place of partially visible, novel objects, where goal placements are non-trivial, e.g., tightly packed into a bin. One approach is (a) use object instance segmentation and shape completion to model the objects and (b) use a regrasp planner to decide grasps and places displacing the models to their goals. However, it is critical for the planner to account for uncertainty in the perceived models, as object geometries in unobserved areas are just guesses. We account for perceptual uncertainty by incorporating it into the regrasp planner's cost function. We compare seven different costs. One of these, which uses neural networks to estimate probability of grasp and place stability, consistently outperforms uncertainty-unaware costs and evaluates faster than Monte Carlo sampling. On a real robot, the proposed cost results in successfully packing objects tightly into a bin 7.8% more often versus the commonly used minimum-number-of-grasps cost.