ReorientBot: Learning Object Reorientation for Specific-Posed Placement

TL;DR

ReorientBot is a vision-based robotic system that learns to reorient objects into specific poses efficiently, combining perception, learned waypoint selection, and traditional motion planning, achieving high success rates in simulation and real-world tests.

Contribution

The paper introduces ReorientBot, a novel system that integrates learned waypoint selection with traditional motion planning for effective object reorientation.

Findings

Achieves 93% success rate in object reorientation tasks.

81% improvement in success rate over heuristic methods.

22% faster execution time compared to baseline approaches.

Abstract

Robots need the capability of placing objects in arbitrary, specific poses to rearrange the world and achieve various valuable tasks. Object reorientation plays a crucial role in this as objects may not initially be oriented such that the robot can grasp and then immediately place them in a specific goal pose. In this work, we present a vision-based manipulation system, ReorientBot, which consists of 1) visual scene understanding with pose estimation and volumetric reconstruction using an onboard RGB-D camera; 2) learned waypoint selection for successful and efficient motion generation for reorientation; 3) traditional motion planning to generate a collision-free trajectory from the selected waypoints. We evaluate our method using the YCB objects in both simulation and the real world, achieving 93% overall success, 81% improvement in success rate, and 22% improvement in execution time compared to a heuristic approach. We demonstrate extended multi-object rearrangement showing the general capability of the system.