FetchBench: A Simulation Benchmark for Robot Fetching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Beining, Parakh, Meenal, Geng, Derek, Defay, Jack A, Luyang, Gan, Deng, Jia
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913552342712320
author Han, Beining
Parakh, Meenal
Geng, Derek
Defay, Jack A
Luyang, Gan
Deng, Jia
author_facet Han, Beining
Parakh, Meenal
Geng, Derek
Defay, Jack A
Luyang, Gan
Deng, Jia
contents Fetching, which includes approaching, grasping, and retrieving, is a critical challenge for robot manipulation tasks. Existing methods primarily focus on table-top scenarios, which do not adequately capture the complexities of environments where both grasping and planning are essential. To address this gap, we propose a new benchmark FetchBench, featuring diverse procedural scenes that integrate both grasping and motion planning challenges. Additionally, FetchBench includes a data generation pipeline that collects successful fetch trajectories for use in imitation learning methods. We implement multiple baselines from the traditional sense-plan-act pipeline to end-to-end behavior models. Our empirical analysis reveals that these methods achieve a maximum success rate of only 20%, indicating substantial room for improvement. Additionally, we identify key bottlenecks within the sense-plan-act pipeline and make recommendations based on the systematic analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11793
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FetchBench: A Simulation Benchmark for Robot Fetching
Han, Beining
Parakh, Meenal
Geng, Derek
Defay, Jack A
Luyang, Gan
Deng, Jia
Robotics
Fetching, which includes approaching, grasping, and retrieving, is a critical challenge for robot manipulation tasks. Existing methods primarily focus on table-top scenarios, which do not adequately capture the complexities of environments where both grasping and planning are essential. To address this gap, we propose a new benchmark FetchBench, featuring diverse procedural scenes that integrate both grasping and motion planning challenges. Additionally, FetchBench includes a data generation pipeline that collects successful fetch trajectories for use in imitation learning methods. We implement multiple baselines from the traditional sense-plan-act pipeline to end-to-end behavior models. Our empirical analysis reveals that these methods achieve a maximum success rate of only 20%, indicating substantial room for improvement. Additionally, we identify key bottlenecks within the sense-plan-act pipeline and make recommendations based on the systematic analysis.
title FetchBench: A Simulation Benchmark for Robot Fetching
topic Robotics
url https://arxiv.org/abs/2406.11793