Benchmarking Simulated Robotic Manipulation Through a Real World Dataset
Benchmarking Simulated Robotic Manipulation Through a Real World Dataset
复制标题
DOI：
10.1109/lra.2019.2953663
复制
发表时间：
2020-01-01
影响因子：
5.2
通讯作者：
Leitner, Jurgen
中科院分区：
文献类型：
--
作者：
Collins, Jack;McVicar, Jessie;Leitner, Jurgen
我们提出了一个基准，以促进模拟操作，试图克服物理基准的障碍，通过分布一个真实的世界，地面实况数据集。用户被给予各种模拟操作任务，所述任务具有复制所记录的数据集的真实的结果的目标的分配的协议。该基准包含一系列用于验证提交的环境的成功的指标，同时提供对其缺陷的洞察。我们将我们的基准应用于两个仿真环境，即，PyBullet和V-Rep，并发布结果。基准测试环境所需的所有材料，包括协议和数据集，都可以在基准测试网站上找到（1）。
We present a benchmark to facilitate simulated manipulation; an attempt to overcome the obstacles of physical benchmarks through the distribution of a real world, ground truth dataset. Users are given various simulated manipulation tasks with assigned protocols having the objective of replicating the real world results of a recorded dataset. The benchmark comprises of a range of metrics used to characterise the successes of submitted environments whilst providing insight into their deficiencies. We apply our benchmark to two simulation environments, i.e., PyBullet and V-Rep, and publish the results. All materials required to benchmark an environment, including protocols and the dataset, can be found at the benchmarks' website(1).