robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Zhu, Yuke; Wong, Josiah; Mandlekar, Ajay; Martí­n-Martí­n, Roberto

doi:10.48550/arxiv.2009.12293

Cited by 79 publications

(113 citation statements)

References 15 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…Thanks to the recent progress of physics simulation (Todorov et al 2012;Coumans and Bai 2016;Erez et al 2015), it has drawn increasing interest to build full-physics robot simulation environment (Urakami et al 2019;Tunyasuvunakool et al 2020;Zhu et al 2020;James et al 2020;Mu et al 2021). Compared to robot simulation with abstract action (Kolve et al 2017;Savva et al 2019;, full-physic robot simulation supports low-level policy learning that could be transferred to real world.…”

Section: Robot Simulationmentioning

confidence: 99%

Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation

Zhang¹,

Chen²,

Xiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of the sensors, we designed a fully physics-grounded simulation pipeline, which includes material acquisition, ray tracing based infrared (IR) image rendering, IR noise simulation, and depth estimation. The pipeline is able to generate depth maps with material-dependent error patterns similar to a real depth sensor. We conduct extensive experiments to show that perception algorithms and reinforcement learning policies trained in our simulation platform could transfer well to real world test cases without any fine-tuning. Furthermore, due to the high degree of realism of this simulation, our depth sensor simulator can be used as a convenient testbed to evaluate the algorithm performance in the real world, which will largely reduce the human effort in developing robotic algorithms. The entire pipeline has been integrated into the SAPIEN simulator and is open-sourced to promote the research of vision and robotics communities.

show abstract

Section: Robot Simulationmentioning

confidence: 99%

Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation

Zhang¹,

Chen²,

Xiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…RLDS stores sequences of steps where each step contains several fields. To select the set of fields, we looked at classical sources [41], common environment suites [8,33,49], existing datasets [15,19] and common RL frameworks [23,18]. The fields that are included for each step are:…”

Section: Dataset Structurementioning

confidence: 99%

“…At the moment of submitting this paper, the following datasets (compatible with RLDS) are in TFDS 7 : a subset of D4RL [15] with tasks from Gym Mujoco [8] and Adroit [37]; the RLUnplugged [19] DMLab [6], Atari [7] and RWRL [13] datasets [19]; two Robosuite [49] datasets generated with the RLDS tools.…”

Section: Sharingmentioning

confidence: 99%

“…We release two sample datasets on the PickPlaceCan environment of the Robosuite robotic arm simulator [49] to illustrate the capabilities of the RLDS ecosystem, from recording datasets using the EnvLogger or the RLDS Creator interface, up to sharing and processing. Those datasets are not meant to supersede previously released datasets [31] but rather demonstrate the different functionalities of RLDS.…”

Section: Sharingmentioning

confidence: 99%

“…• We add some of the popular RL datasets [19,15] to TFDS in RLDS format, making them easy to consume with RLDS. • We exemplify the full RLDS ecosystem by releasing two new datasets on the Robosuite [49] robotic environment, one gathering synthetic demonstrations recorded with EnvLogger and one with human demonstrations recorded with RLDS Creator. • We release three Notebooks (see Sec.7) exemplifying the usage of the RLDS library.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning

Ramos¹,

Girgin²,

Hussenot³

et al. 2021

Preprint

View full text Add to dashboard Cite

We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (SDM) including Reinforcement Learning (RL), Learning from Demonstrations, Offline RL or Imitation Learning. RLDS enables not only reproducibility of existing research and easy generation of new datasets, but also accelerates novel research. By providing a standard and lossless format of datasets it enables to quickly test new algorithms on a wider range of tasks. The RLDS ecosystem makes it easy to share datasets without any loss of information and to be agnostic to the underlying original format when applying various data processing pipelines to large collections of datasets. Besides, RLDS provides tools for collecting data generated by either synthetic agents or humans, as well as for inspecting and manipulating the collected data. Ultimately, integration with TFDS [3] facilitates the sharing of RL datasets with the research community.

show abstract

Research on Network Information Security Risk Assessment Based on Artificial Intelligence

Wang

2021

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as examples respectively from two categories (positive vs. negative) and the policy is then expected to produce trajectories that are indistinguishable from the expert demonstrations. But in the real world, the collected expert demonstrations are more likely to be imperfect, where only an unknown fraction of the demonstrations are optimal. Instead of treating imperfect expert demonstrations as absolutely positive or negative, we investigate unlabeled imperfect expert demonstrations as they are. A positive-unlabeled adversarial imitation learning algorithm is developed to dynamically sample expert demonstrations that can well match the trajectories from the constantly optimized agent policy. The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations. Theoretical analysis shows that our method learns from the imperfect demonstrations via a self-paced way. Experimental results on MuJoCo and Robo-Suite platforms demonstrate the effectiveness of our method from different aspects.

show abstract

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Cited by 79 publications

References 15 publications

Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation

Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation

RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning

Research on Network Information Security Risk Assessment Based on Artificial Intelligence

Contact Info

Product

Resources

About