Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Zhang, Tianhao; McCarthy, Zoe; Jowl, Owen; Lee, Dennis; Chen, Xi; Goldberg, Ken; Abbeel, Pieter

doi:10.1109/icra.2018.8461249

Cited by 411 publications

(314 citation statements)

References 42 publications

Supporting

Mentioning

310

Contrasting

Unclassified

Order By: Relevance

“…In this work we concentrate on the former. The majority of work in behaviour cloning operates on a set of configuration-space trajectories that can be collected via tele-operation [15], [16], kinesthetic teaching [17], [18], sensors on a human demonstrator [19], [20], [21], [22], through motion planners [5], or even by observing humans directly. Expanding further on the latter, learning by observing humans has previously been achieved through hand-designed mappings between human actions and robot actions [1], [2], [23], visual activity recognition and explicit handtracking [24], [25], and more recently by a system that infers actions from a single video of a human via an end-toend trained system [4].…”

Section: Related Workmentioning

confidence: 99%

Learning One-Shot Imitation From Humans Without Humans

Bonardi

James

Davison

2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Humans can naturally learn to execute a new task by seeing it performed by other individuals once, and then reproduce it in a variety of configurations. Endowing robots with this ability of imitating humans from third person is a very immediate and natural way of teaching new tasks. Only recently, through meta-learning, there have been successful attempts to one-shot imitation learning from humans; however, these approaches require a lot of human resources to collect the data in the real world to train the robot. But is there a way to remove the need for real world human demonstrations during training? We show that with Task-Embedded Control Networks, we can infer control polices by embedding human demonstrations that can condition a control policy and achieve one-shot imitation learning. Importantly, we do not use a real human arm to supply demonstrations during training, but instead leverage domain randomisation in an application that has not been seen before: sim-to-real transfer on humans. Upon evaluating our approach on pushing and placing tasks in both simulation and in the real world, we show that in comparison to a system that was trained on real-world data we are able to achieve similar results by utilising only simulation data. Videos can be found here * .

show abstract

Section: Related Workmentioning

confidence: 99%

Learning One-Shot Imitation From Humans Without Humans

Bonardi

James

Davison

2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…A comparison of various control interfaces shows that general purpose hardware is deficient while special purpose hardware is more accurate but is not widely available [19,26]. Virtual reality-based free-space controllers have recently been proposed both for data collection [23,39] and policy learning [40,43]. While these methods have shown the utility of data, they do not provide a seamlessly scalable data collection mechanism.…”

Section: Related Workmentioning

confidence: 99%

“…While these methods have shown the utility of data, they do not provide a seamlessly scalable data collection mechanism. Often the data is either collected locally or requires a powerful local client computer, to render the high definition sensor stream to a VR headset [39,43]. The use of VR hardware and requirement of client-side compute resources has limited the deployment of these interfaces on crowdsourcing platforms.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity

Mandlekar

Booher

Spero

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Large, richly annotated datasets have accelerated progress in fields such as computer vision and natural language processing, but replicating these successes in robotics has been challenging. While prior data collection methodologies such as self-supervision have resulted in large datasets, the data can have poor signal-to-noise ratio. By contrast, previous efforts to collect task demonstrations with humans provide better quality data, but they cannot reach the same data magnitude. Furthermore, neither approach places guarantees on the diversity of the data collected, in terms of solution strategies. In this work, we leverage and extend the RoboTurk platform to scale up data collection for robotic manipulation using remote teleoperation. The primary motivation for our platform is two-fold: (1) to address the shortcomings of prior work and increase the total quantity of manipulation data collected through human supervision by an order of magnitude without sacrificing the quality of the data and (2) to collect data on challenging manipulation tasks across several operators and observe a diverse set of emergent behaviors and solutions. We collected over 111 hours of robot manipulation data across 54 users and 3 challenging manipulation tasks in 1 week, resulting in the largest robot dataset collected via remote teleoperation. We evaluate the quality of our platform, the diversity of demonstrations in our dataset, and the utility of our dataset via quantitative and qualitative analysis. For additional results, supplementary videos, and to download our dataset, visit roboturk.stanford.edu/realrobotdataset

show abstract

“…liuboyi17@mails.ucas.edu.cn; lj.wang1@siat.ac.cn 2 Ming liu is with Department of ECE, Hong Kong University of Science and Technology. eelium@ust.hk 3 Boyi liu is also with the University of Chinese Academy of Sciences. 4 Cheng-Zhong Xu is with the University of Macau.…”

Section: Introductionmentioning

confidence: 99%

Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data

Liu

Wang

Liu

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue, we present a novel framework named FIL. It provides a heterogeneous knowledge fusion mechanism for cloud robotic systems. Then, a knowledge fusion algorithm in FIL is proposed. It enables the cloud to fuse heterogeneous knowledge from local robots and generate guide models for robots with service requests. After that, we introduce a knowledge transfer scheme to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and efficiency. Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a self-driving task for robots (cars). The experimental results demonstrate that the shared model generated by FIL increases imitation learning efficiency of local robots in cloud robotic systems.

show abstract

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Cited by 411 publications

References 42 publications

Learning One-Shot Imitation From Humans Without Humans

Learning One-Shot Imitation From Humans Without Humans

Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity

Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data

Contact Info

Product

Resources

About