One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Yu, Tong; Finn, Chelsea; Xie, Annie; Dasari, Sudeep; Zhang, Tianhao; Abbeel, Pieter; Levine, Sergey

doi:10.48550/arxiv.1802.01557

Cited by 72 publications

(75 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While most prior work on deep visuomotor learning trains a single task in a single domain [7], [8], [9], [10], [11], [12], [13], [14], [15], our goal is not to develop better learning methods, but rather to illustrate how generic multi-domain, multi-task datasets can be used with existing algorithms to boost the generalization of new tasks in new domains. Prior work on multi-task reinforcement learning [5] has shown that data from other tasks can boost generalization of new tasks, however this study is carried out in a single domain.…”

Section: Related Workmentioning

confidence: 99%

“…We provide an overview of the most related datasets in Figure 2. Most existing robot datasets, such as MIME [16], DAML [10], RoboTurk [17], [18], and many others [19], [20], [21], [22], [23], [24], [5] only feature a single domain, making them difficult to use for boosting the generalization in other domains. Merging multiple existing datasets into one multi-domain dataset is difficult due to inconsistencies in data collection protocols, time discretization, robot morphologies, and sensors.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

Ebert¹,

Yang²,

Schmeckpeper³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Robot learning holds the promise of learning policies that generalize broadly. However, such generalization requires sufficiently diverse datasets of the task of interest, which can be prohibitively expensive to collect. In other fields, such as computer vision, it is common to utilize shared, reusable datasets, such as ImageNet, to overcome this challenge, but this has proven difficult in robotics. In this paper, we ask: what would it take to enable practical data reuse in robotics for end-to-end skill learning? We hypothesize that the key is to use datasets with multiple tasks and multiple domains, such that a new user that wants to train their robot to perform a new task in a new domain can include this dataset in their training process and benefit from cross-task and cross-domain generalization. To evaluate this hypothesis, we collect a large multi-domain and multi-task dataset, with 7,200 demonstrations constituting 71 tasks across 10 environments, and empirically study how this data can improve the learning of new tasks in new environments. We find that jointly training with the proposed dataset and 50 demonstrations of a never-before-seen task in a new domain on average leads to a 2x improvement in success rate compared to using target domain data alone. We also find that data for only a few tasks in a new domain can bridge the domain gap and make it possible for a robot to perform a variety of prior tasks that were only seen in other domains. These results suggest that reusing diverse multi-task and multi-domain datasets, including our open-source dataset, may pave the way for broader robot generalization, eliminating the need to re-collect data for each new robot learning project.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

Ebert¹,

Yang²,

Schmeckpeper³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The trajectories are recorded using either kinesthetic teaching [56] or teleoperation [57]. Follow-up papers [58], [55] adopt deep learning approaches to solve the task. Similarly, Yu et al [58] teach the robot to perform tasks from a demonstration video.…”

Section: B Model-free Graspingmentioning

confidence: 99%

“…Follow-up papers [58], [55] adopt deep learning approaches to solve the task. Similarly, Yu et al [58] teach the robot to perform tasks from a demonstration video. In this work, the robot policy is directly predicted from hidden layers of the network.…”

Section: B Model-free Graspingmentioning

confidence: 99%

DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstration

Wang¹,

Manhardt²,

Minciullo³

et al. 2021

Preprint

View full text Add to dashboard Cite

The ability to successfully grasp objects is crucial in robotics, as it enables several interactive downstream applications. To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set of grasping points. While the former approaches do not scale well to multiple object instances or classes yet, the latter require large annotated datasets and are hampered by their poor generalization capabilities to new geometries. To overcome these shortcomings, we propose to teach a robot how to grasp an object with a simple and short human demonstration. Hence, our approach neither requires many annotated images nor is it restricted to a specific geometry. We first present a small sequence of RGB-D images displaying a human-object interaction. This sequence is then leveraged to build associated hand and object meshes that represent the depicted interaction. Subsequently, we complete missing parts of the reconstructed object shape and estimate the relative transformation between the reconstruction and the visible object in the scene. Finally, we transfer the a-priori knowledge from the relative pose between object and human hand with the estimate of the current object pose in the scene into necessary grasping instructions for the robot. Exhaustive evaluations with Toyota's Human Support Robot (HSR) in real and synthetic environments demonstrate the applicability of our proposed methodology and its advantage in comparison to previous approaches.

show abstract

“…Hand-designed unsupervised losses have been used to adapt to distribution shifts with rotation-prediction [47] or entropyminimization [53], as well as to encode inductive biases [3]. Unsupervised losses have also been metalearned for learning to encode human demonstrations [57], few-shot learning exploiting unsupervised information [31,4], and learning to adapt to group distribution shifts [58]. In contrast, our unsupervised loss only takes the single query we care about, thus imposing no additional assumptions on top of standard prediction problems, and takes the form of a conservation law for predicted sequences.…”

Section: Related Workmentioning

confidence: 99%

Noether Networks: Meta-Learning Useful Conserved Quantities

Alet¹,

Doblar²,

Zhou³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on sequential prediction problems and take inspiration from Noether's theorem to reduce the problem of finding inductive biases to meta-learning useful conserved quantities. We propose Noether Networks: a new type of architecture where a meta-learned conservation loss is optimized inside the prediction function. We show, theoretically and experimentally, that Noether Networks improve prediction quality, providing a general framework for discovering inductive biases in sequential problems.

show abstract

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Cited by 72 publications

References 36 publications

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstration

Noether Networks: Meta-Learning Useful Conserved Quantities

Contact Info

Product

Resources

About