Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration

Rahmatizadeh, Rouhollah; Abolghasemi, Pooya; Bölöni, Ladislau; Levine, Sergey

doi:10.48550/arxiv.1707.02920

Cited by 9 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Boularias et al [1], Finn et al [6]), or, as in our case, via adversarial learning [15]. When expert actions or expert policies are available, behavioral cloning can be used (Rahmatizadeh et al [36], James et al [17], Duan et al [5]). Alternatively, expert trajectories can be used as additional training data for off-policy algorithms such as DPG (e.g.…”

Section: Related Workmentioning

confidence: 99%

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Zhu¹,

Wang²,

Merel³

et al. 2018

Robotics: Science and Systems XIV

201

115

View full text Add to dashboard Cite

We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or imitation learning alone. We also illustrate that these policies, trained with large visual and dynamics variations, can achieve preliminary successes in zero-shot sim2real transfer. A brief visual description of this work can be viewed in this video.

show abstract

Section: Related Workmentioning

confidence: 99%

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Zhu¹,

Wang²,

Merel³

et al. 2018

Robotics: Science and Systems XIV

201

115

View full text Add to dashboard Cite

show abstract

“…Kinesthetic teaching is not intuitive and can result in unwanted visual artifacts [9], [11]. Using motion capture devices for teleoperation, such as [37], is more intuitive and can solve this issue. However, the human teacher typically observes the scene through a different angle from the robot, which may render certain objects only visible to the human or the robot (due to occlusions), making imitation challenging.…”

mentioning

confidence: 99%

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Zhang

McCarthy

Jowl

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

461

310

View full text Add to dashboard Cite

Imitation learning is a powerful paradigm for robot skill acquisition. However, obtaining demonstrations suitable for learning a policy that maps from raw pixels to actions can be challenging. In this paper we describe how consumergrade Virtual Reality headsets and hand tracking hardware can be used to naturally teleoperate robots to perform complex tasks. We also describe how imitation learning can learn deep neural network policies (mapping from pixels to actions) that can acquire the demonstrated skills. Our experiments showcase the effectiveness of our approach for learning visuomotor skills.

show abstract

“…Prior work has shown that robots can acquire a range of complex skills through demonstration, such as table tennis [28], lane following [34], pouring water [31], drawer opening [38], and multi-stage manipulation tasks [62]. However, the most effective methods for robot imitation differ significantly from how humans and animals might imitate behaviors: while robots typically need to receive demonstrations in the form of kinesthetic teaching [32,1] or teleoperation [8,35,62], humans and animals can acquire the gist of a behavior simply by watching someone else. In fact, we can adapt to variations in morphology, context, and task details effortlessly, compensating for whatever domain shift may be present and recovering a skill that we can use in new situations [6].…”

Section: Introductionmentioning

confidence: 99%

“…1 II. RELATED WORK Most imitation learning and learning from demonstration methods operate at the level of configuration-space trajectories [44,2], which are typically collected using kinesthetic teaching [32,1], teleoperation [8,35,62], or sensors on the demonstrator [11,9,7,21]. Instead, can we allow robots to imitate just by watching the demonstrator perform the task?…”

Section: Introductionmentioning

confidence: 99%

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

Finn

Xie

et al. 2018

Robotics: Science and Systems XIV

Self Cite

223

192

View full text Add to dashboard Cite

Abstract-Humans and animals are capable of learning a new behavior by observing others perform the skill just once. We consider the problem of allowing a robot to do the same -learning from a video of a human, even when there is domain shift in the perspective, environment, and embodiment between the robot and the observed human. Prior approaches to this problem have hand-specified how human and robot actions correspond and often relied on explicit human pose detection systems. In this work, we present an approach for one-shot learning from a video of a human by using human and robot demonstration data from a variety of previous tasks to build up prior knowledge through meta-learning. Then, combining this prior knowledge and only a single video demonstration from a human, the robot can perform the task that the human demonstrated. We show experiments on both a PR2 arm and a Sawyer arm, demonstrating that after meta-learning, the robot can learn to place, push, and pick-andplace new objects using just one video of a human performing the manipulation.

show abstract

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration

Cited by 9 publications

References 0 publications

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

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

Contact Info

Product

Resources

About