Visual closed-loop control for pouring liquids

Schenck, Connor; Fox, Dieter

doi:10.1109/icra.2017.7989307

Cited by 85 publications

(80 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reinforcement learning has been applied to a wide variety of robotic manipulation tasks, including grasping objects [19], in-hand object manipulation [30,38,32,23], manipulating fluids [35], door opening [44,3], and cloth folding [28]. However, applications of RL in the real world require considerable effort to design and evaluate the reward function.…”

Section: Related Workmentioning

confidence: 99%

“…However, applications of RL in the real world require considerable effort to design and evaluate the reward function. For example, using thermal cameras for tracking fluids [35], mocap sensors [21] or computer vision systems [34] for tracking objects, and accelerometers for determining the state of a door [44]. Since such instrumentation needs to be done for any new task that we may wish to learn, it poses a significant bottleneck to widespread adoption of reinforcement learning for robotics, and precludes the use of these methods directly in open-world environments that lack this instrumentation.…”

Section: Related Workmentioning

confidence: 99%

“…However, in order to enable such continual improvement, the robot must have a way to evaluate whether it is succeeding at the task -it needs a reward function. Unfortunately, in practice, the design of reward functions for robotic skills is very challenging, especially when learning skills from raw observations such as images: manually defining reward functions typically requires manually-designed perception systems or instrumentation of the environment (e.g., by placing additional sensors) [34,44,21,35]. This either precludes learning directly in open-world Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

End-To-End Robotic Reinforcement Learning without Reward Engineering

Singh¹,

Yang²,

Hartikainen³

et al. 2019

Robotics: Science and Systems XV

168

View full text Add to dashboard Cite

The combination of deep neural network models and reinforcement learning algorithms can make it possible to learn policies for robotic behaviors that directly read in raw sensory inputs, such as camera images, effectively subsuming both estimation and control into one model. However, realworld applications of reinforcement learning must specify the goal of the task by means of a manually programmed reward function, which in practice requires either designing the very same perception pipeline that end-to-end reinforcement learning promises to avoid, or else instrumenting the environment with additional sensors to determine if the task has been performed successfully. In this paper, we propose an approach for removing the need for manual engineering of reward specifications by enabling a robot to learn from a modest number of examples of successful outcomes, followed by actively solicited queries, where the robot shows the user a state and asks for a label to determine whether that state represents successful completion of the task. While requesting labels for every single state would amount to asking the user to manually provide the reward signal, our method requires labels for only a tiny fraction of the states seen during training, making it an efficient and practical approach for learning skills without manually engineered rewards. We evaluate our method on real-world robotic manipulation tasks where the observations consist of images viewed by the robot's camera. In our experiments, our method effectively learns to arrange objects, place books, and drape cloth, directly from images and without any manually specified reward functions, and with only 1-4 hours of interaction with the real world. Videos of learned behavior are available at sites.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

End-To-End Robotic Reinforcement Learning without Reward Engineering

Singh¹,

Yang²,

Hartikainen³

et al. 2019

Robotics: Science and Systems XV

168

View full text Add to dashboard Cite

show abstract

“…Therefore, the robust and accurate perception will play an essential role in this task, especially in estimating the liquid height in the target container. Recent approaches to solving this perception problem mostly rely on visual sensing [2]- [5]. By leveraging a camera situated in front of the target container, the current liquid height can be regressed from the visual features of the captured image.…”

Section: Introductionmentioning

confidence: 99%

“…However, the mean height errors for ten pours of 3 transparent liquids were larger than 4 mm. Instead of directly predicting the absolute height of liquid, another popular method estimates the input volume of the liquid by analyzing the visual information of the water flow [2]. Schenck et al [2] used a thermal camera to generate pixellevel groundtruth data of heated water using thermal imagery.…”

Section: Introductionmentioning

confidence: 99%

Making Sense of Audio Vibration for Liquid Height Estimation in Robotic Pouring

Liang

Ma³

et al. 2019

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

View full text Add to dashboard Cite

In this paper, we focus on the challenging perception problem in robotic pouring. Most of the existing approaches either leverage visual or haptic information. However, these techniques may suffer from poor generalization performances on opaque containers or concerning measuring precision. To tackle these drawbacks, we propose to make use of audio vibration sensing and design a deep neural network PouringNet to predict the liquid height from the audio fragment during the robotic pouring task. PouringNet is trained on our collected real-world pouring dataset with multimodal sensing data, which contains more than 3000 recordings of audio, force feedback, video and trajectory data of the human hand that performs the pouring task. Each record represents a complete pouring procedure. We conduct several evaluations on PouringNet with our dataset and robotic hardware. The results demonstrate that our PouringNet generalizes well across different liquid containers, positions of the audio receiver, initial liquid heights and types of liquid, and facilitates a more robust and accurate audio-based perception for robotic pouring.

show abstract

Automated System for Pouring and Filtration Tasks in Laboratory Applications

Neubert

Junginger

Roddelkopf

et al. 2021

Chemie Ingenieur Technik

View full text Add to dashboard Cite

Using established needle-and tip-based liquid-handlers partially restricts applications that require the handling of greater sample amounts, options for filtration or handling of liquids with uncommon behavior. In this paper the prototype development of a versatile liquid pouring device (vLiPD) is described, which offers complementary features to usual liquidhandling solutions. For mapping the container characteristics, a geometrical and an on 3D-CAD-model-based approach are introduced and compared. Influences by the liquids' behaviors are compensated by liquid-specific calibration factors.

show abstract

Visual closed-loop control for pouring liquids

Cited by 85 publications

References 27 publications

End-To-End Robotic Reinforcement Learning without Reward Engineering

End-To-End Robotic Reinforcement Learning without Reward Engineering

Making Sense of Audio Vibration for Liquid Height Estimation in Robotic Pouring

Automated System for Pouring and Filtration Tasks in Laboratory Applications

Contact Info

Product

Resources

About