We propose a deep visuo-tactile model for realtime estimation of the liquid inside a deformable container in a proprioceptive way.We fuse two sensory modalities, i.e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor without any extra sensor calibrations.The robotic system is well controlled and adjusted based on the estimation model in real time. The main contributions and novelties of our work are listed as follows: 1) Explore a proprioceptive way for liquid volume estimation by developing an end-to-end predictive model with multi-modal convolutional networks, which achieve a high precision with an error of around 2 ml in the experimental validation. 2) Propose a multi-task learning architecture which comprehensively considers the losses from both classification and regression tasks, and comparatively evaluate the performance of each variant on the collected data and actual robotic platform. 3) Utilize the proprioceptive robotic system to accurately serve and control the requested volume of liquid, which is continuously flowing into a deformable container in real time. 4) Adaptively adjust the grasping plan to achieve more stable grasping and manipulation according to the real-time liquid volume prediction.

Tuesday of this past week was quite fortuitous: In my Data Science Cohort at Lambda School, we are working a predictive maintenance competition on Kaggle regarding Water pumps in Tanzania. And, I went to a Data Science networking event at a defense contractor who spoke of the importance of Predictive Maintenance Solutions -- in their case, they were predicting the failure rates of parts of the F35 Joint Strike Fighter. According to IoT world, The Predictive Maintenance report forecasts a compound annual growth rate for Predictive Maintenance of 39% between 2016–2022, with annual technology spending reaching US$10.96 This has a large positive impact on Data Science and Machine Learning if the industry can keep up with the needs of predictive maintenance problems. What is predictive maintenance and why is it so important to different domains?

Picture a scenario in which flow-rate sensors in a water pump inside a car's engine detect a drop in water pressure. The sensor information would be automatically transmitted to a local service center via a telematics link. The service center would be tasked with deciding whether the water pump needs to be replaced, and with connecting into the car manufacturer's service portal. There, the service center would gain access to a machine-learning platform that examines a combination of factors, including historical information. That data would help the service technician determine when the water pump is likely to fail.

In this article, we look at two machine learning (ML) techniques, Naive Bayes classifier and neural networks, and demystify how they work. With all the hype surrounding self-driving cars and video-game-playing AI robots, it's worth taking a step back and reminding ourselves how machine learning programs actually "learn". In this article, we look at two machine learning (ML) techniques–spam filters and neural networks–and demystify how they work. And if you're not sure what machine learning even is, read about the difference between artificial intelligence, machine learning, and deep learning. One common machine learning algorithm is the Naive Bayes classifier, which is used for filtering spam emails.