AI News, New robots can see into their future
- On Sunday, June 3, 2018
- By Read More
New robots can see into their future
Using this technology, called visual foresight, the robots can predict what their cameras will see if they perform a particular sequence of movements.
Recent improvements to this class of models, as well as greatly improved planning capabilities, have enabled robotic control based on video prediction to perform increasingly complex tasks, such as sliding toys around obstacles and repositioning multiple objects.
We have shown that it possible to build a robotic system that also leverages large amounts of autonomously collected data to learn widely applicable manipulation skills, specifically object pushing skills,' said Frederik Ebert, a graduate student in Levine's lab who worked on the project.
In contrast to conventional computer vision methods, which require humans to manually label thousands or even millions of images, building video prediction models only requires unannotated video, which can be collected by the robot entirely autonomously.
'The capabilities of this robot are still limited, but its skills are learned entirely automatically, and allow it to predict complex physical interactions with objects that it has never seen before by building on previously observed patterns of interaction.'
The Berkeley scientists are continuing to research control through video prediction, focusing on further improving video prediction and prediction-based control, as well as developing more sophisticated methods by which robots can collected more focused video data, for complex tasks such as picking and placing objects and manipulating soft and deformable objects such as cloth or rope, and assembly.
- On Tuesday, June 25, 2019
Vestri the robot imagines how to perform tasks
UC Berkeley researchers have developed a robotic learning technology that enables robots to imagine the future of their actions so they can figure out how to ...
Robots learn Grasping by sharing their hand-eye coordination experience with each other | QPT
A human child is able to reliably grasp objects after one year, and takes around four years to acquire more sophisticated precision grasps. However, networked ...
What do advancements in AI mean for the military? Military robotics has come a long way with advancements in machine learning, the soaring affordability of ...
Predict Function - Artificial Intelligence for Robotics
This video is part of an online course, Intro to Artificial Intelligence. Check out the course here:
Retouching Photos with Machine Learning, GE and China, and MIT Giving Robots the Sense of Touch
GalcoTV Industry Update - The latest news in electronics, automation and robotics! In this week's industry news update we're talking about Retouching Photos ...
A Multimodal Dataset for Object Model Learning from Natural Human-Robot Interaction
A Multimodal Dataset for Object Model Learning from Natural Human-Robot Interaction submitted to the IROS 2017.
10 Amazing Robots That Will Change the World
The day of living like the Jetsons, mechanized maid and all, gets closer all the time. Here are 10 great robots, some of which are even available to the public.
Robot learns, thinks and acts by itself #DigInfo
DigInfo TV - 28/7/2011 Tokyo Institute of Technology Intelligent humanoid robot capable of learning and decision-making in a real environment
Robot catching flying object
Learning Algorithms and Systems Laboratory(LASA) of EPFL proposes a Programming by Demonstration (PbD) approach to learn how to catch robustly objects ...
Intrinsically Motivated Goal Exploration Processes for Open-Ended Robot Learning
Intrinsically Motivated Multi-Task Reinforcement Learning with open-source Explauto library and Poppy Humanoid Robot Sébastien Forestier, Yoan Mollard, ...