RoboNet: A Dataset for Large-Scale Multi-Robot Learning

#News(IoTStack) [ via IoTGroup ]

Headings…
RoboNet: A Dataset for Large-Scale Multi-Robot Learning
Collecting RoboNet
How can we use RoboNet?
Final Thoughts
Comments

Auto extracted Text……

RoboNet: A Dataset for Large-Scale Multi-Robot Learning
Motivated by the success of large-scale data-driven learning, we created RoboNet, an extensible and diverse dataset of robot interaction collected across four different research labs.
Finally, we find that pre-training on RoboNet offers substantial performance gains compared to training from scratch in entirely new environments.
Our goal is to pre-train reinforcement learning models on a sufficiently diverse dataset and then transfer knowledge (either zero-shot or with fine-tuning) to a different test environment.
First, we pre-train visual dynamics models on a subset of data from RoboNet, and then fine-tune them to work in an unseen test environment using a small amount of new data.
The constructed test environments (one of which is visualized below) all include different lab settings, new cameras and viewpoints, held-out robots, and novel objects purchased after data collection concluded.
Note that while Baxters are present in RoboNet that data is not included during model pre-training.
After tuning, we deploy the learned dynamics models in the test environment to perform control tasks – like picking and placing objects – using the visual foresight model based reinforcement learning algorithm.
For the experiments, the target robot and environment was subtracted from RoboNet during pre-training.
In each environment, we use a standard set of benchmark tasks to compare the performance of our pre-trained controller against the performance of a model trained only on data from the new environment.
The results show that the fine-tuned model is ~4x more likely to complete the benchmark task than the one trained without RoboNet. Impressively, the pre-trained models can even slightly outperform models trained from scratch on significantly (5-20x) more data from the test environment

Read More..
AutoTextExtraction by Working BoT using SmartNews 1.02976805238 Build 26 Aug 2019