Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics.
In this paper we define criteria for industry-oriented DRL, and perform a thorough comparison according to these criteria of one family of learning approaches, DRL from demonstration, against a professional industrial integrator on the recently established NIST assembly benchmark.
no code implementations • 30 Sep 2020 • Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz
In this work we advocate semantic 3D keypoints as a visual representation, and present a semi-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision.
This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy Gradient when trained on a latent image embedding.
1 code implementation • 26 Sep 2019 • Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott Reed, Rae Jeong, Konrad Zolna, Yusuf Aytar, David Budden, Mel Vecerik, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
We propose Generative Predecessor Models for Imitation Learning (GPRIL), a novel imitation learning algorithm that matches the state-action distribution to the distribution observed in expert demonstrations, using generative models to reason probabilistically about alternative histories of demonstrated states.
Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing.
We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards.
The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills.