paper-with-me

홈 › Papers

Transferable Visual Control Policies Through Robot-Awareness

2021-09-29 · ICLR 2022 4 · Edward S. Hu, Kun Huang, Oleh Rybkin, Dinesh Jayaraman

Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. Could we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a “robot-aware control” paradigm that achieves this by exploiting readily available knowledge about the robot. We then instantiate this in a robot-aware model-based RL policy by training modular dynamics models that couple a transferable, robot-agnostic world dynamics module with a robot- specific, potentially analytical, robot dynamics module. This also enables us to set up visual planning costs that separately consider the robot agent and the world. Our experiments on tabletop manipulation tasks with simulated and real robots demonstrate that these plug-in improvements dramatically boost the transferability of visual model-based RL policies, even permitting zero-shot transfer onto new robots for the very first time. Project website: https://sites.google.com/view/rac-iclr22

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

2021-07-19 · Edward S. Hu, Kun Huang, Oleh Rybkin, Dinesh Jayaraman

Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce or even complete…

Model-based Reinforcement LearningTransfer LearningVideo Prediction

Learning Transferable Policies for Monocular Reactive MAV Control

2016-08-01 · Shreyansh Daftry, J. Andrew Bagnell, Martial Hebert

The ability to transfer knowledge gained in previous tasks into new contexts is one of the most important mechanisms of human learning. Despite this, adapting autonomous behavior to be reused in partially similar setting…

Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data

2020-03-03 · Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna 외

Robotic manipulation of deformable 1D objects such as ropes, cables, and hoses is challenging due to the lack of high-fidelity analytic models and large configuration spaces. Furthermore, learning end-to-end manipulation…

Robot ManipulationVisual Reasoning

Scaling simulation-to-real transfer by learning composable robot skills

2018-09-26 · Ryan Julian, Eric Heiden, Zhanpeng He, Hejia Zhang 외

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of di…

Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation

2022-07-05 · Tomoya Yamanokuchi, Yuhwan Kwon, Yoshihisa Tsurumine, Eiji Uchibe 외

Many works have recently explored Sim-to-real transferable visual model predictive control (MPC). However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-r…

Model Predictive Control