no code implementations • 13 Sep 2022 • David Watkins-Valls, Peter Allen, Krzysztof Choromanski, Jacob Varley, Nicholas Waytowich
We propose the Multiple View Performer (MVP) - a new architecture for 3D shape completion from a series of temporally sequential views.
no code implementations • 16 Mar 2022 • Sumeet Singh, Francis McCann Ramirez, Jacob Varley, Andy Zeng, Vikas Sindhwani
Though robot learning is often formulated in terms of discrete-time Markov decision processes (MDPs), physical robots require near-continuous multiscale feedback control.
no code implementations • 16 Apr 2021 • Dmitry Kalashnikov, Jacob Varley, Yevgen Chebotar, Benjamin Swanson, Rico Jonschkowski, Chelsea Finn, Sergey Levine, Karol Hausman
In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks.
no code implementations • 26 Mar 2021 • Iretiayo Akinola, Anelia Angelova, Yao Lu, Yevgen Chebotar, Dmitry Kalashnikov, Jacob Varley, Julian Ibarz, Michael S. Ryoo
We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs.
no code implementations • 28 Dec 2020 • Alberto Camacho, Jacob Varley, Deepali Jain, Atil Iscen, Dmitry Kalashnikov
In this work we augment a Deep Q-Learning agent with a Reward Machine (DQRM) to increase speed of learning vision-based policies for robot tasks, and overcome some of the limitations of DQN that prevent it from converging to good-quality policies.
no code implementations • NeurIPS 2020 • Krzysztof M. Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani
We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d).
no code implementations • NeurIPS 2020 • Krzysztof Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani
We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d).
no code implementations • 21 Feb 2020 • Iretiayo Akinola, Jacob Varley, Dmitry Kalashnikov
In this work, we present an effective multi-view approach to closed-loop end-to-end learning of precise manipulation tasks that are 3D in nature.
no code implementations • 10 Sep 2019 • Bohan Wu, Iretiayo Akinola, Jacob Varley, Peter Allen
When this methodology is used to realize grasps from coarse initial positions provided by a vision-only planner, the system is made dramatically more robust to calibration errors in the camera-robot transform.
1 code implementation • 29 Jun 2018 • Iretiayo Akinola, Jacob Varley, Boyuan Chen, Peter K. Allen
This framework greatly improves the performance of standard online grasp planning algorithms by incorporating a notion of reachability into the online grasp planning process.
Robotics
1 code implementation • 20 Mar 2018 • Jacob Varley, David Watkins-Valls, Peter Allen
At runtime, the network is provided a partial view of an object and tactile information is acquired to augment the captured depth information.
Robotics
no code implementations • 27 Sep 2016 • Jacob Varley, Chad DeChant, Adam Richardson, Joaquín Ruales, Peter Allen
At runtime, a 2. 5D pointcloud captured from a single point of view is fed into the CNN, which fills in the occluded regions of the scene, allowing grasps to be planned and executed on the completed object.
Robotics