Search Results for author: Jeffrey Ichnowski

Found 21 papers, 4 papers with code

Residual-NeRF: Learning Residual NeRFs for Transparent Object Manipulation

no code implementations10 May 2024 Bardienus P. Duisterhof, Yuemin Mao, Si Heng Teng, Jeffrey Ichnowski

In this work, we propose Residual-NeRF, a method to improve depth perception and training speed for transparent objects.

Object Transparent objects

MD-Splatting: Learning Metric Deformation from 4D Gaussians in Highly Deformable Scenes

no code implementations30 Nov 2023 Bardienus P. Duisterhof, Zhao Mandi, Yunchao Yao, Jia-Wei Liu, Mike Zheng Shou, Shuran Song, Jeffrey Ichnowski

MD-Splatting builds on recent advances in Gaussian splatting, a method that learns the properties of a large number of Gaussians for state-of-the-art and fast novel view synthesis.

Novel View Synthesis

Learning to Efficiently Plan Robust Frictional Multi-Object Grasps

no code implementations13 Oct 2022 Wisdom C. Agboh, Satvik Sharma, Kishore Srinivas, Mallika Parulekar, Gaurav Datta, Tianshuang Qiu, Jeffrey Ichnowski, Eugen Solowjow, Mehmet Dogar, Ken Goldberg

In physical experiments, we find a 13. 7% increase in success rate, a 1. 6x increase in picks per hour, and a 6. 3x decrease in grasp planning time compared to prior work on multi-object grasping.

Friction Object

Multi-Object Grasping in the Plane

no code implementations1 Jun 2022 Wisdom C. Agboh, Jeffrey Ichnowski, Ken Goldberg, Mehmet R. Dogar

In physical grasping experiments comparing performance with a single-object picking baseline, we find that the frictionless multi-object grasping system achieves 13. 6\% higher grasp success and is 59. 9\% faster, from 212 PPH to 340 PPH.


Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models

no code implementations8 Mar 2022 Vincent Lim, Ellen Novoseller, Jeffrey Ichnowski, Huang Huang, Ken Goldberg

For applications in healthcare, physics, energy, robotics, and many other fields, designing maximally informative experiments is valuable, particularly when experiments are expensive, time-consuming, or pose safety hazards.

Experimental Design reinforcement-learning +1

Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects

1 code implementation27 Oct 2021 Jeffrey Ichnowski, Yahav Avigal, Justin Kerr, Ken Goldberg

The ability to grasp and manipulate transparent objects is a major challenge for robots.

Transparent objects

Accelerating Quadratic Optimization with Reinforcement Learning

1 code implementation NeurIPS 2021 Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato, Goran Banjac, Michael Luo, Francesco Borrelli, Joseph E. Gonzalez, Ion Stoica, Ken Goldberg

First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved.

reinforcement-learning Reinforcement Learning (RL)

Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms

no code implementations29 May 2021 Shivin Devgon, Jeffrey Ichnowski, Ashwin Balakrishna, Harry Zhang, Ken Goldberg

We formulate a self-supervised objective for this problem and train a deep neural network to estimate the 3D rotation as parameterized by a quaternion, between these current and desired depth images.

Self-Supervised Learning

Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables

no code implementations10 Nov 2020 Harry Zhang, Jeffrey Ichnowski, Daniel Seita, Jonathan Wang, Huang Huang, Ken Goldberg

The framework finds a 3D apex point for the robot arm, which, together with a task-specific trajectory function, defines an arcing motion that dynamically manipulates the cable to perform tasks with varying obstacle and target locations.

Self-Supervised Learning

Untangling Dense Knots by Learning Task-Relevant Keypoints

no code implementations10 Nov 2020 Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Jeffrey Ichnowski, Ashwin Balakrishna, Minho Hwang, Vainavi Viswanath, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

HULK successfully untangles a cable from a dense initial configuration containing up to two overhand and figure-eight knots in 97. 9% of 378 simulation experiments with an average of 12. 1 actions per trial.

Efficiently Calibrating Cable-Driven Surgical Robots with RGBD Fiducial Sensing and Recurrent Neural Networks

no code implementations19 Mar 2020 Minho Hwang, Brijen Thananjeyan, Samuel Paradis, Daniel Seita, Jeffrey Ichnowski, Danyal Fer, Thomas Low, Ken Goldberg

Automation of surgical subtasks using cable-driven robotic surgical assistants (RSAs) such as Intuitive Surgical's da Vinci Research Kit (dVRK) is challenging due to imprecision in control from cable-related effects such as cable stretching and hysteresis.

GOMP: Grasp-Optimized Motion Planning for Bin Picking

no code implementations5 Mar 2020 Jeffrey Ichnowski, Michael Danielczuk, Jingyi Xu, Vishal Satish, Ken Goldberg

Rapid and reliable robot bin picking is a critical challenge in automating warehouses, often measured in picks-per-hour (PPH).


Applying Depth-Sensing to Automated Surgical Manipulation with a da Vinci Robot

no code implementations15 Feb 2020 Minho Hwang, Daniel Seita, Brijen Thananjeyan, Jeffrey Ichnowski, Samuel Paradis, Danyal Fer, Thomas Low, Ken Goldberg

We report experimental results for a handover-free version of the peg transfer task, performing 20 and 5 physical episodes with single- and bilateral-arm setups, respectively.


Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor

1 code implementation23 Sep 2019 Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Katsu Yamane, Soshi Iba, John Canny, Ken Goldberg

In 180 physical experiments with the da Vinci Research Kit (dVRK) surgical robot, RGBD policies trained in simulation attain coverage of 83% to 95% depending on difficulty tier, suggesting that effective fabric smoothing policies can be learned from an algorithmic supervisor and that depth sensing is a valuable addition to color alone.

Imitation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.