b'Stephen James'

research

∙ 08/31/2023

Language-Conditioned Path Planning

Contact is at the core of robotic manipulation. At times, it is desired ...

0 Amber Xie, et al. ∙

research

∙ 08/23/2023

Language Reward Modulation for Pretraining Reinforcement Learning

Using learned reward functions (LRFs) as a means to solve sparse-reward ...

0 Ademi Adeniji, et al. ∙

research

∙ 02/05/2023

Multi-View Masked World Models for Visual Robotic Manipulation

Visual robotic manipulation research and applications often use multiple...

0 Younggyo Seo, et al. ∙

research

∙ 11/03/2022

StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS

Most existing methods for category-level pose estimation rely on object ...

0 Kai Chen, et al. ∙

research

∙ 10/25/2022

Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data

Autonomous driving is complex, requiring sophisticated 3D scene understa...

0 John So, et al. ∙

research

∙ 10/06/2022

Real-World Robot Learning with Masked Visual Pre-training

In this work, we explore self-supervised visual pre-training on images f...

15 Ilija Radosavovic, et al. ∙

research

∙ 10/05/2022

Temporally Consistent Video Transformer for Long-Term Video Prediction

Generating long, temporally consistent video remains an open challenge i...

0 Wilson Yan, et al. ∙

research

∙ 09/15/2022

HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator

Video prediction is an important yet challenging problem; burdened with ...

0 Younggyo Seo, et al. ∙

research

∙ 06/28/2022

Masked World Models for Visual Control

Visual model-based reinforcement learning (RL) has the potential to enab...

0 Younggyo Seo, et al. ∙

research

∙ 06/08/2022

Patch-based Object-centric Transformers for Efficient Video Generation

In this work, we present Patch-based Object-centric Video Transformer (P...

0 Wilson Yan, et al. ∙

research

∙ 06/07/2022

On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning

Intelligent agents should have the ability to leverage knowledge from pr...

0 Zhao Mandi, et al. ∙

research

∙ 04/26/2022

Coarse-to-fine Q-attention with Tree Expansion

Coarse-to-fine Q-attention enables sample-efficient robot manipulation b...

2 Stephen James, et al. ∙

research

∙ 04/14/2022

Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin-picking

In this paper, we propose an iterative self-training framework for sim-t...

4 Kai Chen, et al. ∙

research

∙ 04/04/2022

Coarse-to-Fine Q-attention with Learned Path Ranking

We propose Learned Path Ranking (LPR), a method that accepts an end-effe...

6 Stephen James, et al. ∙

research

∙ 03/25/2022

Reinforcement Learning with Action-Free Pre-Training from Videos

Recent unsupervised pre-training methods have shown to be effective on l...

0 Younggyo Seo, et al. ∙

research

∙ 02/22/2022

ReorientBot: Learning Object Reorientation for Specific-Posed Placement

Robots need the capability of placing objects in arbitrary, specific pos...

6 Kentaro Wada, et al. ∙

research

∙ 02/11/2022

SafePicking: Learning Safe Object Extraction via Object-Level Mapping

Robots need object-level scene understanding to manipulate objects while...

0 Kentaro Wada, et al. ∙

research

∙ 02/08/2022

Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning

We propose a new policy parameterization for representing 3D rotations d...

0 Stephen James, et al. ∙

research

∙ 02/07/2022

Auto-Lambda: Disentangling Dynamic Task Relationships

Understanding the structure of multiple related tasks allows for multi-t...

0 Shikun Liu, et al. ∙

research

∙ 06/23/2021

Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation

Reflecting on the last few years, the biggest breakthroughs in deep rein...

0 Stephen James, et al. ∙

research

∙ 05/31/2021

Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

Despite the success of reinforcement learning methods, they have yet to ...

0 Stephen James, et al. ∙

research

∙ 03/30/2021

SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks

By estimating 3D shape and instances from a single view, we can capture ...

8 Zoe Landgraf, et al. ∙

research

∙ 02/15/2021

End-to-End Egospheric Spatial Memory

Spatial memory, or the ability to remember and recall specific locations...

8 Daniel Lenton, et al. ∙

research

∙ 02/04/2021

Ivy: Templated Deep Learning for Inter-Framework Portability

We introduce Ivy, a templated Deep Learning (DL) framework which abstrac...

12 Daniel Lenton, et al. ∙

research

∙ 04/09/2020

MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion

Robots and other smart devices need efficient object-based scene represe...

13 Kentaro Wada, et al. ∙

research

∙ 11/04/2019

Learning One-Shot Imitation from Humans without Humans

Humans can naturally learn to execute a new task by seeing it performed ...

28 Alessandro Bonardi, et al. ∙

research

∙ 09/26/2019

RLBench: The Robot Learning Benchmark Learning Environment

We present a challenging new benchmark and learning-environment for robo...

21 Stephen James, et al. ∙

research

∙ 06/26/2019

PyRep: Bringing V-REP to Deep Robot Learning

PyRep is a toolkit for robot learning research, built on top of the virt...

0 Stephen James, et al. ∙

research

∙ 12/18/2018

Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks

Real world data, especially in the domain of robotics, is notoriously co...

8 Stephen James, et al. ∙

research

∙ 10/08/2018

Task-Embedded Control Networks for Few-Shot Imitation Learning

Much like humans, robots should have the ability to leverage knowledge f...

8 Stephen James, et al. ∙

research

∙ 06/20/2018

Sim-to-Real Reinforcement Learning for Deformable Object Manipulation

We have seen much recent progress in rigid object manipulation, but inte...

0 Jan Matas, et al. ∙

research

∙ 09/13/2016

3D Simulation for Robot Arm Control with Deep Q-Learning

Recent trends in robot arm control have seen a shift towards end-to-end ...

0 Stephen James, et al. ∙

Stephen James

Featured Co-authors