Search Results for author: Stephen James

Found 40 papers, 25 papers with code

Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning

no code implementations28 May 2024 Vitalis Vosylius, Younggyo Seo, Jafar Uruç, Stephen James

In the field of Robot Learning, the complex mapping between high-dimensional observations such as RGB images and low-level robotic actions, two inherently very different spaces, constitutes a complex learning problem, especially with limited amounts of data.

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

no code implementations6 Mar 2024 Xiao Ma, Sumit Patidar, Iain Haughton, Stephen James

This paper introduces Hierarchical Diffusion Policy (HDP), a hierarchical agent for multi-task robotic manipulation.

Position

Language Reward Modulation for Pretraining Reinforcement Learning

1 code implementation23 Aug 2023 Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Younggyo Seo, Stephen James, Pieter Abbeel

Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years.

reinforcement-learning Reinforcement Learning (RL) +1

Multi-View Masked World Models for Visual Robotic Manipulation

1 code implementation5 Feb 2023 Younggyo Seo, Junsu Kim, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel

In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation.

Camera Calibration Representation Learning

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

no code implementations3 Nov 2022 Kai Chen, Stephen James, Congying Sui, Yun-hui Liu, Pieter Abbeel, Qi Dou

To further improve the performance of the stereo framework, StereoPose is equipped with a parallax attention module for stereo feature fusion and an epipolar loss for improving the stereo-view consistency of network predictions.

Object Pose Estimation +1

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

1 code implementation25 Oct 2022 John So, Amber Xie, Sunggoo Jung, Jeffrey Edlund, Rohan Thakker, Ali Agha-mohammadi, Pieter Abbeel, Stephen James

In this paper, we address this challenge by presenting Sim2Seg, a re-imagining of RCAN that crosses the visual reality gap for off-road autonomous driving, without using any real-world data.

Autonomous Driving Reinforcement Learning (RL) +2

Real-World Robot Learning with Masked Visual Pre-training

1 code implementation6 Oct 2022 Ilija Radosavovic, Tete Xiao, Stephen James, Pieter Abbeel, Jitendra Malik, Trevor Darrell

Finally, we train a 307M parameter vision transformer on a massive collection of 4. 5M images from the Internet and egocentric videos, and demonstrate clearly the benefits of scaling visual pre-training for robot learning.

Temporally Consistent Transformers for Video Generation

1 code implementation5 Oct 2022 Wilson Yan, Danijar Hafner, Stephen James, Pieter Abbeel

To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world.

Video Generation Video Prediction

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

no code implementations15 Sep 2022 Younggyo Seo, Kimin Lee, Fangchen Liu, Stephen James, Pieter Abbeel

Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics.

Data Augmentation Video Prediction +1

Masked World Models for Visual Control

no code implementations28 Jun 2022 Younggyo Seo, Danijar Hafner, Hao liu, Fangchen Liu, Stephen James, Kimin Lee, Pieter Abbeel

Yet the current approaches typically train a single model end-to-end for learning both visual representations and dynamics, making it difficult to accurately model the interaction between robots and small objects.

Model-based Reinforcement Learning Reinforcement Learning (RL) +1

Patch-based Object-centric Transformers for Efficient Video Generation

1 code implementation8 Jun 2022 Wilson Yan, Ryo Okumura, Stephen James, Pieter Abbeel

In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos.

Object Video Editing +2

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

no code implementations7 Jun 2022 Zhao Mandi, Pieter Abbeel, Stephen James

From these findings, we advocate for evaluating future meta-RL methods on more challenging tasks and including multi-task pretraining with fine-tuning as a simple, yet strong baseline.

Meta-Learning Meta Reinforcement Learning +4

Coarse-to-fine Q-attention with Tree Expansion

1 code implementation26 Apr 2022 Stephen James, Pieter Abbeel

Coarse-to-fine Q-attention enables sample-efficient robot manipulation by discretizing the translation space in a coarse-to-fine manner, where the resolution gradually increases at each layer in the hierarchy.

Robot Manipulation

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

no code implementations14 Apr 2022 Kai Chen, Rui Cao, Stephen James, Yichuan Li, Yun-hui Liu, Pieter Abbeel, Qi Dou

To continuously improve the quality of pseudo labels, we iterate the above steps by taking the trained student model as a new teacher and re-label real data using the refined teacher model.

6D Pose Estimation using RGB Robotic Grasping

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

1 code implementation4 Apr 2022 Stephen James, Pieter Abbeel

We propose Learned Path Ranking (LPR), a method that accepts an end-effector goal pose, and learns to rank a set of goal-reaching paths generated from an array of path generating methods, including: path planning, Bezier curve sampling, and a learned policy.

Benchmarking

Reinforcement Learning with Action-Free Pre-Training from Videos

2 code implementations25 Mar 2022 Younggyo Seo, Kimin Lee, Stephen James, Pieter Abbeel

Our framework consists of two phases: we pre-train an action-free latent video prediction model, and then utilize the pre-trained representations for efficiently learning action-conditional world models on unseen environments.

reinforcement-learning Reinforcement Learning (RL) +2

ReorientBot: Learning Object Reorientation for Specific-Posed Placement

1 code implementation22 Feb 2022 Kentaro Wada, Stephen James, Andrew J. Davison

Robots need the capability of placing objects in arbitrary, specific poses to rearrange the world and achieve various valuable tasks.

Motion Planning Object +2

SafePicking: Learning Safe Object Extraction via Object-Level Mapping

1 code implementation11 Feb 2022 Kentaro Wada, Stephen James, Andrew J. Davison

We evaluate our methods using the YCB objects in both simulation and the real world, achieving safe object extraction from piles.

Motion Planning Object +2

Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning

1 code implementation8 Feb 2022 Stephen James, Pieter Abbeel

We propose a new policy parameterization for representing 3D rotations during reinforcement learning.

Continuous Control reinforcement-learning +2

Auto-Lambda: Disentangling Dynamic Task Relationships

1 code implementation7 Feb 2022 Shikun Liu, Stephen James, Andrew J. Davison, Edward Johns

Unlike previous methods where task relationships are assumed to be fixed, Auto-Lambda is a gradient-based meta learning framework which explores continuous, dynamic task relationships via task-specific weightings, and can optimise any choice of combination of tasks through the formulation of a meta-loss; where the validation loss automatically influences task weightings throughout training.

Ranked #3 on Robot Manipulation on RLBench (Succ. Rate (10 tasks, 100 demos/task) metric)

Auxiliary Learning Meta-Learning +2

Autoregressive Latent Video Prediction with High-Fidelity Image Generator

no code implementations29 Sep 2021 Younggyo Seo, Kimin Lee, Fangchen Liu, Stephen James, Pieter Abbeel

Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics.

Data Augmentation Video Prediction +1

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

1 code implementation CVPR 2022 Stephen James, Kentaro Wada, Tristan Laidlow, Andrew J. Davison

We present a coarse-to-fine discretisation method that enables the use of discrete reinforcement learning approaches in place of unstable and data-inefficient actor-critic methods in continuous robotics domains.

Continuous Control Q-Learning +2

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

1 code implementation31 May 2021 Stephen James, Andrew J. Davison

Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks.

reinforcement-learning Reinforcement Learning (RL) +1

Waypoint Planning Networks

1 code implementation1 May 2021 Alexandru-Iosif Toma, Hussein Ali Jaafar, Hao-Ya Hsueh, Stephen James, Daniel Lenton, Ronald Clark, Sajad Saeedi

We propose waypoint planning networks (WPN), a hybrid algorithm based on LSTMs with a local kernel - a classic algorithm such as A*, and a global kernel using a learned algorithm.

Motion Planning

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

no code implementations ICCV 2021 Zoe Landgraf, Raluca Scona, Tristan Laidlow, Stephen James, Stefan Leutenegger, Andrew J. Davison

At test time, our model can generate 3D shape and instance segmentation from a single depth view, probabilistically sampling proposals for the occluded region from the learned latent space.

Instance Segmentation Segmentation +2

End-to-End Egospheric Spatial Memory

2 code implementations15 Feb 2021 Daniel Lenton, Stephen James, Ronald Clark, Andrew J. Davison

Spatial memory, or the ability to remember and recall specific locations and objects, is central to autonomous agents' ability to carry out tasks in real environments.

General Reinforcement Learning Imitation Learning +3

Ivy: Templated Deep Learning for Inter-Framework Portability

1 code implementation4 Feb 2021 Daniel Lenton, Fabio Pardo, Fabian Falck, Stephen James, Ronald Clark

We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.

Attention-driven Robotic Manipulation

no code implementations1 Jan 2021 Stephen James, Andrew Davison

Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks.

reinforcement-learning Reinforcement Learning (RL)

Ego-Centric Spatial Memory Networks

no code implementations ICLR 2021 Daniel James Lenton, Stephen James, Ronald Clark, Andrew Davison

With our broad demonstrations, we show that ESMN represents a useful and general computation graph for embodied spatial reasoning, and the module forms a bridge between real-time mapping systems and differentiable memory architectures.

Inductive Bias Semantic Segmentation

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

1 code implementation CVPR 2020 Kentaro Wada, Edgar Sucar, Stephen James, Daniel Lenton, Andrew J. Davison

Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion.

6D Pose Estimation Object

Learning One-Shot Imitation from Humans without Humans

1 code implementation4 Nov 2019 Alessandro Bonardi, Stephen James, Andrew J. Davison

But is there a way to remove the need for real world human demonstrations during training?

Imitation Learning Meta-Learning

PyRep: Bringing V-REP to Deep Robot Learning

1 code implementation26 Jun 2019 Stephen James, Marc Freese, Andrew J. Davison

PyRep is a toolkit for robot learning research, built on top of the virtual robotics experimentation platform (V-REP).

Imitation Learning reinforcement-learning +1

Task-Embedded Control Networks for Few-Shot Imitation Learning

3 code implementations8 Oct 2018 Stephen James, Michael Bloesch, Andrew J. Davison

Despite this, most robot learning approaches have focused on learning a single task, from scratch, with a limited notion of generalisation, and no way of leveraging the knowledge to learn other tasks more efficiently.

Few-Shot Imitation Learning Imitation Learning +1

Sim-to-Real Reinforcement Learning for Deformable Object Manipulation

1 code implementation20 Jun 2018 Jan Matas, Stephen James, Andrew J. Davison

Moreover, due to the large amount of data needed to learn these end-to-end solutions, an emerging trend is to learn control policies in simulation and then transfer them over to the real world.

Deformable Object Manipulation Object +2

Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task

1 code implementation7 Jul 2017 Stephen James, Andrew J. Davison, Edward Johns

End-to-end control for robot manipulation and grasping is emerging as an attractive alternative to traditional pipelined approaches.

Robotic Grasping Robot Manipulation

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

no code implementations13 Sep 2016 Stephen James, Edward Johns

Building upon the recent success of deep Q-networks, we present an approach which uses 3D simulations to train a 7-DOF robotic arm in a control task without any prior knowledge.

Q-Learning

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