Stephen James

Previous PI of the Robot Learning Lab, London.

people/stephen_james.jpg

Previous PI

Robot Learning Lab

London

I was previously the principal investigator of the Robot Learning Lab in London, UK, where I lead a large concentration of the top Robot Learning talent in the world. My interests lie in investigating how to get robots to learn practical skills and behaviours in a data-driven manner, without explicitly needing to hard-code steps for each new task. My work lies on the intersection of reinforcement learning, imitation learning, and unsupervised representation learning. Previously, I was a postdoctoral fellow at UC Berkeley, advised by Pieter Abbeel, and prior to that, I completed my PhD at Imperial College London, under the supervision of Andrew Davison. I serve as area chair for NeurIPS, CVPR, ICML, and ICLR. For a formal bio, please see here.

selected publications

  1. shridhar_genima.gif
    Generative Image as Action Models
    Mohit Shridhar, Yat Long Lo, and Stephen James
    arXiv preprint arXiv:2407.07875, 2024
  2. eugene_greenaug.gif
    Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation
    Eugene Teoh, Sumit Patidar, Xiao Ma, and Stephen James
    arXiv preprint arXiv:2407.07868, 2024
  3. chernyadev_bigym.gif
    BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark
    Nikita Chernyadev, Nicholas Backshall, Xiao Ma, Yunfan Lu, Younggyo Seo, and Stephen James
    arXiv preprint arXiv:2407.07788, 2024
  4. seo_cqn.gif
    Continuous Control with Coarse-to-fine Reinforcement Learning
    Younggyo Seo, Jafar Uruç, and Stephen James
    arXiv preprint arXiv:2407.07787, 2024
  5. vosylius_randd.gif
    Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning
    Vitalis Vosylius, Younggyo Seo, Jafar Uruç, and Stephen James
    Robotics: Science and Systems, 2024
  6. xie_lapp.gif
    Language-conditioned path planning
    Amber Xie, Youngwoon Lee, Pieter Abbeel, and Stephen James
    Conference on Robot Learning, 2023
  7. james_c2f.gif
    Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation
    Stephen James, Kentaro Wada, Tristan Laidlow, and Andrew J Davison
    Conference on Computer Vision and Pattern Recognition, 2022
  8. james_rlbench.jpg
    RLBench: The Robot Learning Benchmark & Learning Environment
    Stephen James, Zicong Ma, David Rovick Arrojo, and Andrew J Davison
    IEEE Robotics and Automation Letters, 2020
  9. james_rcan.gif
    Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks
    Stephen James, Paul Wohlhart, Mrinal Kalakrishnan, Dmitry Kalashnikov, Alex Irpan, Julian Ibarz, Sergey Levine, Raia Hadsell, and Konstantinos Bousmalis
    Conference on Computer Vision and Pattern Recognition, 2019
  10. james_dr.gif
    Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task
    Stephen James, Andrew J Davison, and Edward Johns
    Conference on Robot Learning, 2017